diff --git a/project.Makefile b/project.Makefile index 2302f9cfe2..cc4c73ef21 100644 --- a/project.Makefile +++ b/project.Makefile @@ -421,7 +421,7 @@ assets/ncbi_mappings/ncbi_attribute_mappings_filled.tsv: assets/ncbi_mappings/nc $(RUN) nmdc-ncbi-mapping ignore-import-schema-slots $@ -src/data/valid/Database-interleaved-new.yaml: src/schema/nmdc.yaml +src/data/valid/Database-interleaved.yaml: src/schema/nmdc.yaml $(RUN) interleave-yaml \ --directory-path src/data/valid \ --output-file $@ \ diff --git a/src/data/valid/Database-interleaved.yaml b/src/data/valid/Database-interleaved.yaml index b8126a33ae..9714c80f29 100644 --- a/src/data/valid/Database-interleaved.yaml +++ b/src/data/valid/Database-interleaved.yaml @@ -1,4234 +1,2680 @@ -workflow_execution_set: - - id: nmdc:wfmtas-99-v9w6y.1 - type: nmdc:MetatranscriptomeAssembly - asm_score: 0.85 - ctg_n50: 10000.0 - ended_at_time: '2023-08-04T14:00:00Z' - execution_resource: NERSC-Perlmutter - git_url: https://github.com/microbiomedata/metatranscriptome_assembly/releases/tag/v1.2.3 - name: human gut metatranscriptome assembly - scaf_bp: 567890123.0 - scaffolds: 1234.0 - started_at_time: '2023-08-04T08:00:00Z' - was_informed_by: nmdc:dgns-12-dk484s - has_input: - - nmdc:dobj-99-7l49z - has_output: - - nmdc:dobj-99-9t74d - - id: nmdc:wfmp-99-74d83.1 - type: nmdc:MetaproteomicsAnalysis - name: soil metaproteomics analysis - has_input: - - nmdc:dobj-99-74d83z - has_output: - - nmdc:dobj-99-74d83 - ended_at_time: '2023-08-11T17:00:00Z' - execution_resource: EMSL - git_url: https://github.com/microbiomedata/metaproteomics_analysis/releases/tag/v0.6.3 - was_informed_by: nmdc:dgms-12-384j8d - started_at_time: '2023-08-11T11:00:00Z' - metaproteomics_analysis_category: matched_metagenome -material_processing_set: - - id: nmdc:cspro-99-oW43DzG0 - type: nmdc:ChromatographicSeparationProcess - has_input: - - nmdc:procsm-99-9gjxns61 - has_output: - - nmdc:procsm-99-05g48p90 - - nmdc:procsm-99-05g48p91 - stationary_phase: "CN" - chromatographic_category: solid_phase_extraction - ordered_mobile_phases: - - type: nmdc:MobilePhaseSegment - substances_used: - - known_as: glucose - type: nmdc:PortionOfSubstance - final_concentration: - type: nmdc:QuantityValue - has_unit: '%' - has_numeric_value: 10 - volume: - type: nmdc:QuantityValue - has_numeric_value: 700 - has_unit: mL - - type: nmdc:MobilePhaseSegment - substances_used: - - known_as: water - type: nmdc:PortionOfSubstance - final_concentration: - type: nmdc:QuantityValue - has_unit: mM - has_numeric_value: 15 - volume: - type: nmdc:QuantityValue - has_numeric_value: 700 - has_unit: mL - - id: nmdc:subspr-99-oW43DzG0 - type: nmdc:SubSamplingProcess - has_input: - - nmdc:bsm-99-oW43DzG1 - container_size: - type: nmdc:QuantityValue - has_numeric_value: 50 - has_unit: mL - contained_in: v-bottom_conical_tube - volume: - type: nmdc:QuantityValue - has_numeric_value: 20 - has_unit: mL - temperature: - type: nmdc:QuantityValue - has_numeric_value: 25 - has_unit: C - mass: +biosample_set: +- id: nmdc:bsm-99-dtTMNb + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + rna_volume: 12.0 +- id: nmdc:bsm-99-dtTMNc + type: nmdc:Biosample + name: Lithgow State Coal Mine Calcium nutrients (early) + description: Bulk Aqueous phase filtered water + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + gold_biosample_identifiers: + - gold:Gb0101224 + ecosystem: Environmental + ecosystem_category: Aquatic + ecosystem_subtype: Groundwater + ecosystem_type: Freshwater + geo_loc_name: + type: nmdc:TextValue + has_raw_value: Lithgow + lat_lon: + type: nmdc:GeolocationValue + has_raw_value: -33.460524 150.168149 + latitude: -33.460524 + longitude: 150.168149 + samp_taxon_id: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: coal metagenome [NCBITaxon:1260732] + term: + id: NCBITaxon:1260732 + type: nmdc:OntologyClass + name: coal metagenome + specific_ecosystem: Coalbed water + add_date: 28-JUL-14 12.00.00.000000000 AM + community: microbial communities + habitat: Coalbed water + location: from the Lithgow State Coal Mine, New South Wales, Australia + mod_date: 26-AUG-16 01.50.27.000000000 PM + ncbi_taxonomy_name: coal metagenome + sample_collection_site: Lithgow State Coal Mine +- id: nmdc:bsm-99-AtTUOs + type: nmdc:Biosample + name: Lithgow State Coal Mine Calcium nutrients (early) + description: Bulk Aqueous phase filtered water + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + biosample_categories: + - LTER + - SIP + gold_biosample_identifiers: + - gold:Gb0101224 + ecosystem: Environmental + ecosystem_category: Aquatic + ecosystem_subtype: Groundwater + ecosystem_type: Freshwater + geo_loc_name: + type: nmdc:TextValue + has_raw_value: Lithgow + lat_lon: + type: nmdc:GeolocationValue + has_raw_value: -33.460524 150.168149 + latitude: -33.460524 + longitude: 150.168149 + samp_taxon_id: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: coal metagenome [NCBITaxon:1260732] + term: + id: NCBITaxon:1260732 + type: nmdc:OntologyClass + name: coal metagenome + specific_ecosystem: Coalbed water + add_date: 28-JUL-14 12.00.00.000000000 AM + community: microbial communities + habitat: Coalbed water + location: from the Lithgow State Coal Mine, New South Wales, Australia + mod_date: 26-AUG-16 01.50.27.000000000 PM + ncbi_taxonomy_name: coal metagenome + sample_collection_site: Lithgow State Coal Mine +- id: nmdc:bsm-99-eBVHjN + type: nmdc:Biosample + name: Lithgow State Coal Mine Calcium nutrients Extra + description: Bulk Aqueous phase filtered water + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + gold_biosample_identifiers: + - gold:Gb0101225 + ecosystem: Environmental + ecosystem_category: Aquatic + ecosystem_subtype: Groundwater + ecosystem_type: Freshwater + geo_loc_name: + type: nmdc:TextValue + has_raw_value: Lithgow + lat_lon: + type: nmdc:GeolocationValue + has_raw_value: -33.460524 150.168149 + latitude: -33.460524 + longitude: 150.168149 + samp_taxon_id: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: coal metagenome [NCBITaxon:1260732] + term: + id: NCBITaxon:1260732 + type: nmdc:OntologyClass + name: coal metagenome + specific_ecosystem: Coalbed water + add_date: 28-JUL-14 12.00.00.000000000 AM + community: microbial communities + habitat: Coalbed water + location: from the Lithgow State Coal Mine, New South Wales, Australia + mod_date: 26-AUG-16 01.50.27.000000000 PM + ncbi_taxonomy_name: coal metagenome + sample_collection_site: Lithgow State Coal Mine +- id: nmdc:bsm-99-TDPHTh + type: nmdc:Biosample + name: Lithgow State Coal Mine Calcium nutrients + description: Bulk Aqueous phase filtered water + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + gold_biosample_identifiers: + - gold:Gb0101226 + ecosystem: Environmental + ecosystem_category: Aquatic + ecosystem_subtype: Groundwater + ecosystem_type: Freshwater + geo_loc_name: + type: nmdc:TextValue + has_raw_value: Lithgow + lat_lon: + type: nmdc:GeolocationValue + has_raw_value: -33.460524 150.168149 + latitude: -33.460524 + longitude: 150.168149 + samp_taxon_id: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: coal metagenome [NCBITaxon:1260732] + term: + id: NCBITaxon:1260732 + type: nmdc:OntologyClass + name: coal metagenome + specific_ecosystem: Coalbed water + add_date: 28-JUL-14 12.00.00.000000000 AM + community: microbial communities + habitat: Coalbed water + location: from the Lithgow State Coal Mine, New South Wales, Australia + mod_date: 26-AUG-16 01.50.27.000000000 PM + ncbi_taxonomy_name: coal metagenome + sample_collection_site: Lithgow State Coal Mine +- id: nmdc:bsm-99-dtTMNd + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + dna_cont_well: B2 + dna_cont_type: plate +- id: nmdc:bsm-99-000001 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + dna_cont_well: A10 + dna_cont_type: plate +- id: nmdc:bsm-99-000002 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + dna_cont_well: A11 + dna_cont_type: plate +- id: nmdc:bsm-99-000003 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + dna_cont_well: H10 + dna_cont_type: plate +- id: nmdc:bsm-99-000004 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + dna_cont_well: H11 + dna_cont_type: plate +- id: nmdc:bsm-99-000005 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + dna_cont_well: C1 + dna_cont_type: plate +- id: nmdc:bsm-99-000006 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + dna_cont_well: C12 + dna_cont_type: plate +- id: nmdc:bsm-99-dtTMNe + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + dna_cont_type: tube +- id: nmdc:bsm-99-dtTMNf + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + infiltrations: + - 00:01:32 + - 00:00:53 +- id: nmdc:bsm-99-abcdef + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + infiltrations: + - 00:02:54 +- id: nmdc:bsm-99-qwerty + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + infiltrations: + - 01:24:03 + - 00:02:33 + - 00:02:02 +- id: nmdc:bsm-99-dtTMNg + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass +- id: nmdc:bsm-99-dtTMNh + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + rna_cont_type: plate + rna_cont_well: B2 +- id: nmdc:bsm-99-000007 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + rna_cont_type: plate + rna_cont_well: A10 +- id: nmdc:bsm-99-000008 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + rna_cont_type: plate + rna_cont_well: A11 +- id: nmdc:bsm-99-000009 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + rna_cont_type: plate + rna_cont_well: H10 +- id: nmdc:bsm-99-0000010 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + rna_cont_type: plate + rna_cont_well: H11 +- id: nmdc:bsm-99-0000011 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + rna_cont_type: plate + rna_cont_well: C1 +- id: nmdc:bsm-99-0000012 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + rna_cont_type: plate + rna_cont_well: C12 +- id: nmdc:bsm-99-dtTMNi + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + rna_cont_type: tube +- id: nmdc:bsm-99-J9FcnC + type: nmdc:Biosample + name: Root microbial communities from poplar common garden site in Clatskanie, Oregon, + USA - BESC-13-CL1_35_33 endosphere + description: Root microbial communities from poplar common garden site in Clatskanie, + Oregon, USA + associated_studies: + - nmdc:sty-99-U21mUX + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + collected_from: nmdc:frsite-99-SPreao + gold_biosample_identifiers: + - gold:Gb0305833 +- id: nmdc:bsm-99-BdlWdQ + type: nmdc:Biosample + name: Rhizosphere soil microbial communities from poplar common garden site in Clatskanie, + Oregon, USA - BESC-13-CL1_35_33 + description: Rhizosphere soil microbial communities from poplar common garden site + in Clatskanie, Oregon, USA + associated_studies: + - nmdc:sty-99-U21mUX + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + collected_from: nmdc:frsite-99-SPreao + gold_biosample_identifiers: + - gold:Gb0291692 +- id: nmdc:bsm-99-vn74Wq + type: nmdc:Biosample + name: Bulk soil microbial communities from poplar common garden site in Clatskanie, + Oregon, USA - BESC-13-CL1_35_33 + description: Bulk soil microbial communities from poplar common garden site in Clatskanie, + Oregon, USA + associated_studies: + - nmdc:sty-99-U21mUX + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + collected_from: nmdc:frsite-99-SPreao + gold_biosample_identifiers: + - gold:Gb0291582 +- id: nmdc:bsm-99-P8FdpS + type: nmdc:Biosample + name: Root microbial communities from poplar common garden site in Clatskanie, Oregon, + USA - BESC-13-CL2_39_29 endosphere + description: Root microbial communities from poplar common garden site in Clatskanie, + Oregon, USA + associated_studies: + - nmdc:sty-99-U21mUX + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + collected_from: nmdc:frsite-99-h2mYFG + gold_biosample_identifiers: + - gold:Gb0305834 +- id: nmdc:bsm-99-ugBwz3 + type: nmdc:Biosample + name: Rhizosphere soil microbial communities from poplar common garden site in Clatskanie, + Oregon, USA - BESC-13-CL2_39_29 + description: Rhizosphere soil microbial communities from poplar common garden site + in Clatskanie, Oregon, USA + associated_studies: + - nmdc:sty-99-U21mUX + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + collected_from: nmdc:frsite-99-h2mYFG + gold_biosample_identifiers: + - gold:Gb0291693 +- id: nmdc:bsm-99-tN5lxM + type: nmdc:Biosample + name: Bulk soil microbial communities from poplar common garden site in Clatskanie, + Oregon, USA - BESC-13-CL2_39_29 + description: Bulk soil microbial communities from poplar common garden site in Clatskanie, + Oregon, USA + associated_studies: + - nmdc:sty-99-U21mUX + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + collected_from: nmdc:frsite-99-h2mYFG + gold_biosample_identifiers: + - gold:Gb0291583 +- id: nmdc:bsm-99-dtTMNj + type: nmdc:Biosample + name: real biosample from the field + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass +- id: nmdc:bsm-99-XYZ + type: nmdc:Biosample + name: one DNA library, like an analytical sample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass +- id: nmdc:bsm-99-abcdef1 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass +- id: nmdc:bsm-99-abcdef2 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass +- id: nmdc:bsm-99-abcdef3 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-00-abc123 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass +- id: nmdc:bsm-99-abcdef4 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-11-34xj1150 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass +- id: nmdc:bsm-99-abcdef5 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-11-34xj1150 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass +- id: nmdc:bsm-99-abcdef6 + type: nmdc:Biosample + associated_studies: + - nmdc:sty-11-34xj1150 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass +- id: nmdc:bsm-99-isqhuW + type: nmdc:Biosample + name: Permafrost microbial communities from Stordalen Mire, Sweden - 611E1M metaG + description: Permafrost microbial communities from Stordalen Mire, Sweden + associated_studies: + - nmdc:sty-00-8675309 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + samp_name: 11E1M metaG + gold_biosample_identifiers: + - gold:Gb0150408 + ecosystem: Environmental + ecosystem_category: Terrestrial + ecosystem_subtype: Wetlands + ecosystem_type: Soil + geo_loc_name: + type: nmdc:TextValue + has_raw_value: 'Sweden: Stordalen' + lat_lon: + type: nmdc:GeolocationValue + has_raw_value: 68.35 19.05 + latitude: 68.35 + longitude: 19.05 + specific_ecosystem: Permafrost + add_date: 17-MAR-17 04.55.54.717000000 PM + community: microbial communities + habitat: Fen + location: Stordalen Mire, Sweden + mod_date: 08-JAN-20 02.49.23.000000000 PM + ncbi_taxonomy_name: permafrost metagenome + sample_collection_site: Mire fen +- id: nmdc:bsm-99-dge3H9 + type: nmdc:Biosample + name: Forest soil microbial communities from Barre Woods Harvard Forest LTER site, + Petersham, Massachusetts, United States - Inc-BW-C-14-O + description: Forest soil from Barre Woods Harvard Forest LTER site was incubated + at 10C with heavy water. Sample is from a control plot at ambient soil temperature, + organic horizon - top 4cm of soil + associated_studies: + - nmdc:sty-00-8675309 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + samp_name: Inc-BW-C-14-O + gold_biosample_identifiers: + - gold:Gb0157174 + ecosystem: Environmental + ecosystem_category: Terrestrial + ecosystem_subtype: Unclassified + ecosystem_type: Soil + geo_loc_name: + type: nmdc:TextValue + has_raw_value: 'USA: Massachusetts' + lat_lon: + type: nmdc:GeolocationValue + has_raw_value: 42.481016 -72.178343 + latitude: 42.481016 + longitude: -72.178343 + specific_ecosystem: Forest Soil + add_date: 17-AUG-17 05.38.34.719000000 PM + community: microbial communities + habitat: soil + location: Barre Woods Harvard Forest LTER site, Petersham, Massachusetts, United + States + mod_date: 08-JAN-20 02.49.23.000000000 PM + ncbi_taxonomy_name: soil metagenome + sample_collection_site: forest soil +- id: nmdc:bsm-99-dc6tg6 + type: nmdc:Biosample + name: Rhizosphere microbial communities from Carex aquatilis grown in University + of Washington, Seatle, WA, United States - 4-1-23 metaG + description: Rhizosphere microbial communities from Carex aquatilis grown in submerged + peat from a thermokarst bog, University of Washington, Seatle, WA, United States + associated_studies: + - nmdc:sty-00-8675309 + env_broad_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002030 + term: + id: ENVO:00002030 + type: nmdc:OntologyClass + env_local_scale: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00002169 + term: + id: ENVO:00002169 + type: nmdc:OntologyClass + env_medium: + type: nmdc:ControlledIdentifiedTermValue + has_raw_value: ENVO:00005792 + term: + id: ENVO:00005792 + type: nmdc:OntologyClass + samp_name: 4-1-23 metaG + gold_biosample_identifiers: + - gold:Gb0188037 + ecosystem: Host-associated + ecosystem_category: Plants + ecosystem_subtype: Soil + ecosystem_type: Rhizosphere + geo_loc_name: + type: nmdc:TextValue + has_raw_value: 'USA: Seattle, Washington' + lat_lon: + type: nmdc:GeolocationValue + has_raw_value: 47.6516 -122.3045 + latitude: 47.6516 + longitude: -122.3045 + specific_ecosystem: Unclassified + add_date: 29-MAR-18 01.27.40.709000000 PM + community: microbial communities + habitat: rhizosphere + host_name: Carex aquatilis + location: University of Washington, Seatle, WA, United States + mod_date: 08-JAN-20 02.49.25.000000000 PM + ncbi_taxonomy_name: rhizosphere metagenome + sample_collection_site: Peat Soil +calibration_set: +- id: nmdc:calib-99-zUCd5Q + type: nmdc:CalibrationInformation + internal_calibration: false + calibration_target: retention_index + calibration_object: nmdc:dobj-12-krhrtjw9 + calibration_standard: fames +- id: nmdc:calib-14-93cjjw92 + type: nmdc:CalibrationInformation + name: GCMS FAMES calibration (GCMS_FAMEs_01_GCMS01_20160523) + description: Full scan GC-MS FAMES calibration run (GCMS_FAMEs_01_GCMS01_20160523) + internal_calibration: false + calibration_target: retention_index + calibration_object: nmdc:dobj-13-rf3br219 + calibration_standard: fames +- id: nmdc:calib-14-hhn3qb47 + type: nmdc:CalibrationInformation + name: Negative mode NOM reference calibration + description: Negative electrospray mode reference calibration for Natural Organic + Matter analysis + internal_calibration: false + calibration_target: mass_charge_ratio + calibration_object: nmdc:dobj-14-1e9qeq49 +collecting_biosamples_from_site_set: +- id: nmdc:clsite-99-Cq00d1 + type: nmdc:CollectingBiosamplesFromSite + name: Collection of biosamples from BESC-13-CL1_35_33 + has_input: + - nmdc:frsite-99-SPreao + has_output: + - nmdc:bsm-99-J9FcnC + - nmdc:bsm-99-BdlWdQ + - nmdc:bsm-99-vn74Wq +- id: nmdc:clsite-99-yzmLBN + type: nmdc:CollectingBiosamplesFromSite + name: Collection of biosamples from BESC-13-CL2_39_29 + has_input: + - nmdc:frsite-99-h2mYFG + has_output: + - nmdc:bsm-99-P8FdpS + - nmdc:bsm-99-ugBwz3 + - nmdc:bsm-99-tN5lxM +configuration_set: +- id: nmdc:mscon-99-oW43DzG1 + type: nmdc:MassSpectrometryConfiguration + name: EMSL lipidomics mass spectrometry method, positive polarity + description: Mass spectrometry method used by EMSL for lipidomics analysis, positive + polarity + mass_spectrometry_acquisition_strategy: data_dependent_acquisition + resolution_categories: + - high + - low + mass_analyzers: + - Orbitrap + - ion_trap + ionization_source: electrospray_ionization + mass_spectrum_collection_modes: + - full_profile + - centroid + polarity_mode: positive +- id: nmdc:mscon-99-oW43DzG2 + type: nmdc:MassSpectrometryConfiguration + name: EMSL lipidomics mass spectrometry method, negative polarity + description: Mass spectrometry method used by EMSL for lipidomics analysis, negative + polarity + mass_spectrometry_acquisition_strategy: data_dependent_acquisition + resolution_categories: + - high + - low + mass_analyzers: + - Orbitrap + - ion_trap + ionization_source: electrospray_ionization + mass_spectrum_collection_modes: + - full_profile + - centroid + polarity_mode: negative +- id: nmdc:chrcon-11-oW43DzG0 + type: nmdc:ChromatographyConfiguration + name: EMSL LC method for non-polar metabolites + description: LC method for non-polar metabolites used by EMSL + chromatographic_category: liquid_chromatography + stationary_phase: C18 + ordered_mobile_phases: + - type: nmdc:MobilePhaseSegment + duration: type: nmdc:QuantityValue - has_numeric_value: 30 - has_unit: g - has_output: - - nmdc:procsm-99-05g48p90 - sampled_portion: - - supernatant -storage_process_set: - - id: nmdc:storpr-99-zUCd5N + has_numeric_value: 60 + has_unit: min substances_used: - - known_as: acetonitrile - type: nmdc:PortionOfSubstance - final_concentration: - type: nmdc:QuantityValue - has_unit: '%' - has_numeric_value: 1 - contained_in: falcon_tube - start_date: "2021-01-14" - temperature: - type: nmdc:QuantityValue - has_unit: degrees Celsius - has_numeric_value: 80 - has_input: - - nmdc:procsm-99-dtTMNb - has_output: - - nmdc:procsm-78-BZAPKH - type: nmdc:StorageProcess - -material_processing_set: - - id: nmdc:cspro-99-xyzxyz - type: nmdc:ChromatographicSeparationProcess - has_input: - - nmdc:procsm-99-9gjxns61 - has_output: - - nmdc:procsm-99-05g48p90 - - nmdc:procsm-99-05g48p91 - stationary_phase: BEH-HILIC - chromatographic_category: liquid_chromatography - temperature: - type: nmdc:QuantityValue - has_numeric_value: 25 - has_unit: Cel - ordered_mobile_phases: - - type: nmdc:MobilePhaseSegment - duration: - type: nmdc:QuantityValue - has_unit: min - has_numeric_value: 60 - substances_used: - - known_as: water - type: nmdc:PortionOfSubstance - final_concentration: - type: nmdc:QuantityValue - has_unit: '%' - has_numeric_value: 10 - - type: nmdc:MobilePhaseSegment - substances_used: - - known_as: glucose - type: nmdc:PortionOfSubstance - final_concentration: - type: nmdc:QuantityValue - has_unit: mM - has_numeric_value: 15 + - type: nmdc:PortionOfSubstance + final_concentration: + type: nmdc:QuantityValue + has_numeric_value: 10 + has_unit: '%' + known_as: water + - type: nmdc:MobilePhaseSegment + substances_used: + - type: nmdc:PortionOfSubstance + final_concentration: + type: nmdc:QuantityValue + has_numeric_value: 15 + has_unit: mM + known_as: glucose + temperature: + type: nmdc:QuantityValue + has_numeric_value: 30 + has_unit: Cel +- id: nmdc:chrcon-99-oW43DzG1 + type: nmdc:ChromatographyConfiguration + name: EMSL GC method for small molecules + description: EMSL's Gas Chromatography method for small molecules + chromatographic_category: gas_chromatography + stationary_phase: Polysiloxane +- id: nmdc:mscon-99-oW43DzG0 + type: nmdc:MassSpectrometryConfiguration + name: EMSL EI mass spectrometry method for small molecules + description: Electron impact mass spectrometry method for small molecules + mass_spectrometry_acquisition_strategy: data_dependent_acquisition + resolution_categories: + - low + mass_analyzers: + - quadrupole + ionization_source: electron_ionization + mass_spectrum_collection_modes: + - centroid + polarity_mode: positive +data_generation_set: +- id: nmdc:dgms-99-zUCd5N + type: nmdc:MassSpectrometry + has_input: + - nmdc:procsm-11-0wxpzf08 + analyte_category: metabolome + associated_studies: + - nmdc:sty-00-555xxx + eluent_introduction_category: direct_infusion_syringe + has_mass_spectrometry_configuration: nmdc:mscon-11-e1vant11 +- id: nmdc:dgns-99-gKlQlF + type: nmdc:NucleotideSequencing + has_input: + - nmdc:procsm-11-0wxpzf08 + analyte_category: metagenome + associated_studies: + - nmdc:sty-00-555xxx +- id: nmdc:dgms-99-zUCd5O + type: nmdc:MassSpectrometry + has_input: + - nmdc:procsm-11-0wxpzf08 + analyte_category: metabolome + associated_studies: + - nmdc:sty-00-555xxx + eluent_introduction_category: direct_infusion_syringe + has_mass_spectrometry_configuration: nmdc:mscon-11-e1vant11 +- id: nmdc:dgns-99-zUCd5N + type: nmdc:NucleotideSequencing + name: Thawing permafrost microbial communities from the Arctic, studying carbon + transformations - Permafrost 712P3D + alternative_identifiers: + - gold:Gp0108335 + has_input: + - nmdc:bsm-00-red + has_output: + - nmdc:dobj-00-9n9n9n + processing_institution: JGI + analyte_category: metagenome + associated_studies: + - nmdc:sty-00-555xxx + add_date: 30-OCT-14 12.00.00.000000000 AM + mod_date: 22-MAY-20 06.13.12.927000000 PM + ncbi_project_name: Thawing permafrost microbial communities from the Arctic, studying + carbon transformations - Permafrost 712P3D +- id: nmdc:dgns-99-gKlQlG + type: nmdc:NucleotideSequencing + name: Thawing permafrost microbial communities from the Arctic, studying carbon + transformations - Permafrost 612S3M + alternative_identifiers: + - gold:Gp0108340 + has_input: + - nmdc:bsm-00-orange0 + has_output: + - nmdc:dobj-00-123456 + processing_institution: JGI + analyte_category: metagenome + associated_studies: + - nmdc:sty-00-555xxx + add_date: 30-OCT-14 12.00.00.000000000 AM + mod_date: 22-MAY-20 06.10.59.590000000 PM + ncbi_project_name: Thawing permafrost microbial communities from the Arctic, studying + carbon transformations - Permafrost 612S3M +- id: nmdc:dgns-99-5kgIJR + type: nmdc:NucleotideSequencing + name: Thawing permafrost microbial communities from the Arctic, studying carbon + transformations - Permafrost 712S3S + alternative_identifiers: + - gold:Gp0108341 + has_input: + - nmdc:bsm-00-orange1 + has_output: + - nmdc:dobj-00-thx1198 + processing_institution: JGI + analyte_category: metagenome + associated_studies: + - nmdc:sty-00-555xxx + add_date: 30-OCT-14 12.00.00.000000000 AM + mod_date: 22-MAY-20 06.09.46.171000000 PM + ncbi_project_name: Thawing permafrost microbial communities from the Arctic, studying + carbon transformations - Permafrost 712S3S +- id: nmdc:omprc-99-123456 + type: nmdc:NucleotideSequencing + name: Permafrost 712P3D + alternative_identifiers: + - gold:Gp0108335 + has_input: + - nmdc:bsm-00-red + has_output: + - nmdc:dobj-11-dtTMNb + processing_institution: JGI + analyte_category: metagenome + associated_studies: + - nmdc:sty-00-123456 + add_date: 30-OCT-14 12.00.00.000000000 AM + mod_date: 22-MAY-20 06.13.12.927000000 PM +- id: nmdc:dgms-99-zUCd5P + type: nmdc:MassSpectrometry + has_input: + - nmdc:procsm-11-0wxpzf08 + has_output: + - nmdc:dobj-00-msdem1 + start_date: 30-OCT-14 01.00.00.000000000 AM + end_date: 30-OCT-14 01.30.00.000000000 AM + analyte_category: lipidome + associated_studies: + - nmdc:sty-00-555xxx + add_date: 07-MAY-24 12.00.00.000000000 AM + mod_date: 07-MAY-24 12.00.00.000000000 AM + eluent_introduction_category: liquid_chromatography + has_mass_spectrometry_configuration: nmdc:mscon-99-oW43DzG1 + has_chromatography_configuration: nmdc:chrcon-11-oW43DzG0 +- id: nmdc:dgms-99-zUCd5x + type: nmdc:MassSpectrometry + has_input: + - nmdc:procsm-11-0wxpzf08 + has_output: + - nmdc:dobj-00-msdem2 + start_date: 31-OCT-14 01.00.00.000000000 AM + end_date: 31-OCT-14 01.30.00.000000000 AM + analyte_category: lipidome + associated_studies: + - nmdc:sty-00-555xxx + add_date: 07-MAY-24 12.00.00.000000000 AM + mod_date: 07-MAY-24 12.00.00.000000000 AM + eluent_introduction_category: liquid_chromatography + has_mass_spectrometry_configuration: nmdc:mscon-99-oW43DzG2 + has_chromatography_configuration: nmdc:chrcon-11-oW43DzG0 +- id: nmdc:dgms-99-oW43DzG1 + type: nmdc:MassSpectrometry + has_input: + - nmdc:procsm-11-9gjxns61 + has_output: + - nmdc:dobj-11-9n9n9n + analyte_category: metabolome + associated_studies: + - nmdc:sty-00-555xxx + eluent_introduction_category: gas_chromatography + has_mass_spectrometry_configuration: nmdc:mscon-99-oW43DzG0 + generates_calibration: nmdc:calib-99-zUCd5Q + has_chromatography_configuration: nmdc:chrcon-99-oW43DzG1 +- id: nmdc:dgms-99-oW43DzG2 + type: nmdc:MassSpectrometry + has_input: + - nmdc:procsm-11-9gjxns62 + has_output: + - nmdc:dobj-11-9n9n91 + analyte_category: metabolome + associated_studies: + - nmdc:sty-00-555xxx + eluent_introduction_category: gas_chromatography + has_mass_spectrometry_configuration: nmdc:mscon-99-oW43DzG0 + generates_calibration: nmdc:calib-99-zUCd5Q + has_chromatography_configuration: nmdc:chrcon-99-oW43DzG1 +- id: nmdc:dgms-13-122e4240 + type: nmdc:MassSpectrometry + name: Froze_Core_2015_S1_20_30_19_Metab + description: Full scan GC-MS (but not GC QExactive, which is EI-HMS) + alternative_identifiers: + - emsl:499777 + has_input: + - nmdc:bsm-13-kem2v355 + has_output: + - nmdc:dobj-13-vws2zc98 + processing_institution: EMSL + start_date: '2016-05-24 18:17:00.000' + end_date: '2016-05-24 18:54:29.000' + analyte_category: metabolome + associated_studies: + - nmdc:sty-11-aygzgv51 + instrument_used: + - nmdc:inst-14-fas8ny90 + mod_date: '2024-11-07T15:02:18' + eluent_introduction_category: gas_chromatography + has_mass_spectrometry_configuration: nmdc:mscon-14-5jk7rg60 + generates_calibration: nmdc:calib-14-dy7mc666 + has_chromatography_configuration: nmdc:chrcon-14-qpvt3v15 +- id: nmdc:dgns-99-zUCd5O + type: nmdc:NucleotideSequencing + name: a process in which a biosample was sequenced? + alternative_identifiers: + - gold:Gp0108335 + has_input: + - nmdc:bsm-00-red + has_output: + - nmdc:dobj-00-9n9n9n + processing_institution: JGI + analyte_category: metagenome + associated_studies: + - nmdc:sty-00-555xxx + add_date: 30-OCT-14 12.00.00.000000000 AM + mod_date: 22-MAY-20 06.13.12.927000000 PM + ncbi_project_name: Thawing permafrost microbial communities from the Arctic, studying + carbon transformations - Permafrost 712P3D +- id: nmdc:dgns-11-s9xj2r24 + type: nmdc:NucleotideSequencing + name: Test NEON data + has_input: + - nmdc:procsm-99-xyz3 + has_output: + - nmdc:dobj-12-jdhk9537 + - nmdc:dobj-12-yx0tfp52 + processing_institution: Battelle + analyte_category: metagenome + associated_studies: + - nmdc:sty-11-34xj1150 + instrument_used: + - nmdc:inst-14-xx07be40 +- id: nmdc:dgns-99-9XUVVF + type: nmdc:NucleotideSequencing + name: Forest soil microbial communities from Barre Woods Harvard Forest LTER site, + Petersham, Massachusetts, United States - Inc-BW-C-14-O + description: Forest soil from Barre Woods Harvard Forest LTER site was incubated + at 10C with heavy water. Sample is from a control plot at ambient soil temperature, + organic horizon - top 4cm of soil + alternative_identifiers: + - gold:Gp0225767 + has_input: + - nmdc:bsm-00-yellow + has_output: + - nmdc:dobj-00-90125 + processing_institution: JGI + analyte_category: metagenome + associated_studies: + - nmdc:sty-00-31415 + add_date: 17-AUG-17 05.08.38.451000000 PM + mod_date: 16-OCT-20 02.04.01.374000000 AM + ncbi_project_name: Forest soil microbial communities from Barre Woods Harvard Forest + LTER site, Petersham, Massachusetts, United States - Inc-BW-C-14-O +- id: nmdc:dgns-99-dk9vgI + type: nmdc:NucleotideSequencing + name: Permafrost microbial communities from Stordalen Mire, Sweden - 611E1M metaG + description: Permafrost microbial communities from Stordalen Mire, Sweden + alternative_identifiers: + - gold:Gp0208560 + has_input: + - nmdc:bsm-00-green + has_output: + - nmdc:dobj-00-pizza + processing_institution: JGI + analyte_category: metagenome + associated_studies: + - nmdc:sty-00-8675309 + add_date: 17-MAR-17 04.55.44.822000000 PM + mod_date: 22-MAY-20 06.38.19.576000000 PM + ncbi_project_name: Permafrost microbial communities from Stordalen Mire, Sweden + - 611E1M metaG +- id: nmdc:dgns-99-MVW1FV + type: nmdc:NucleotideSequencing + name: Rhizosphere microbial communities from Carex aquatilis grown in University + of Washington, Seatle, WA, United States - 4-1-23 metaG + description: Rhizosphere microbial communities from Carex aquatilis grown in submerged + peat from a thermokarst bog, University of Washington, Seatle, WA, United States + alternative_identifiers: + - gold:Gp0306221 + has_input: + - nmdc:bsm-00-blue + has_output: + - nmdc:dobj-00-mobydick + processing_institution: JGI + analyte_category: metagenome + associated_studies: + - nmdc:sty-00-avacado + add_date: 29-MAR-18 01.27.30.036000000 PM + mod_date: 04-APR-20 08.26.35.067000000 AM + ncbi_project_name: Rhizosphere microbial communities from Carex aquatilis grown + in University of Washington, Seatle, WA, United States - 4-1-23 metaG +- id: nmdc:dgms-11-0003fm52 + type: nmdc:MassSpectrometry + name: 1000S_WLUP_FTMS_SPE_BTM_1_run2_Fir_22Apr22_300SA_p01_149_1_3506 + description: High resolution MS spectra only + has_input: + - nmdc:bsm-11-jht0ty76 + has_output: + - nmdc:dobj-11-cp4p5602 + processing_institution: EMSL + start_date: '2022-04-25 13:48:27.000' + end_date: '2022-04-25 14:01:57.000' + analyte_category: nom + associated_studies: + - nmdc:sty-11-28tm5d36 + instrument_used: + - nmdc:inst-14-mwrrj632 + mod_date: '2024-11-07T15:02:18' + eluent_introduction_category: direct_infusion_autosampler + has_mass_spectrometry_configuration: nmdc:mscon-14-j5y11q51 +data_object_set: +- id: nmdc:dobj-99-izwYW6 + type: nmdc:DataObject + name: nmdc:wfmt-11-2471da.rnaseq_gea.txt + description: Metatranscriptome expression results for nmdc:omprc-11-a894kd + data_category: processed_data + data_object_type: Metatranscriptome Expression + file_size_bytes: 32787380 +- id: nmdc:dobj-99-izwYW7 + type: nmdc:DataObject + name: nmdc:wfmt-11-2471da.rnaseq_gea.intergenic.txt + description: Metatranscriptome expression intergentic results for nmdc:omprc-11-a894kd + data_category: processed_data + data_object_type: Metatranscriptome Expression Intergenic + file_size_bytes: 2787380 +- id: nmdc:dobj-99-izwYW8 + type: nmdc:DataObject + name: nmdc:wfmt-11-2471da_readcount.info + description: Metatranscriptome expression version information for nmdc:omprc-11-a894kd + data_category: processed_data + data_object_type: Metatranscriptome Expression Info File + file_size_bytes: 4982 +- id: nmdc:dobj-70-izwYW6 + type: nmdc:DataObject + name: CoreMS.toml + description: Confiuration toml file for CoreMS + data_category: workflow_parameter_data + data_object_type: Configuration toml + file_size_bytes: 4262400 +- id: nmdc:dobj-80-izwYW6 + type: nmdc:DataObject + name: Froze_Core_2015_S1_20_30_19_Metab_raw_data.raw + description: raw direct infusion FT ICR-MS for Froze_Core_2015_S1_20_30_19 + data_category: instrument_data + data_object_type: Direct Infusion FT ICR-MS Raw Data + file_size_bytes: 3262400 +- id: nmdc:dobj-90-izwYW61 + type: nmdc:DataObject + name: Froze_Core_2015_S1_20_30_19_Metab_raw_data.processed + description: Full scan GC-MS (but not GC QExactive, which is EI-HMS) + data_category: processed_data + data_object_type: Direct Infusion FT-ICR MS Analysis Results + file_size_bytes: 5262400 +- id: nmdc:dobj-11-dtTMNa + type: nmdc:DataObject + name: nmdc_wfmgan-11-abc123_virus_summary.tsv + description: Virus summary nmdc:ann0vx38 + data_category: processed_data + data_object_type: Virus Summary + file_size_bytes: 1234 +- id: nmdc:dobj-11-dtTMNc + type: nmdc:DataObject + name: nmdc_wfmgan-11-abc123_plasmid_summary.tsv + description: Plasmid summary nmdc:ann0vx38 + data_category: processed_data + data_object_type: Plasmid Summary + file_size_bytes: 1234 +- id: nmdc:dobj-11-dtTMNd + type: nmdc:DataObject + name: nmdc_wfmgan-11-abc12_aggregated_classification.tsv + description: agg results nmdc:ann0vx38 + data_category: processed_data + data_object_type: GeNomad Aggregated Classification +- id: nmdc:dobj-11-dtTMNb + type: nmdc:DataObject + name: 1237.14.3718.ATCG-ACTG.fastq.gz + description: my awesome fastq file + data_category: instrument_data + data_object_type: Metagenome Raw Reads + file_size_bytes: 1382304 + md5_checksum: 22afa3d49b73eaec2e9787a6b88fbdc3 + was_generated_by: nmdc:omprc-99-123456 +- id: nmdc:dobj-11-r3xkmv70 + type: nmdc:DataObject + name: Blanch_Nat_Lip_C_7_AB_M_07_POS_23Jan18_Brandi-WCSH5801.raw + description: LC-DDA-MS/MS raw data for lipidomics data acquisition. + data_category: instrument_data + data_object_type: LC-DDA-MS/MS Raw Data + file_size_bytes: 77760665 + md5_checksum: 79ad73b4fc737cc2814c74c59a774b45 + url: https://nmdcdemo.emsl.pnnl.gov/lipidomics/blanchard_11_8ws97026/Blanch_Nat_Lip_C_7_AB_M_07_POS_23Jan18_Brandi-WCSH5801.raw + was_generated_by: nmdc:dgms-11-vfzh1754 +- id: nmdc:dobj-11-kc4ff319 + type: nmdc:DataObject + name: Blanch_Nat_Lip_C_7_AB_M_07_POS_23Jan18_Brandi-WCSH5801.toml + description: CoreMS parameters used for Lipidomics workflow. + data_category: workflow_parameter_data + data_object_type: Configuration toml + file_size_bytes: 12668 + md5_checksum: 6c5596d6f9f0446f1a0a628ff25a860a + url: https://nmdcdemo.emsl.pnnl.gov/lipidomics/blanchard_11_8ws97026/20241219_processed/Blanch_Nat_Lip_C_7_AB_M_07_POS_23Jan18_Brandi-WCSH5801.toml + was_generated_by: nmdc:wfmb-11-q0czdv62.1 +- id: nmdc:dobj-11-h5z5w905 + type: nmdc:DataObject + name: Blanch_Nat_Lip_C_7_AB_M_07_POS_23Jan18_Brandi-WCSH5801.hdf5 + description: CoreMS hdf5 file representing a lipidomics data file including annotations. + data_category: processed_data + data_object_type: LC-MS Lipidomics Processed Data + file_size_bytes: 1065056853 + md5_checksum: dfd5515ee4b31c563d0f07cca9d52ed6 + url: https://nmdcdemo.emsl.pnnl.gov/lipidomics/blanchard_11_8ws97026/20241219_processed/Blanch_Nat_Lip_C_7_AB_M_07_POS_23Jan18_Brandi-WCSH5801.hdf5 + was_generated_by: nmdc:wfmb-11-q0czdv62.1 +- id: nmdc:dobj-11-j6kfna43 + type: nmdc:DataObject + name: Blanch_Nat_Lip_C_7_AB_M_07_POS_23Jan18_Brandi-WCSH5801.csv + description: Lipid annotations as a result of a lipidomics workflow activity. + data_category: processed_data + data_object_type: LC-MS Lipidomics Results + file_size_bytes: 37809139 + md5_checksum: a0a270c77ce2c7f4813d1e0b3e9b11ef + url: https://nmdcdemo.emsl.pnnl.gov/lipidomics/blanchard_11_8ws97026/20241219_processed/Blanch_Nat_Lip_C_7_AB_M_07_POS_23Jan18_Brandi-WCSH5801.csv + was_generated_by: nmdc:wfmb-11-q0czdv62.1 +- id: nmdc:dobj-00-msdem1 + type: nmdc:DataObject + name: EMSL_49991_Brodie_122_Lipids_POS_09Aug19_Lola-WCSH417820 + description: raw instrument file for nmdc:dgms-99-zUCd5N + alternative_identifiers: + - my_emsl:1826381 + data_category: instrument_data + data_object_type: LC-DDA-MS/MS Raw Data + file_size_bytes: 1150434379 + md5_checksum: 3EFB4966125DFA9329ADE5B18EADDA8E + url: https://nmdcdemo.emsl.pnnl.gov/proteomics/raw/SpruceW_P19_15_22Jun17_Pippin_17-04-06.raw +- id: nmdc:dobj-00-msdem2 + type: nmdc:DataObject + name: EMSL_49991_Brodie_123_Lipids_Neg_12Aug19_Lola-WCSH417820 + description: raw instrument file for nmdc:dgms-99-zUCd5x + alternative_identifiers: + - my_emsl:1826333 + data_category: instrument_data + data_object_type: LC-DDA-MS/MS Raw Data + file_size_bytes: 1150434379 + md5_checksum: 3EFB4966125DFA9329ADE5B18EADDA8E + url: https://nmdcdemo.emsl.pnnl.gov/proteomics/raw/SpruceW_P19_15_22Jun17_Pippin_17-04-06.raw +- id: nmdc:dobj-12-krhrtjw9 + type: nmdc:DataObject + name: emsl_calibration_run.raw + description: GCMS data file + data_category: instrument_data + data_object_type: GC-MS Raw Data + file_size_bytes: 9208349052 + url: https://emsl_site/emsl_calibration_run.raw + in_manifest: + - nmdc:manif-99-krhtest +- id: nmdc:dobj-11-9n9n9n + type: nmdc:DataObject + name: example_gcms_emsl_run.raw + description: GCMS data file + data_category: instrument_data + data_object_type: GC-MS Raw Data + file_size_bytes: 9208349052 + url: https://emsl_site/example_gcms_emsl_run.raw + in_manifest: + - nmdc:manif-99-krhtest +- id: nmdc:dobj-13-rf3br219 + type: nmdc:DataObject + name: 'output: GCMS_FAMEs_01_GCMS01_20160523' + description: Full scan GC-MS (but not GC QExactive, which is EI-HMS) + data_category: workflow_parameter_data + data_object_type: Reference Calibration File + file_size_bytes: 1818624 +- id: nmdc:dobj-13-vws2zc98 + type: nmdc:DataObject + name: Froze_Core_2015_S1_20_30_19_Metab.cdf + description: Full scan GC-MS raw data file + data_category: instrument_data + data_object_type: GC-MS Raw Data + file_size_bytes: 1818624 +- id: nmdc:dobj-11-547rwq72 + type: nmdc:DataObject + name: nmdc_wfmgas-11-abec.mapped.bam.bai + description: Alignment index file for nmdc_wfmgas-11-abec + data_category: processed_data + data_object_type: BAI File +- id: nmdc:dobj-12-jdhk9537 + type: nmdc:DataObject + name: BMI_HY7W2BGXG_Plate19S_13WellG10_R1.fastq.gz + description: Test R1 data + data_category: instrument_data + data_object_type: Metagenome Raw Read 1 + url: https://storage.neonscience.org/neon-microbial-raw-seq-files/2020/BMI_HY7W2BGXG_mms_R1/BMI_HY7W2BGXG_Plate19S_13WellG10_R1.fastq.gz +- id: nmdc:dobj-12-yx0tfp52 + type: nmdc:DataObject + name: W2BGXG_Plate19S_13WellG10_R2.fastq.gz + description: Test R2 data + data_category: instrument_data + data_object_type: Metagenome Raw Read 2 + url: https://storage.neonscience.org/neon-microbial-raw-seq-files/2020/BMI_HY7W2BGXG_mms_R2/BMI_HY7W2BGXG_Plate19S_13WellG10_R2.fastq.gz +- id: nmdc:dobj-12-71q7wv80 + type: nmdc:DataObject + name: 1472_51293.filtered.fastq.gz + description: Test filtered data for NEON + data_category: processed_data + data_object_type: Filtered Sequencing Reads + url: https://data.microbiomedata.org/data/1472_51293/qa/1472_51293.filtered.fastq.gz +- id: nmdc:dobj-99-dkJ8ab + type: nmdc:DataObject + name: 11340.8.202049.GTCTCCT-AAGGAGA.fastq.gz + description: Raw sequencer read data + data_category: instrument_data + data_object_type: Metagenome Raw Read 1 + file_size_bytes: 9208349052 +- id: nmdc:dobj-99-7zrm55 + type: nmdc:DataObject + name: 11839.4.222578.GAGCTCA-TTGAGCT.fastq.gz + description: Raw sequencer read data + data_category: instrument_data + data_object_type: Metagenome Raw Read 1 + file_size_bytes: 34243309819 +- id: nmdc:dobj-99-sQQw0I + type: nmdc:DataObject + name: 12660.4.274923.GATCGTAC-GTACGATC.fastq.gz + description: Raw sequencer read data + data_category: instrument_data + data_object_type: Metagenome Raw Read 1 + file_size_bytes: 7580035314 +- id: nmdc:dobj-14-1e9qeq49 + type: nmdc:DataObject + name: Hawkes_neg.ref + description: Natural organic matter negative electrospray mode reference calibration + file for Calibration object nmdc:calib-14-hhn3qb47 + data_category: workflow_parameter_data + data_object_type: Reference Calibration File + file_size_bytes: 67316 + md5_checksum: 2ef63544da2bbe6b703c3559f1d5ef2f + url: https://nmdcdemo.emsl.pnnl.gov/nom/reference_calibration_files/Hawkes_neg.ref +field_research_site_set: +- id: nmdc:frsite-99-SPreao + type: nmdc:FieldResearchSite + name: BESC-13-CL1_35_33 + description: Bioscales tree BESC-13-CL1_35_33 +- id: nmdc:frsite-99-h2mYFG + type: nmdc:FieldResearchSite + name: BESC-13-CL2_39_29 + description: Bioscales tree BESC-13-CL2_39_29 +functional_annotation_agg: +- was_generated_by: nmdc:wfmgan-99-123456.1 + gene_function_id: KEGG.ORTHOLOGY:K00627 + count: 120 + type: nmdc:FunctionalAnnotationAggMember +functional_annotation_set: +- type: nmdc:FunctionalAnnotation + has_function: KEGG_PATHWAY:rsk00410 +- type: nmdc:FunctionalAnnotation + has_function: KEGG.REACTION:R00100 +- type: nmdc:FunctionalAnnotation + has_function: RHEA:12345 +- type: nmdc:FunctionalAnnotation + has_function: MetaCyc:RXN-14904 +- type: nmdc:FunctionalAnnotation + has_function: EC:1.1.1.1 +- type: nmdc:FunctionalAnnotation + has_function: GO:0032571 +- type: nmdc:FunctionalAnnotation + has_function: MetaNetX:MNXR101574 +- type: nmdc:FunctionalAnnotation + has_function: SEED:Biotin_biosynthesis +- type: nmdc:FunctionalAnnotation + has_function: KEGG.ORTHOLOGY:K00001 +- type: nmdc:FunctionalAnnotation + has_function: EGGNOG:veNOG12876 +- type: nmdc:FunctionalAnnotation + has_function: PFAM:PF11779 +- type: nmdc:FunctionalAnnotation + has_function: TIGRFAM:TIGR00010 +- type: nmdc:FunctionalAnnotation + has_function: SUPFAM:SSF57615 +- type: nmdc:FunctionalAnnotation + has_function: CATH:1.10.10.200 +- type: nmdc:FunctionalAnnotation + has_function: PANTHER.FAMILY:PTHR12345 +instrument_set: +- id: nmdc:inst-12-dtTMNb + type: nmdc:Instrument + name: Illumina NovaSeq + vendor: illumina + model: novaseq_6000 +- id: nmdc:inst-12-dtTMN3 + type: nmdc:Instrument + name: my favorite Orbitrap + model: exploris_480 +- id: nmdc:inst-14-xx07be40 + type: nmdc:Instrument + name: Illumina NovaSeq + vendor: illumina + model: novaseq +manifest_set: +- id: nmdc:manif-99-krhtest + type: nmdc:Manifest + manifest_category: instrument_run material_processing_set: - - id: nmdc:mixpro-99-A74 - type: nmdc:MixingProcess - has_input: - - nmdc:bsm-99-A67 - - nmdc:bsm-99-A68 - has_output: - - nmdc:procsm-11-abd123 - duration: +- id: nmdc:dispro-99-123 + type: nmdc:DissolvingProcess + has_input: + - nmdc:bsm-00-435737 + has_output: + - nmdc:procsm-00-1 + substances_used: + - type: nmdc:PortionOfSubstance + final_concentration: + type: nmdc:QuantityValue + has_numeric_value: 0.2 + has_unit: g.mL-1 + known_as: glucose +- id: nmdc:chcpr-99-123 + type: nmdc:ChemicalConversionProcess + has_input: + - nmdc:procsm-00-1 + has_output: + - nmdc:procsm-00-2 + chemical_conversion_category: acid_base + substances_used: + - type: nmdc:PortionOfSubstance + final_concentration: type: nmdc:QuantityValue - has_numeric_value: 2 - has_unit: hours - instrument_used: - - nmdc:inst-12-124 - - id: nmdc:filtpr-22-32G2BS - type: nmdc:FiltrationProcess - has_input: - - nmdc:procsm-99-05g48p90 - has_output: - - nmdc:procsm-99-05g48p91 - conditionings: - - Methanol - - Sterile water #Milli-Q - filtration_category: pressure - instrument_used: - - nmdc:inst-12-125 - is_pressurized: true - - id: nmdc:dispro-99-A74 - type: nmdc:DissolvingProcess - has_input: - - nmdc:bsm-12-A67 - has_output: - - nmdc:procsm-13-S67F + has_numeric_value: 37 + has_unit: percentile + known_as: water + substance_role: acid + substances_volume: + type: nmdc:QuantityValue + has_numeric_value: 2 + has_unit: uL +- id: nmdc:filtpr-00-123 + type: nmdc:FiltrationProcess + has_input: + - nmdc:procsm-00-2 + has_output: + - nmdc:procsm-00-3 + conditionings: + - deionized water + filter_material: paper + filter_pore_size: + type: nmdc:QuantityValue + has_numeric_value: 0.45 + has_unit: um + separation_method: syringe +- id: nmdc:cspro-99-456 + type: nmdc:ChromatographicSeparationProcess + has_input: + - nmdc:procsm-00-3 + has_output: + - nmdc:procsm-00-4 + chromatographic_category: solid_phase_extraction + ordered_mobile_phases: + - type: nmdc:MobilePhaseSegment substances_used: - - known_as: water - type: nmdc:PortionOfSubstance - final_concentration: - type: nmdc:QuantityValue - has_unit: mM - has_numeric_value: 15 - volume: - type: nmdc:QuantityValue - has_numeric_value: 500 - has_unit: mL - - known_as: formic_acid - type: nmdc:PortionOfSubstance - substance_role: solubilizing_agent - duration: + - type: nmdc:PortionOfSubstance + known_as: water + volume: type: nmdc:QuantityValue - has_numeric_value: 2 - has_unit: hours - instrument_used: - - nmdc:inst-12-124 - - - id: nmdc:chcpr-19-789 - type: nmdc:ChemicalConversionProcess - # has_input: - # - nmdc-procsm-99-000001 - # has_output: - # - nmdc-procsm-99-000002 - chemical_conversion_category: acid_base + has_numeric_value: 700 + has_unit: mL + - type: nmdc:MobilePhaseSegment substances_used: - - known_as: glucose - type: nmdc:PortionOfSubstance - volume: - type: nmdc:QuantityValue - has_numeric_value: 120 - has_unit: mL - final_concentration: - type: nmdc:QuantityValue - has_unit: mM - has_numeric_value: 10 - temperature: - type: nmdc:QuantityValue - has_numeric_value: 25 - has_unit: Cel - duration: + - type: nmdc:PortionOfSubstance + known_as: acetonitrile + - type: nmdc:PortionOfSubstance + final_concentration: + type: nmdc:QuantityValue + has_numeric_value: 10 + has_unit: mM + known_as: glucose + substance_role: acid + volume: type: nmdc:QuantityValue - has_numeric_value: 1 - has_unit: h - - - id: nmdc:chcpr-19-7890 - type: nmdc:ChemicalConversionProcess - # has_input: - # - nmdc:procsm-37 - # has_output: - # - nmdc:procsm-39 + has_numeric_value: 700 + has_unit: mL + - type: nmdc:MobilePhaseSegment substances_used: - - known_as: water - type: nmdc:PortionOfSubstance - substance_role: solvent - - known_as: formic_acid - type: nmdc:PortionOfSubstance - substance_role: buffer - source_concentration: - type: nmdc:QuantityValue - has_unit: mM - has_numeric_value: 50 - - known_as: glucose - type: nmdc:PortionOfSubstance - substance_role: ms_proteolytic_enzyme - final_concentration: - type: nmdc:QuantityValue - has_unit: μg/μL - has_numeric_value: 0.05 - substances_volume: - type: nmdc:QuantityValue - has_numeric_value: 75 - has_unit: μL - temperature: - type: nmdc:QuantityValue - has_numeric_value: 37 - has_unit: Cel - duration: - type: nmdc:QuantityValue - has_numeric_value: 3 - has_unit: h - - id: nmdc:poolp-9x9-1x - type: nmdc:Pooling - name: first pooling process - description: xxx - alternative_identifiers: - - generic:xxx - has_input: - - nmdc:procsm-99-xyz1 - - nmdc:procsm-99-xyz2 - has_output: - - nmdc:procsm-99-xyz3 - - id: nmdc:extrp-99-999999 - type: nmdc:Extraction - has_input: - - nmdc:bsm-99-435737 - has_output: - - nmdc:procsm-99-0938548 - - - id: nmdc:libprp-99-999999 - type: nmdc:LibraryPreparation - has_input: - - nmdc:procsm-99-0938548 - has_output: - - nmdc:procsm-99-sdsdll - -functional_annotation_agg: - - gene_function_id: KEGG.ORTHOLOGY:K00627 - count: 120 - type: nmdc:FunctionalAnnotationAggMember - was_generated_by: nmdc:wfmgan-99-123456.1 -biosample_set: - - id: nmdc:bsm-99-isqhuW - type: nmdc:Biosample - name: Permafrost microbial communities from Stordalen Mire, Sweden - 611E1M metaG - description: Permafrost microbial communities from Stordalen Mire, Sweden - associated_studies: - - nmdc:sty-99-8675309 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - samp_name: 11E1M metaG - gold_biosample_identifiers: - - gold:Gb0150408 - ecosystem: Environmental - ecosystem_category: Terrestrial - ecosystem_subtype: Wetlands - ecosystem_type: Soil - geo_loc_name: - type: nmdc:TextValue - has_raw_value: 'Sweden: Stordalen' - lat_lon: - type: nmdc:GeolocationValue - has_raw_value: 68.35 19.05 - latitude: 68.35 - longitude: 19.05 - specific_ecosystem: Permafrost - add_date: 17-MAR-17 04.55.54.717000000 PM - community: microbial communities - habitat: Fen - location: Stordalen Mire, Sweden - mod_date: 08-JAN-20 02.49.23.000000000 PM - ncbi_taxonomy_name: permafrost metagenome - sample_collection_site: Mire fen - - id: nmdc:bsm-99-dge3H9 - type: nmdc:Biosample - name: Forest soil microbial communities from Barre Woods Harvard Forest LTER site, - Petersham, Massachusetts, United States - Inc-BW-C-14-O - description: Forest soil from Barre Woods Harvard Forest LTER site was incubated - at 10C with heavy water. Sample is from a control plot at ambient soil temperature, - organic horizon - top 4cm of soil - associated_studies: - - nmdc:sty-99-8675309 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - samp_name: Inc-BW-C-14-O - gold_biosample_identifiers: - - gold:Gb0157174 - ecosystem: Environmental - ecosystem_category: Terrestrial - ecosystem_subtype: Unclassified - ecosystem_type: Soil - geo_loc_name: - type: nmdc:TextValue - has_raw_value: 'USA: Massachusetts' - lat_lon: - type: nmdc:GeolocationValue - has_raw_value: 42.481016 -72.178343 - latitude: 42.481016 - longitude: -72.178343 - specific_ecosystem: Forest Soil - add_date: 17-AUG-17 05.38.34.719000000 PM - community: microbial communities - habitat: soil - location: Barre Woods Harvard Forest LTER site, Petersham, Massachusetts, United - States - mod_date: 08-JAN-20 02.49.23.000000000 PM - ncbi_taxonomy_name: soil metagenome - sample_collection_site: forest soil - - id: nmdc:bsm-99-dc6tg6 - type: nmdc:Biosample - name: Rhizosphere microbial communities from Carex aquatilis grown in University - of Washington, Seatle, WA, United States - 4-1-23 metaG - description: Rhizosphere microbial communities from Carex aquatilis grown in submerged - peat from a thermokarst bog, University of Washington, Seatle, WA, United States - associated_studies: - - nmdc:sty-99-8675309 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - samp_name: 4-1-23 metaG - gold_biosample_identifiers: - - gold:Gb0188037 - ecosystem: Host-associated - ecosystem_category: Plants - ecosystem_subtype: Soil - ecosystem_type: Rhizosphere - geo_loc_name: - type: nmdc:TextValue - has_raw_value: 'USA: Seattle, Washington' - lat_lon: - type: nmdc:GeolocationValue - has_raw_value: 47.6516 -122.3045 - latitude: 47.6516 - longitude: -122.3045 - specific_ecosystem: Unclassified - add_date: 29-MAR-18 01.27.40.709000000 PM - community: microbial communities - habitat: rhizosphere - host_name: Carex aquatilis - location: University of Washington, Seatle, WA, United States - mod_date: 08-JAN-20 02.49.25.000000000 PM - ncbi_taxonomy_name: rhizosphere metagenome - sample_collection_site: Peat Soil - - id: nmdc:bsm-99-dtTMNb - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - dna_cont_type: tube - - id: nmdc:bsm-99-J9FcnC - type: nmdc:Biosample - name: Root microbial communities from poplar common garden site in Clatskanie, Oregon, - USA - BESC-13-CL1_35_33 endosphere - description: Root microbial communities from poplar common garden site in Clatskanie, - Oregon, USA - associated_studies: - - nmdc:sty-99-U21mUX - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-SPreao - gold_biosample_identifiers: - - gold:Gb0305833 - - id: nmdc:bsm-99-BdlWdQ - type: nmdc:Biosample - name: Rhizosphere soil microbial communities from poplar common garden site in Clatskanie, - Oregon, USA - BESC-13-CL1_35_33 - description: Rhizosphere soil microbial communities from poplar common garden site - in Clatskanie, Oregon, USA - associated_studies: - - nmdc:sty-99-U21mUX - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-SPreao - gold_biosample_identifiers: - - gold:Gb0291692 - - id: nmdc:bsm-99-vn74Wq - type: nmdc:Biosample - name: Bulk soil microbial communities from poplar common garden site in Clatskanie, - Oregon, USA - BESC-13-CL1_35_33 - description: Bulk soil microbial communities from poplar common garden site in Clatskanie, - Oregon, USA - associated_studies: - - nmdc:sty-99-U21mUX - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-SPreao - gold_biosample_identifiers: - - gold:Gb0291582 - - id: nmdc:bsm-99-P8FdpS - type: nmdc:Biosample - name: Root microbial communities from poplar common garden site in Clatskanie, Oregon, - USA - BESC-13-CL2_39_29 endosphere - description: Root microbial communities from poplar common garden site in Clatskanie, - Oregon, USA - associated_studies: - - nmdc:sty-99-U21mUX - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-h2mYFG - gold_biosample_identifiers: - - gold:Gb0305834 - - id: nmdc:bsm-99-ugBwz3 - type: nmdc:Biosample - name: Rhizosphere soil microbial communities from poplar common garden site in Clatskanie, - Oregon, USA - BESC-13-CL2_39_29 - description: Rhizosphere soil microbial communities from poplar common garden site - in Clatskanie, Oregon, USA - associated_studies: - - nmdc:sty-99-U21mUX - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-h2mYFG - gold_biosample_identifiers: - - gold:Gb0291693 - - id: nmdc:bsm-99-tN5lxM - type: nmdc:Biosample - name: Bulk soil microbial communities from poplar common garden site in Clatskanie, - Oregon, USA - BESC-13-CL2_39_29 - description: Bulk soil microbial communities from poplar common garden site in Clatskanie, - Oregon, USA - associated_studies: - - nmdc:sty-99-U21mUX - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-h2mYFG - gold_biosample_identifiers: - - gold:Gb0291583 - - id: nmdc:bsm-99-n3ybxz - type: nmdc:Biosample - name: soil sample 1 - description: soil sample collected from a grassland ecosystem - associated_studies: - - nmdc:sty-99-b27v55 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000001 - term: - id: ENVO:00000001 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000446 - term: - id: ENVO:00000446 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00001998 - term: - id: ENVO:00001998 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-78f4bc - - id: nmdc:bsm-99-b316vq - type: nmdc:Biosample - name: soil sample 2 - description: soil sample collected from a grassland ecosystem - associated_studies: - - nmdc:sty-99-b27v55 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000001 - term: - id: ENVO:00000001 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000446 - term: - id: ENVO:00000446 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00001998 - term: - id: ENVO:00001998 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-78f4bc - - id: nmdc:bsm-99-q9t93w - type: nmdc:Biosample - name: soil sample 3 - description: soil sample collected from a grassland ecosystem - associated_studies: - - nmdc:sty-99-b27v55 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000001 - term: - id: ENVO:00000001 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000446 - term: - id: ENVO:00000446 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00001998 - term: - id: ENVO:00001998 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-78f4bc - - id: nmdc:bsm-99-t2r77l - type: nmdc:Biosample - name: water sample 1 - description: water sample from a freshwater lake - associated_studies: - - nmdc:sty-99-t9w6g8 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000001 - term: - id: ENVO:00000001 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000234 - term: - id: ENVO:00000234 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002004 - term: - id: ENVO:00002004 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-k4m6j9 - - id: nmdc:bsm-99-x971d3 - type: nmdc:Biosample - name: water sample 2 - description: water sample from a freshwater lake - associated_studies: - - nmdc:sty-99-t9w6g8 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000001 - term: - id: ENVO:00000001 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000234 - term: - id: ENVO:00000234 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002004 - term: - id: ENVO:00002004 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-k4m6j9 - - id: nmdc:bsm-99-c6dlm7 - type: nmdc:Biosample - name: water sample 3 - description: water sample from a freshwater lake - associated_studies: - - nmdc:sty-99-t9w6g8 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000001 - term: - id: ENVO:00000001 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000234 - term: - id: ENVO:00000234 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002004 - term: - id: ENVO:00002004 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-k4m6j9 - - id: nmdc:bsm-99-p7k6v9 - type: nmdc:Biosample - name: human gut sample 1 - description: fecal sample from a human subject - associated_studies: - - nmdc:sty-99-q4g1z3 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000001 - term: - id: ENVO:00000001 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: UBERON:0000059 - term: - id: UBERON:0000059 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002005 - term: - id: ENVO:00002005 - type: nmdc:OntologyClass - host_taxid: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: NCBITaxon:9606 - term: - id: NCBITaxon:9606 - type: nmdc:OntologyClass - - id: nmdc:bsm-99-bbbbbb - type: nmdc:Biosample - name: human gut sample 2 - description: fecal sample from a human subject - associated_studies: - - nmdc:sty-99-q4g1z3 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000001 - term: - id: ENVO:00000001 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: UBERON:0000059 - term: - id: UBERON:0000059 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002005 - term: - id: ENVO:00002005 - type: nmdc:OntologyClass - host_taxid: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: NCBITaxon:9606 - term: - id: NCBITaxon:9606 - type: nmdc:OntologyClass - - id: nmdc:bsm-99-d9j6n9 - type: nmdc:Biosample - name: human gut sample 3 - description: fecal sample from a human subject - associated_studies: - - nmdc:sty-99-q4g1z3 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000001 - term: - id: ENVO:00000001 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: UBERON:0000059 - term: - id: UBERON:0000059 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002005 - term: - id: ENVO:00002005 - type: nmdc:OntologyClass - host_taxid: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: NCBITaxon:9606 - term: - id: NCBITaxon:9606 - type: nmdc:OntologyClass - - id: nmdc:bsm-99-999999 - type: nmdc:Biosample - name: Lithgow State Coal Mine Calcium nutrients (early) - description: Bulk Aqueous phase filtered water - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - gold_biosample_identifiers: - - gold:Gb0101224 - ecosystem: Environmental - ecosystem_category: Aquatic - ecosystem_subtype: Groundwater - ecosystem_type: Freshwater - geo_loc_name: - type: nmdc:TextValue - has_raw_value: Lithgow - lat_lon: - type: nmdc:GeolocationValue - has_raw_value: -33.460524 150.168149 - latitude: -33.460524 - longitude: 150.168149 - samp_taxon_id: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: coal metagenome [NCBITaxon:1260732] - term: - id: NCBITaxon:1260732 - type: nmdc:OntologyClass - name: coal metagenome - specific_ecosystem: Coalbed water - add_date: 28-JUL-14 12.00.00.000000000 AM - community: microbial communities - habitat: Coalbed water - location: from the Lithgow State Coal Mine, New South Wales, Australia - mod_date: 26-AUG-16 01.50.27.000000000 PM - ncbi_taxonomy_name: coal metagenome - sample_collection_site: Lithgow State Coal Mine - - id: nmdc:bsm-99-AtTUOs - type: nmdc:Biosample - name: Lithgow State Coal Mine Calcium nutrients (early) - description: Bulk Aqueous phase filtered water - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - biosample_categories: - - LTER - - SIP - gold_biosample_identifiers: - - gold:Gb0101224 - ecosystem: Environmental - ecosystem_category: Aquatic - ecosystem_subtype: Groundwater - ecosystem_type: Freshwater - geo_loc_name: - type: nmdc:TextValue - has_raw_value: Lithgow - lat_lon: - type: nmdc:GeolocationValue - has_raw_value: -33.460524 150.168149 - latitude: -33.460524 - longitude: 150.168149 - samp_taxon_id: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: coal metagenome [NCBITaxon:1260732] - term: - id: NCBITaxon:1260732 - type: nmdc:OntologyClass - name: coal metagenome - specific_ecosystem: Coalbed water - add_date: 28-JUL-14 12.00.00.000000000 AM - community: microbial communities - habitat: Coalbed water - location: from the Lithgow State Coal Mine, New South Wales, Australia - mod_date: 26-AUG-16 01.50.27.000000000 PM - ncbi_taxonomy_name: coal metagenome - sample_collection_site: Lithgow State Coal Mine - - id: nmdc:bsm-99-eBVHjN - type: nmdc:Biosample - name: Lithgow State Coal Mine Calcium nutrients Extra - description: Bulk Aqueous phase filtered water - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - gold_biosample_identifiers: - - gold:Gb0101225 - ecosystem: Environmental - ecosystem_category: Aquatic - ecosystem_subtype: Groundwater - ecosystem_type: Freshwater - geo_loc_name: - type: nmdc:TextValue - has_raw_value: Lithgow - lat_lon: - type: nmdc:GeolocationValue - has_raw_value: -33.460524 150.168149 - latitude: -33.460524 - longitude: 150.168149 - samp_taxon_id: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: coal metagenome [NCBITaxon:1260732] - term: - id: NCBITaxon:1260732 - type: nmdc:OntologyClass - name: coal metagenome - specific_ecosystem: Coalbed water - add_date: 28-JUL-14 12.00.00.000000000 AM - community: microbial communities - habitat: Coalbed water - location: from the Lithgow State Coal Mine, New South Wales, Australia - mod_date: 26-AUG-16 01.50.27.000000000 PM - ncbi_taxonomy_name: coal metagenome - sample_collection_site: Lithgow State Coal Mine - - id: nmdc:bsm-99-TDPHTh - type: nmdc:Biosample - name: Lithgow State Coal Mine Calcium nutrients - description: Bulk Aqueous phase filtered water - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - gold_biosample_identifiers: - - gold:Gb0101226 - ecosystem: Environmental - ecosystem_category: Aquatic - ecosystem_subtype: Groundwater - ecosystem_type: Freshwater - geo_loc_name: - type: nmdc:TextValue - has_raw_value: Lithgow - lat_lon: - type: nmdc:GeolocationValue - has_raw_value: -33.460524 150.168149 - latitude: -33.460524 - longitude: 150.168149 - samp_taxon_id: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: coal metagenome [NCBITaxon:1260732] - term: - id: NCBITaxon:1260732 - type: nmdc:OntologyClass - name: coal metagenome - specific_ecosystem: Coalbed water - add_date: 28-JUL-14 12.00.00.000000000 AM - community: microbial communities - habitat: Coalbed water - location: from the Lithgow State Coal Mine, New South Wales, Australia - mod_date: 26-AUG-16 01.50.27.000000000 PM - ncbi_taxonomy_name: coal metagenome - sample_collection_site: Lithgow State Coal Mine - - id: nmdc:bsm-99-111111 - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - infiltrations: - - 00:01:32 - - 00:00:53 - - id: nmdc:bsm-99-abcdef - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - infiltrations: - - 00:02:54 - - id: nmdc:bsm-99-qwerty - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - infiltrations: - - 01:24:03 - - 00:02:33 - - 00:02:02 - - id: nmdc:bsm-99-74d83z - type: nmdc:Biosample - name: soil sample from tropical rainforest - description: Soil sample collected from the forest floor of a tropical rainforest. - associated_studies: - - nmdc:sty-99-dl968v - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000428 - term: - id: ENVO:00000428 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:01000338 - term: - id: ENVO:01000338 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00001998 - term: - id: ENVO:00001998 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-29dl6v - gold_biosample_identifiers: - - gold:Gb01234567 - insdc_biosample_identifiers: - - biosample:SAMN12345678 - emsl_biosample_identifiers: - - emsl:emsl_12345 - igsn_biosample_identifiers: - - igsn:IEPA12345 - annual_precpt: - type: nmdc:QuantityValue - has_numeric_value: 2500 - has_unit: mm - lat_lon: - type: nmdc:GeolocationValue - latitude: 1.23456789 - longitude: -54.32109876 - ph: 6.5 - salinity: - type: nmdc:QuantityValue - has_numeric_value: 0.1 - has_unit: PSU - temp: - type: nmdc:QuantityValue - has_numeric_value: 25 - has_unit: Celsius - - id: nmdc:bsm-99-49z38t - type: nmdc:Biosample - name: mouse gut sample - description: Fecal sample collected from a laboratory mouse. - associated_studies: - - nmdc:sty-99-dl968v - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000001 - term: - id: ENVO:00000001 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: UBERON:0000059 - term: - id: UBERON:0000059 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002005 - term: - id: ENVO:00002005 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-96d7l4 - host_taxid: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: NCBITaxon:10090 - term: - id: NCBITaxon:10090 - type: nmdc:OntologyClass - gold_biosample_identifiers: - - gold:Gb76543210 - insdc_biosample_identifiers: - - biosample:SAMN98765432 - emsl_biosample_identifiers: - - emsl:emsl_67890 - igsn_biosample_identifiers: - - igsn:IEPA65432 - - id: nmdc:bsm-99-aaaaaa - type: nmdc:Biosample - name: human gut sample - description: Fecal sample collected from a human subject. - associated_studies: - - nmdc:sty-99-z3t9g4 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00000001 - term: - id: ENVO:00000001 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: UBERON:0000059 - term: - id: UBERON:0000059 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002005 - term: - id: ENVO:00002005 - type: nmdc:OntologyClass - collected_from: nmdc:frsite-99-9j6n9t - host_taxid: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: NCBITaxon:9606 - term: - id: NCBITaxon:9606 - type: nmdc:OntologyClass - gold_biosample_identifiers: - - gold:Gb90123456 - insdc_biosample_identifiers: - - biosample:SAMN23456789 - emsl_biosample_identifiers: - - emsl:emsl_78901 - igsn_biosample_identifiers: - - igsn:IEPA76543 - - id: nmdc:bsm-99-222222 - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - rna_volume: 12.0 - - id: nmdc:bsm-99-333333 - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - dna_cont_well: B2 - dna_cont_type: plate - - id: nmdc:bsm-99-000002 - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - dna_cont_well: A11 - dna_cont_type: plate - - id: nmdc:bsm-99-000003 - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - dna_cont_well: H10 - dna_cont_type: plate - - id: nmdc:bsm-99-000004 - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - dna_cont_well: H11 - dna_cont_type: plate - - id: nmdc:bsm-99-000005 - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - dna_cont_well: C1 - dna_cont_type: plate - - id: nmdc:bsm-99-4444444 - type: nmdc:Biosample - name: Sample Exhaustive Biosample instance. Although all of these values should - pass validation, that does not mean that any Biosample of any type would necessarily - have this particular combination of values. - description: unconstrained text - alternative_identifiers: - - generic:abc123 - associated_studies: - - nmdc:sty-99-987654 - - nmdc:sty-99-qwerty - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - biosample_categories: - - LTER - - FICUS - collected_from: nmdc:frsite-99-29dl6v - embargoed: true - host_taxid: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: NCBITaxon:9606 - term: - id: NCBITaxon:9606 - type: nmdc:OntologyClass - img_identifiers: - - img.taxon:abc123 - samp_name: see also name - gold_biosample_identifiers: - - gold:Gb123456789 - - gold:Gb90909090 - insdc_biosample_identifiers: - - biosample:SAMN123456789 - - biosample:SAMN000 - emsl_biosample_identifiers: - - generic:abc123 - igsn_biosample_identifiers: - - any:curie_1 - - any:curie_2 - abs_air_humidity: - type: nmdc:QuantityValue - has_raw_value: xxx - add_recov_method: - type: nmdc:TextValue - has_raw_value: xxx - additional_info: - type: nmdc:TextValue - has_raw_value: xxx - address: - type: nmdc:TextValue - has_raw_value: xxx - adj_room: - type: nmdc:TextValue - has_raw_value: xxx - aero_struc: - type: nmdc:TextValue - has_raw_value: xxx - agrochem_addition: - - type: nmdc:TextValue - has_raw_value: lime;1 kg/acre;2022-99-16T16:05:42+0000 - air_PM_concen: - - type: nmdc:TextValue - has_raw_value: xxx - air_temp: - type: nmdc:QuantityValue - has_raw_value: xxx - air_temp_regm: - - type: nmdc:TextValue - has_raw_value: 25 degree Celsius;R2/2018-05-11T14:30/2018-05-11T19:30/P1H30M - al_sat: - type: nmdc:QuantityValue - has_raw_value: 0.1 mg/kg - al_sat_meth: - type: nmdc:TextValue - has_raw_value: https://journaljeai.com/index.php/JEAI/article/view/583 - alkalinity: - type: nmdc:QuantityValue - has_raw_value: 50 milligram per liter - alkalinity_method: - type: nmdc:TextValue - has_raw_value: https://wrrc.umass.edu/research/projects/acid-rain-monitoring-project/analysis-method-ph-and-alkalinity - alkyl_diethers: - type: nmdc:QuantityValue - has_raw_value: 0.005 mole per liter - alt: - type: nmdc:QuantityValue - has_raw_value: 100 meter - aminopept_act: - type: nmdc:QuantityValue - has_raw_value: 0.269 mole per liter per hour - ammonium: - type: nmdc:QuantityValue - has_raw_value: 1.5 milligram per liter - ammonium_nitrogen: - type: nmdc:QuantityValue - has_raw_value: 0.5 milligram per liter - amount_light: - type: nmdc:QuantityValue - has_raw_value: xxx - ances_data: - type: nmdc:TextValue - has_raw_value: xxx - annual_precpt: - type: nmdc:QuantityValue - has_raw_value: 0.5 milligram per liter - annual_temp: - type: nmdc:QuantityValue - has_raw_value: 12.5 degree Celsius - antibiotic_regm: - - type: nmdc:TextValue - has_raw_value: xxx - api: - type: nmdc:QuantityValue - has_raw_value: xxx - arch_struc: building - aromatics_pc: - type: nmdc:TextValue - has_raw_value: xxx - asphaltenes_pc: - type: nmdc:TextValue - has_raw_value: xxx - atmospheric_data: - - type: nmdc:TextValue - has_raw_value: xxx - avg_dew_point: - type: nmdc:QuantityValue - has_raw_value: xxx - avg_occup: - type: nmdc:TextValue - has_raw_value: xxx - avg_temp: - type: nmdc:QuantityValue - has_raw_value: xxx - bac_prod: - type: nmdc:QuantityValue - has_raw_value: xxx - bac_resp: - type: nmdc:QuantityValue - has_raw_value: xxx - bacteria_carb_prod: - type: nmdc:QuantityValue - has_raw_value: 2.53 microgram per liter per hour - barometric_press: - type: nmdc:QuantityValue - has_raw_value: xxx - basin: - type: nmdc:TextValue - has_raw_value: xxx - bathroom_count: - type: nmdc:TextValue - has_raw_value: xxx - bedroom_count: - type: nmdc:TextValue - has_raw_value: xxx - benzene: - type: nmdc:QuantityValue - has_raw_value: xxx - biochem_oxygen_dem: - type: nmdc:QuantityValue - has_raw_value: xxx - biocide: - type: nmdc:TextValue - has_raw_value: xxx - biocide_admin_method: - type: nmdc:TextValue - has_raw_value: xxx - biol_stat: wild - biomass: - - type: nmdc:TextValue - has_raw_value: xxx - biotic_regm: - type: nmdc:TextValue - has_raw_value: sample inoculated with Rhizobium spp. Culture - biotic_relationship: parasite - bishomohopanol: - type: nmdc:QuantityValue - has_raw_value: 14 microgram per liter - blood_press_diast: - type: nmdc:QuantityValue - has_raw_value: xxx - blood_press_syst: - type: nmdc:QuantityValue - has_raw_value: xxx - bromide: - type: nmdc:QuantityValue - has_raw_value: 0.05 parts per million - build_docs: building information model - build_occup_type: - - office - building_setting: urban - built_struc_age: - type: nmdc:QuantityValue - has_raw_value: xxx - built_struc_set: - type: nmdc:TextValue - has_raw_value: xxx - built_struc_type: - type: nmdc:TextValue - has_raw_value: xxx - calcium: - type: nmdc:QuantityValue - has_raw_value: 0.2 micromole per liter - carb_dioxide: - type: nmdc:QuantityValue - has_raw_value: xxx - carb_monoxide: - type: nmdc:QuantityValue - has_raw_value: xxx - carb_nitro_ratio: - type: nmdc:QuantityValue - has_raw_value: '0.417361111' - ceil_area: - type: nmdc:QuantityValue - has_raw_value: xxx - ceil_cond: new - ceil_finish_mat: drywall - ceil_struc: - type: nmdc:TextValue - has_raw_value: xxx - ceil_texture: crows feet - ceil_thermal_mass: - type: nmdc:QuantityValue - has_raw_value: xxx - ceil_type: cathedral - ceil_water_mold: - type: nmdc:TextValue - has_raw_value: xxx - chem_administration: - - type: nmdc:ControlledTermValue - has_raw_value: agar [CHEBI:2509];2018-05-11T20:00Z - chem_mutagen: - - type: nmdc:TextValue - has_raw_value: xxx - chem_oxygen_dem: - type: nmdc:QuantityValue - has_raw_value: xxx - chem_treat_method: xxx - chem_treatment: - type: nmdc:TextValue - has_raw_value: xxx - chloride: - type: nmdc:QuantityValue - has_raw_value: 5000 milligram per liter - chlorophyll: - type: nmdc:QuantityValue - has_raw_value: 5 milligram per cubic meter - climate_environment: - - type: nmdc:TextValue - has_raw_value: tropical climate;R2/2018-05-11T14:30/2018-05-11T19:30/P1H30M - collection_date: - type: nmdc:TimestampValue - has_raw_value: xxx - conduc: - type: nmdc:QuantityValue - has_raw_value: xxx - cool_syst_id: - type: nmdc:TextValue - has_raw_value: xxx - crop_rotation: - type: nmdc:TextValue - has_raw_value: yes;R2/2017-01-01/2018-12-31/P6M - cult_root_med: - type: nmdc:TextValue - has_raw_value: xxx - cur_land_use: farmstead - cur_vegetation: - type: nmdc:TextValue - has_raw_value: MIxS doesn't provide any guidance more specific than "text" - cur_vegetation_meth: - type: nmdc:TextValue - has_raw_value: https://link.springer.com/article/10.1023/A:1011975321668 - date_last_rain: - type: nmdc:TimestampValue - has_raw_value: xxx - density: - type: nmdc:QuantityValue - has_raw_value: 1000 kilogram per cubic meter - depos_env: other - depth: - type: nmdc:QuantityValue - has_raw_value: 1.5 to 2.5 meters (that may not be the pattern the submission schema - expects). Extractions below require external migration logic. - has_maximum_numeric_value: 2.5 - has_minimum_numeric_value: 1.5 - has_numeric_value: 2 - has_unit: meter - dew_point: - type: nmdc:QuantityValue - has_raw_value: xxx - diether_lipids: - - type: nmdc:TextValue - has_raw_value: xxx - diss_carb_dioxide: - type: nmdc:QuantityValue - has_raw_value: 5 milligram per liter - diss_hydrogen: - type: nmdc:QuantityValue - has_raw_value: 0.3 micromole per liter - diss_inorg_carb: - type: nmdc:QuantityValue - has_raw_value: 2059 micromole per kilogram - diss_inorg_nitro: - type: nmdc:QuantityValue - has_raw_value: xxx - diss_inorg_phosp: - type: nmdc:QuantityValue - has_raw_value: 56.5 micromole per liter - diss_iron: - type: nmdc:QuantityValue - has_raw_value: xxx - diss_org_carb: - type: nmdc:QuantityValue - has_raw_value: 197 micromole per liter - diss_org_nitro: - type: nmdc:QuantityValue - has_raw_value: 0.05 micromole per liter - diss_oxygen: - type: nmdc:QuantityValue - has_raw_value: 175 micromole per kilogram - diss_oxygen_fluid: - type: nmdc:QuantityValue - has_raw_value: xxx - dna_cont_well: C2 - door_comp_type: revolving - door_cond: damaged - door_direct: inward - door_loc: north - door_mat: aluminum - door_move: collapsible - door_size: - type: nmdc:QuantityValue - has_raw_value: xxx - door_type: composite - door_type_metal: collapsible - door_type_wood: battened - door_water_mold: - type: nmdc:TextValue - has_raw_value: xxx - down_par: - type: nmdc:QuantityValue - has_raw_value: xxx - drainage_class: well - drawings: operation - ecosystem: unconstrained text. should be validated against the controlled vocabulary, - by the sample's environmental package. would also be nice to align the CV with - MIxS environmental triads - ecosystem_category: unconstrained text - ecosystem_subtype: unconstrained text - ecosystem_type: unconstrained text - efficiency_percent: - type: nmdc:QuantityValue - has_raw_value: xxx - elev: 100.0 - elevator: - type: nmdc:TextValue - has_raw_value: xxx - emulsions: - - type: nmdc:TextValue - has_raw_value: xxx - env_package: - type: nmdc:TextValue - has_raw_value: unconstrained text. should require the name of a MIxS EnvironmentalPackage - class. have asked MIxS to return this term to their model. UPDATE VALIDATION - RULES/PATTERN/ENUM! - escalator: - type: nmdc:TextValue - has_raw_value: xxx - ethylbenzene: - type: nmdc:QuantityValue - has_raw_value: xxx - exp_duct: - type: nmdc:QuantityValue - has_raw_value: xxx - exp_pipe: - type: nmdc:QuantityValue - has_raw_value: xxx - experimental_factor: - type: nmdc:ControlledTermValue - has_raw_value: unconstrained text, unlike the MIxS environmental triad - ext_door: - type: nmdc:TextValue - has_raw_value: xxx - ext_wall_orient: north - ext_window_orient: north - extreme_event: '2023-01-15' - fao_class: Fluvisols - fertilizer_regm: - - type: nmdc:TextValue - has_raw_value: xxx - field: - type: nmdc:TextValue - has_raw_value: xxx - filter_type: - - HEPA - fire: 2000-11 to 2000-12 - fireplace_type: - type: nmdc:TextValue - has_raw_value: xxx - flooding: '2000-01-15' - floor_age: - type: nmdc:QuantityValue - has_raw_value: xxx - floor_area: - type: nmdc:QuantityValue - has_raw_value: xxx - floor_cond: new - floor_count: - type: nmdc:TextValue - has_raw_value: xxx - floor_finish_mat: tile - floor_struc: balcony - floor_thermal_mass: - type: nmdc:QuantityValue - has_raw_value: xxx - floor_water_mold: condensation - fluor: - type: nmdc:QuantityValue - has_raw_value: xxx - freq_clean: - type: nmdc:QuantityValue - has_raw_value: xxx - freq_cook: - type: nmdc:QuantityValue - has_raw_value: xxx - fungicide_regm: - - type: nmdc:TextValue - has_raw_value: xxx - furniture: cabinet - gaseous_environment: - - type: nmdc:TextValue - has_raw_value: nitric oxide;0.5 micromole per liter;R2/2018-05-11T14:30/2018-05-11T19:30/P1H30M - gaseous_substances: - - type: nmdc:TextValue - has_raw_value: xxx - gender_restroom: female - genetic_mod: - type: nmdc:TextValue - has_raw_value: xxx - geo_loc_name: - type: nmdc:TextValue - has_raw_value: 'USA: Maryland, Bethesda' - glucosidase_act: - type: nmdc:QuantityValue - has_raw_value: 5 mol per liter per hour - gravidity: - type: nmdc:TextValue - has_raw_value: xxx - gravity: - - type: nmdc:TextValue - has_raw_value: xxx - growth_facil: - type: nmdc:ControlledTermValue - has_raw_value: Growth chamber [CO_715:0000189] - growth_habit: erect - growth_hormone_regm: - - type: nmdc:TextValue - has_raw_value: xxx - hall_count: - type: nmdc:TextValue - has_raw_value: xxx - handidness: ambidexterity - hc_produced: Oil - hcr: Shale - hcr_fw_salinity: - type: nmdc:QuantityValue - has_raw_value: xxx - hcr_geol_age: Archean - hcr_pressure: - type: nmdc:TextValue - has_raw_value: xxx - hcr_temp: - type: nmdc:TextValue - has_raw_value: xxx - heat_cool_type: - - radiant system - heat_deliv_loc: north - heat_sys_deliv_meth: xxx - heat_system_id: - type: nmdc:TextValue - has_raw_value: xxx - heavy_metals: - - type: nmdc:TextValue - has_raw_value: arsenic;0.09 micrograms per gram - heavy_metals_meth: - - type: nmdc:TextValue - has_raw_value: https://link.springer.com/article/10.1007/s42452-019-1578-x - height_carper_fiber: - type: nmdc:QuantityValue - has_raw_value: xxx - herbicide_regm: - - type: nmdc:TextValue - has_raw_value: xxx - horizon_meth: - type: nmdc:TextValue - has_raw_value: xxx - host_age: - type: nmdc:QuantityValue - has_raw_value: xxx - host_body_habitat: - type: nmdc:TextValue - has_raw_value: xxx - host_body_product: - type: nmdc:ControlledTermValue - has_raw_value: xxx - host_body_site: - type: nmdc:ControlledTermValue - has_raw_value: xxx - host_body_temp: - type: nmdc:QuantityValue - has_raw_value: xxx - host_color: - type: nmdc:TextValue - has_raw_value: xxx - host_common_name: - type: nmdc:TextValue - has_raw_value: xxx - host_diet: - - type: nmdc:TextValue - has_raw_value: xxx - host_dry_mass: - type: nmdc:QuantityValue - has_raw_value: xxx - host_family_relation: - - xxx - host_genotype: - type: nmdc:TextValue - has_raw_value: xxx - host_growth_cond: - type: nmdc:TextValue - has_raw_value: xxx - host_height: - type: nmdc:QuantityValue - has_raw_value: xxx - host_last_meal: - - type: nmdc:TextValue - has_raw_value: xxx - host_length: - type: nmdc:QuantityValue - has_raw_value: xxx - host_life_stage: - type: nmdc:TextValue - has_raw_value: xxx - host_phenotype: - type: nmdc:ControlledTermValue - has_raw_value: xxx - host_sex: female - host_shape: - type: nmdc:TextValue - has_raw_value: xxx - host_subject_id: - type: nmdc:TextValue - has_raw_value: xxx - host_subspecf_genlin: - - xxx - host_substrate: - type: nmdc:TextValue - has_raw_value: xxx - host_symbiont: - - xxx - host_tot_mass: - type: nmdc:QuantityValue - has_raw_value: xxx - host_wet_mass: - type: nmdc:QuantityValue - has_raw_value: xxx - humidity: - type: nmdc:QuantityValue - has_raw_value: xxx - humidity_regm: - - type: nmdc:TextValue - has_raw_value: 25 gram per cubic meter;R2/2018-05-11T14:30/2018-05-11T19:30/P1H30M - indoor_space: bedroom - indoor_surf: cabinet - indust_eff_percent: - type: nmdc:QuantityValue - has_raw_value: xxx - inorg_particles: - - type: nmdc:TextValue - has_raw_value: xxx - inside_lux: - type: nmdc:QuantityValue - has_raw_value: xxx - int_wall_cond: new - iw_bt_date_well: - type: nmdc:TimestampValue - has_raw_value: xxx - iwf: - type: nmdc:QuantityValue - has_raw_value: xxx - last_clean: - type: nmdc:TimestampValue - has_raw_value: xxx - lat_lon: - type: nmdc:GeolocationValue - has_raw_value: 50.586825 6.408977 - latitude: 50.586825 - longitude: 6.408977 - lbc_thirty: - type: nmdc:QuantityValue - has_raw_value: 543 mg/kg - lbceq: - type: nmdc:QuantityValue - has_raw_value: 1575 mg/kg - light_intensity: - type: nmdc:QuantityValue - has_raw_value: xxx - light_regm: - type: nmdc:TextValue - has_raw_value: incandescent light;10 lux;450 nanometer - light_type: - - none - link_addit_analys: - type: nmdc:TextValue - has_raw_value: https://pubmed.ncbi.nlm.nih.gov/2315679/ - link_class_info: - type: nmdc:TextValue - has_raw_value: https://wisconsindot.gov/Documents/doing-bus/eng-consultants/cnslt-rsrces/geotechmanual/gt-03-03.pdf - link_climate_info: - type: nmdc:TextValue - has_raw_value: https://www.int-res.com/abstracts/cr/v14/n3/p161-173/ - lithology: Basement - local_class: - type: nmdc:TextValue - has_raw_value: jicama soil - local_class_meth: - type: nmdc:TextValue - has_raw_value: https://www.sciencedirect.com/science/article/abs/pii/S0016706105003083 - magnesium: - type: nmdc:QuantityValue - has_raw_value: 52.8 micromole per kilogram - manganese: - type: nmdc:QuantityValue - has_raw_value: 24.7 mg/kg - max_occup: - type: nmdc:QuantityValue - has_raw_value: xxx - mean_frict_vel: - type: nmdc:QuantityValue - has_raw_value: 0.5 meter per second - mean_peak_frict_vel: - type: nmdc:QuantityValue - has_raw_value: 1 meter per second - mech_struc: subway - mechanical_damage: - - type: nmdc:TextValue - has_raw_value: xxx - methane: - type: nmdc:QuantityValue - has_raw_value: xxx - micro_biomass_meth: xxx - microbial_biomass: - type: nmdc:QuantityValue - has_raw_value: xxx - mineral_nutr_regm: - - type: nmdc:TextValue - has_raw_value: xxx - misc_param: - - type: nmdc:TextValue - has_raw_value: Bicarbonate ion concentration;2075 micromole per kilogram - n_alkanes: - - type: nmdc:TextValue - has_raw_value: n-hexadecane;100 milligram per liter - nitrate: - type: nmdc:QuantityValue - has_raw_value: 65 micromole per liter - nitrite: - type: nmdc:QuantityValue - has_raw_value: 0.5 micromole per liter - nitrite_nitrogen: - type: nmdc:QuantityValue - has_raw_value: 1.2 mg/kg - nitro: - type: nmdc:QuantityValue - has_raw_value: xxx - non_min_nutr_regm: - - xxx - number_pets: - type: nmdc:QuantityValue - has_raw_value: xxx - number_plants: - type: nmdc:QuantityValue - has_raw_value: xxx - number_resident: - type: nmdc:QuantityValue - has_raw_value: xxx - occup_density_samp: - type: nmdc:QuantityValue - has_raw_value: xxx - occup_document: estimate - occup_samp: - type: nmdc:QuantityValue - has_raw_value: xxx - org_carb: - type: nmdc:QuantityValue - has_raw_value: xxx - org_count_qpcr_info: xxx - org_matter: - type: nmdc:QuantityValue - has_raw_value: 1.75 milligram per cubic meter - org_nitro: - type: nmdc:QuantityValue - has_raw_value: 4 micromole per liter - org_particles: - - type: nmdc:TextValue - has_raw_value: xxx - organism_count: - - type: nmdc:QuantityValue - has_raw_value: ATP - owc_tvdss: - type: nmdc:QuantityValue - has_raw_value: xxx - oxy_stat_samp: aerobic - oxygen: - type: nmdc:QuantityValue - has_raw_value: xxx - part_org_carb: - type: nmdc:QuantityValue - has_raw_value: 1.92 micromole per liter - part_org_nitro: - type: nmdc:QuantityValue - has_raw_value: xxx - particle_class: - - type: nmdc:TextValue - has_raw_value: xxx - permeability: - type: nmdc:TextValue - has_raw_value: xxx - perturbation: - - type: nmdc:TextValue - has_raw_value: antibiotic addition;R2/2018-05-11T14:30Z/2018-05-11T19:30Z/P1H30M - pesticide_regm: - - type: nmdc:TextValue - has_raw_value: xxx - petroleum_hydrocarb: - type: nmdc:QuantityValue - has_raw_value: 0.05 micromole per liter - ph: 99.99 - ph_meth: - type: nmdc:TextValue - has_raw_value: https://www.epa.gov/sites/production/files/2015-12/documents/9040c.pdf - ph_regm: - - type: nmdc:TextValue - has_raw_value: xxx - phaeopigments: - - type: nmdc:TextValue - has_raw_value: 2.5 milligram per cubic meter - phosphate: - type: nmdc:QuantityValue - has_raw_value: 0.7 micromole per liter - phosplipid_fatt_acid: - - type: nmdc:TextValue - has_raw_value: 2.98 milligram per liter - photon_flux: - type: nmdc:QuantityValue - has_raw_value: xxx - plant_growth_med: - type: nmdc:ControlledTermValue - has_raw_value: xxx - plant_product: - type: nmdc:TextValue - has_raw_value: xxx - plant_sex: Androdioecious - plant_struc: - type: nmdc:ControlledTermValue - has_raw_value: xxx - pollutants: - - type: nmdc:TextValue - has_raw_value: xxx - porosity: - type: nmdc:TextValue - has_raw_value: xxx - potassium: - type: nmdc:QuantityValue - has_raw_value: 463 milligram per liter - pour_point: - type: nmdc:QuantityValue - has_raw_value: xxx - pre_treatment: - type: nmdc:TextValue - has_raw_value: xxx - pres_animal_insect: cat;3 - pressure: - type: nmdc:QuantityValue - has_raw_value: 50 atmosphere - prev_land_use_meth: xxx - previous_land_use: - type: nmdc:TextValue - has_raw_value: xxx - primary_prod: - type: nmdc:QuantityValue - has_raw_value: xxx - primary_treatment: - type: nmdc:TextValue - has_raw_value: xxx - prod_rate: - type: nmdc:QuantityValue - has_raw_value: xxx - prod_start_date: - type: nmdc:TimestampValue - has_raw_value: xxx - profile_position: summit - quad_pos: North side - radiation_regm: - - type: nmdc:TextValue - has_raw_value: xxx - rainfall_regm: - - type: nmdc:TextValue - has_raw_value: xxx - reactor_type: - type: nmdc:TextValue - has_raw_value: xxx - redox_potential: - type: nmdc:QuantityValue - has_raw_value: 300 millivolt - rel_air_humidity: - type: nmdc:QuantityValue - has_raw_value: xxx - rel_humidity_out: - type: nmdc:QuantityValue - has_raw_value: xxx - rel_samp_loc: edge of car - reservoir: - type: nmdc:TextValue - has_raw_value: xxx - resins_pc: - type: nmdc:TextValue - has_raw_value: xxx - room_air_exch_rate: - type: nmdc:QuantityValue - has_raw_value: xxx - room_architec_elem: xxx - room_condt: new - room_connected: attic - room_count: - type: nmdc:TextValue - has_raw_value: xxx - room_dim: - type: nmdc:TextValue - has_raw_value: xxx - room_door_dist: - type: nmdc:TextValue - has_raw_value: xxx - room_door_share: - type: nmdc:TextValue - has_raw_value: xxx - room_hallway: - type: nmdc:TextValue - has_raw_value: xxx - room_loc: corner room - room_moist_dam_hist: 123 - room_net_area: - type: nmdc:TextValue - has_raw_value: xxx - room_occup: - type: nmdc:QuantityValue - has_raw_value: xxx - room_samp_pos: north corner - room_type: attic - room_vol: - type: nmdc:TextValue - has_raw_value: xxx - room_wall_share: - type: nmdc:TextValue - has_raw_value: xxx - room_window_count: 123 - root_cond: - type: nmdc:TextValue - has_raw_value: xxx - root_med_carbon: - type: nmdc:TextValue - has_raw_value: xxx - root_med_macronutr: - type: nmdc:TextValue - has_raw_value: xxx - root_med_micronutr: - type: nmdc:TextValue - has_raw_value: xxx - root_med_ph: - type: nmdc:QuantityValue - has_raw_value: xxx - root_med_regl: - type: nmdc:TextValue - has_raw_value: xxx - root_med_solid: - type: nmdc:TextValue - has_raw_value: xxx - root_med_suppl: - type: nmdc:TextValue - has_raw_value: xxx - salinity: - type: nmdc:QuantityValue - has_raw_value: 25 practical salinity unit - salinity_meth: - type: nmdc:TextValue - has_raw_value: PMID:22895776 - salt_regm: - - type: nmdc:TextValue - has_raw_value: xxx - samp_capt_status: other - samp_collec_device: xxx - samp_collec_method: swabbing - samp_collect_point: well - samp_dis_stage: dissemination - samp_floor: basement - samp_loc_corr_rate: - type: nmdc:TextValue - has_raw_value: xxx - samp_mat_process: - type: nmdc:ControlledTermValue - has_raw_value: filtering of seawater - samp_md: - type: nmdc:QuantityValue - has_raw_value: xxx - samp_preserv: - type: nmdc:TextValue - has_raw_value: xxx - samp_room_id: - type: nmdc:TextValue - has_raw_value: xxx - samp_size: - type: nmdc:QuantityValue - has_raw_value: 5 liters - samp_sort_meth: - - type: nmdc:TextValue - has_raw_value: xxx - samp_store_dur: - type: nmdc:TextValue - has_raw_value: P1Y6M - samp_store_loc: - type: nmdc:TextValue - has_raw_value: Freezer no:5 - samp_store_temp: - type: nmdc:QuantityValue - has_raw_value: -80 degree Celsius - samp_subtype: biofilm - samp_taxon_id: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: soil metagenome [NCBItaxon:410658] - term: - id: NCBItaxon:410658 - type: nmdc:OntologyClass - name: soil metagenome - samp_time_out: - type: nmdc:TextValue - has_raw_value: xxx - samp_transport_cond: - type: nmdc:TextValue - has_raw_value: xxx - samp_tvdss: - type: nmdc:TextValue - has_raw_value: xxx - samp_type: - type: nmdc:TextValue - has_raw_value: xxx - samp_weather: cloudy - samp_well_name: - type: nmdc:TextValue - has_raw_value: xxx - saturates_pc: - type: nmdc:TextValue - has_raw_value: xxx - season: - type: nmdc:TextValue - has_raw_value: xxx - season_environment: - - type: nmdc:TextValue - has_raw_value: xxx - season_precpt: - type: nmdc:QuantityValue - has_raw_value: 75 millimeters - season_temp: - type: nmdc:QuantityValue - has_raw_value: 18 degree Celsius - season_use: Spring - secondary_treatment: - type: nmdc:TextValue - has_raw_value: xxx - sediment_type: biogenous - sewage_type: - type: nmdc:TextValue - has_raw_value: xxx - shad_dev_water_mold: xxx - shading_device_cond: damaged - shading_device_loc: - type: nmdc:TextValue - has_raw_value: xxx - shading_device_mat: - type: nmdc:TextValue - has_raw_value: xxx - shading_device_type: tree - sieving: - type: nmdc:TextValue - has_raw_value: MIxS does not provide an example - silicate: - type: nmdc:QuantityValue - has_raw_value: xxx - size_frac: - type: nmdc:TextValue - has_raw_value: xxx - size_frac_low: - type: nmdc:QuantityValue - has_raw_value: 0.2 micrometer - size_frac_up: - type: nmdc:QuantityValue - has_raw_value: 20 micrometer - slope_aspect: - type: nmdc:QuantityValue - has_raw_value: MIxS does not provide an example - slope_gradient: - type: nmdc:QuantityValue - has_raw_value: MIxS does not provide an example - sludge_retent_time: - type: nmdc:QuantityValue - has_raw_value: xxx - sodium: - type: nmdc:QuantityValue - has_raw_value: 10.5 milligram per liter - soil_horizon: O horizon - soil_text_measure: - type: nmdc:QuantityValue - has_raw_value: xxx - soil_texture_meth: xxx - soil_type: - type: nmdc:TextValue - has_raw_value: plinthosol [ENVO:00002250] - soil_type_meth: - type: nmdc:TextValue - has_raw_value: Frederick series - solar_irradiance: - type: nmdc:QuantityValue - has_raw_value: xxx - soluble_inorg_mat: - - type: nmdc:TextValue - has_raw_value: xxx - soluble_org_mat: - - type: nmdc:TextValue - has_raw_value: xxx - soluble_react_phosp: - type: nmdc:QuantityValue - has_raw_value: xxx - source_mat_id: - type: nmdc:TextValue - has_raw_value: MPI012345 - space_typ_state: - type: nmdc:TextValue - has_raw_value: xxx - specific: operation - specific_ecosystem: unconstrained text - specific_humidity: - type: nmdc:QuantityValue - has_raw_value: xxx - sr_dep_env: Lacustine - sr_geol_age: Archean - sr_kerog_type: other - sr_lithology: Clastic - standing_water_regm: - - type: nmdc:TextValue - has_raw_value: xxx - store_cond: - type: nmdc:TextValue - has_raw_value: -20 degree Celsius freezer;P2Y10D - substructure_type: - - basement - sulfate: - type: nmdc:QuantityValue - has_raw_value: 5 micromole per liter - sulfate_fw: - type: nmdc:QuantityValue - has_raw_value: xxx - sulfide: - type: nmdc:QuantityValue - has_raw_value: 2 micromole per liter - surf_air_cont: - - dust - surf_humidity: - type: nmdc:QuantityValue - has_raw_value: xxx - surf_material: adobe - surf_moisture: - type: nmdc:QuantityValue - has_raw_value: xxx - surf_moisture_ph: 123.0 - surf_temp: - type: nmdc:QuantityValue - has_raw_value: xxx - suspend_part_matter: - type: nmdc:QuantityValue - has_raw_value: xxx - suspend_solids: - - type: nmdc:TextValue - has_raw_value: xxx - tan: - type: nmdc:QuantityValue - has_raw_value: xxx - temp: - type: nmdc:QuantityValue - has_raw_value: 25 degree Celsius - temp_out: - type: nmdc:QuantityValue - has_raw_value: xxx - tertiary_treatment: - type: nmdc:TextValue - has_raw_value: xxx - tidal_stage: high tide - tillage: - - chisel - tiss_cult_growth_med: - type: nmdc:TextValue - has_raw_value: xxx - toluene: - type: nmdc:QuantityValue - has_raw_value: xxx - tot_carb: - type: nmdc:QuantityValue - has_raw_value: MIxS does not provide an example - tot_depth_water_col: - type: nmdc:QuantityValue - has_raw_value: 500 meter - tot_diss_nitro: - type: nmdc:QuantityValue - has_raw_value: 40 microgram per liter - tot_inorg_nitro: - type: nmdc:QuantityValue - has_raw_value: xxx - tot_iron: - type: nmdc:QuantityValue - has_raw_value: xxx - tot_nitro: - type: nmdc:QuantityValue - has_raw_value: xxx - tot_nitro_cont_meth: https://currentprotocols.onlinelibrary.wiley.com/doi/abs/10.1002/0471142913.fab0102s00 - tot_nitro_content: - type: nmdc:QuantityValue - has_raw_value: 35 milligrams Nitrogen per kilogram of soil - tot_org_c_meth: - type: nmdc:TextValue - has_raw_value: https://www.epa.gov/sites/production/files/2015-12/documents/9060a.pdf - tot_org_carb: - type: nmdc:QuantityValue - has_raw_value: 2% - tot_part_carb: - type: nmdc:QuantityValue - has_raw_value: xxx - tot_phosp: - type: nmdc:QuantityValue - has_raw_value: 0.03 milligram per liter - tot_phosphate: - type: nmdc:QuantityValue - has_raw_value: xxx - tot_sulfur: - type: nmdc:QuantityValue - has_raw_value: xxx - train_line: red - train_stat_loc: south station above ground - train_stop_loc: end - turbidity: - type: nmdc:QuantityValue - has_raw_value: xxx - tvdss_of_hcr_press: - type: nmdc:QuantityValue - has_raw_value: xxx - tvdss_of_hcr_temp: - type: nmdc:QuantityValue - has_raw_value: xxx - typ_occup_density: 123.0 - ventilation_rate: - type: nmdc:QuantityValue - has_raw_value: xxx - ventilation_type: - type: nmdc:TextValue - has_raw_value: xxx - vfa: - type: nmdc:QuantityValue - has_raw_value: xxx - vfa_fw: - type: nmdc:QuantityValue - has_raw_value: xxx - vis_media: photos - viscosity: - type: nmdc:TextValue - has_raw_value: xxx - volatile_org_comp: - - type: nmdc:TextValue - has_raw_value: xxx - wall_area: - type: nmdc:QuantityValue - has_raw_value: xxx - wall_const_type: frame construction - wall_finish_mat: plaster - wall_height: - type: nmdc:QuantityValue - has_raw_value: xxx - wall_loc: north - wall_surf_treatment: painted - wall_texture: knockdown - wall_thermal_mass: - type: nmdc:QuantityValue - has_raw_value: xxx - wall_water_mold: - type: nmdc:TextValue - has_raw_value: xxx - wastewater_type: - type: nmdc:TextValue - has_raw_value: xxx - water_cont_soil_meth: MIxS doesn't provide an example - water_content: - - MIxS doesn't provide an example 1 - - MIxS doesn't provide an example 2 - water_current: + - type: nmdc:PortionOfSubstance + known_as: alphaLP + volume: type: nmdc:QuantityValue - has_raw_value: xxx - water_cut: + has_numeric_value: 1000 + has_unit: mL +- id: nmdc:dispro-99-456 + type: nmdc:DissolvingProcess + has_input: + - nmdc:procsm-00-4 + has_output: + - nmdc:procsm-00-5 + substances_used: + - type: nmdc:PortionOfSubstance + known_as: Asp-N + volume: type: nmdc:QuantityValue - has_raw_value: xxx - water_feat_size: + has_numeric_value: 5 + has_unit: mL +- id: nmdc:chcpr-99-456 + type: nmdc:ChemicalConversionProcess + has_input: + - nmdc:procsm-00-5 + has_output: + - nmdc:procsm-00-6 + chemical_conversion_category: acid_base + substances_used: + - type: nmdc:PortionOfSubstance + final_concentration: type: nmdc:QuantityValue - has_raw_value: xxx - water_feat_type: fountain - water_prod_rate: + has_numeric_value: 37 + has_unit: percentile + known_as: formic_acid + substance_role: acid + substances_volume: + type: nmdc:QuantityValue + has_numeric_value: 5 + has_unit: uL +- id: nmdc:extrp-99-01 + type: nmdc:Extraction + name: MPLEx_extraction + description: MPLEx extraction of nmdc:procsm-99-99 to obtain metabolites, proteins, + and lipids + has_input: + - nmdc:procsm-99-99 + has_output: + - nmdc:procsm-99-01 + - nmdc:procsm-99-02 + - nmdc:procsm-99-03 + processing_institution: EMSL + substances_used: + - type: nmdc:PortionOfSubstance + known_as: chloroform + substance_role: solvent + volume: type: nmdc:QuantityValue - has_raw_value: xxx - water_temp_regm: - - type: nmdc:TextValue - has_raw_value: xxx - watering_regm: - - type: nmdc:TextValue - has_raw_value: 1 liter;R2/2018-05-11T14:30/2018-05-11T19:30/P1H30M - weekday: Monday - win: - type: nmdc:TextValue - has_raw_value: xxx - wind_direction: - type: nmdc:TextValue - has_raw_value: xxx - wind_speed: + has_raw_value: 13.33 mL + has_numeric_value: 13.33 + has_unit: mL + - type: nmdc:PortionOfSubstance + known_as: methanol + substance_role: solvent + volume: type: nmdc:QuantityValue - has_raw_value: xxx - window_cond: damaged - window_cover: blinds - window_horiz_pos: left - window_loc: north - window_mat: fiberglass - window_open_freq: - type: nmdc:TextValue - has_raw_value: xxx - window_size: - type: nmdc:TextValue - has_raw_value: xxx - window_status: - type: nmdc:TextValue - has_raw_value: xxx - window_type: single-hung sash window - window_vert_pos: bottom - window_water_mold: - type: nmdc:TextValue - has_raw_value: xxx - xylene: + has_raw_value: 6.67 mL + has_numeric_value: 6.67 + has_unit: mL + - type: nmdc:PortionOfSubstance + known_as: water + substance_role: solvent + volume: type: nmdc:QuantityValue - has_raw_value: xxx - zinc: + has_raw_value: 4 mL + has_numeric_value: 4 + has_unit: mL + extraction_targets: + - metabolite + - protein + - lipid +- id: nmdc:dispro-99-01 + type: nmdc:DissolvingProcess + name: resuspend_metabolites + description: Dissolving metabolites from nmdc:procsm-99-01 + has_input: + - nmdc:procsm-99-01 + has_output: + - nmdc:procsm-99-04 + processing_institution: EMSL + substances_used: + - type: nmdc:PortionOfSubstance + known_as: chloroform + substance_role: solvent + volume: type: nmdc:QuantityValue - has_raw_value: 2.5 mg/kg - add_date: '2021-03-31' - community: no_example_from_mixs - habitat: unconstrained text - host_name: snail is an example value, but unconstrained text is accepted at this - point - location: unconstrained text. should we even keep this slot? check if it has been - used in MongoDB. - mod_date: '2023-01-25' - ncbi_taxonomy_name: soil metagenome - proport_woa_temperature: no example from MIxS - salinity_category: halotolerant is an example from the schema, but MIxS doesn't - provide this slot any more - sample_collection_site: unconstrained text - soluble_iron_micromol: MIxS doesn't provide an example - subsurface_depth: + has_raw_value: 0.3333 mL + has_numeric_value: 0.3333 + has_unit: mL + - type: nmdc:PortionOfSubstance + known_as: methanol + substance_role: solvent + volume: type: nmdc:QuantityValue - has_raw_value: MIxS does not provide an example - dna_absorb1: 2.02 - dna_absorb2: 2.02 - dna_collect_site: untreated pond water - dna_concentration: 100.0 - dna_cont_type: plate - dna_container_id: Pond_MT_041618 - dna_dnase: 'yes' - dna_isolate_meth: DNA - dna_organisms: expected to contain microbes (59%) fungi (30%), viruses (10%), tadpoles - (1%) - dna_project_contact: John Jones - dna_samp_id: '187654' - dna_sample_format: 10 mM Tris-HCl - dna_sample_name: JGI_pond_041618 - dna_seq_project: '1191234' - dna_seq_project_pi: Jane Johnson - dna_seq_project_name: JGI Pond metagenomics - dna_volume: 25.0 - proposal_dna: '504000' - dnase_rna: 'yes' - proposal_rna: '504000' - rna_absorb1: 2.02 - rna_absorb2: 2.02 - rna_collect_site: untreated pond water - rna_concentration: 100.0 - rna_cont_type: plate - rna_cont_well: C2 - rna_container_id: Pond_MT_041618 - rna_isolate_meth: RNA - rna_organisms: expected to contain microbes (59%) fungi (30%), viruses (10%), tadpoles - (1%) - rna_project_contact: John Jones - rna_samp_id: '187654' - rna_sample_format: 10 mM Tris-HCl - rna_sample_name: JGI_pond_041618 - rna_seq_project: '1191234' - rna_seq_project_pi: Jane Johnson - rna_seq_project_name: JGI Pond metagenomics - rna_volume: 25.0 - collection_date_inc: '2023-01-29' - collection_time: 05:42+0000 - collection_time_inc: 13:42+0000 - experimental_factor_other: unconstrained text, but presumably expects 'term label - [term id]' - filter_method: Basix PES, 13-100-106 FisherSci is an example value, but unconstrained - text is accepted at this point - isotope_exposure: 13C glucose - micro_biomass_c_meth: https://acsess.onlinelibrary.wiley.com/doi/abs/10.2136/sssaspecpub49.c12 - micro_biomass_n_meth: https://acsess.onlinelibrary.wiley.com/doi/abs/10.2136/sssaspecpub49.c12 - microbial_biomass_c: 0.05 ug C/g dry soil - microbial_biomass_n: 0.05 ug N/g dry soil - non_microb_biomass: insect 0.23 ug; plant 1g - non_microb_biomass_method: https://doi.org/10.1038/s41467-021-26181-3 - org_nitro_method: https://doi.org/10.1016/0038-0717(85)90144-0 - other_treatment: unconstrained text - start_date_inc: '2023-01-27' - start_time_inc: 13:42+0000 - project_id: no example from MIxS - replicate_number: '1' - sample_shipped: 15 g - sample_type: soil - water extract - technical_reps: '2' - analysis_type: - - metabolomics - - metagenomics - sample_link: - - IGSN:DSJ0284 - - any:curie - - id: nmdc:bsm-99-555555 - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - rna_cont_type: plate - rna_cont_well: B2 - - id: nmdc:bsm-99-000001 - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - rna_cont_type: plate - rna_cont_well: A10 - - id: nmdc:bsm-99-000006 - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - rna_cont_type: plate - rna_cont_well: C12 - - id: nmdc:bsm-99-666666 - type: nmdc:Biosample - name: real biosample from the field - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - - id: nmdc:bsm-99-XYZ - type: nmdc:Biosample - name: one DNA library, like an analytical sample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - - id: nmdc:bsm-99-abcdef1 - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - - id: nmdc:bsm-99-abcdef2 - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass - - id: nmdc:bsm-99-abcdef3 - type: nmdc:Biosample - associated_studies: - - nmdc:sty-99-abc123 - env_broad_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002030 - term: - id: ENVO:00002030 - type: nmdc:OntologyClass - env_local_scale: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00002169 - term: - id: ENVO:00002169 - type: nmdc:OntologyClass - env_medium: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: ENVO:00005792 - term: - id: ENVO:00005792 - type: nmdc:OntologyClass -collecting_biosamples_from_site_set: - - id: nmdc:clsite-99-Cq00d1 - type: nmdc:CollectingBiosamplesFromSite - name: Collection of biosamples from BESC-13-CL1_35_33 - has_input: - - nmdc:frsite-99-SPreao - has_output: - - nmdc:bsm-99-J9FcnC - - nmdc:bsm-99-BdlWdQ - - nmdc:bsm-99-vn74Wq - - id: nmdc:clsite-99-yzmLBN - type: nmdc:CollectingBiosamplesFromSite - name: Collection of biosamples from BESC-13-CL2_39_29 - has_input: - - nmdc:frsite-99-h2mYFG - has_output: - - nmdc:bsm-99-P8FdpS - - nmdc:bsm-99-ugBwz3 - - nmdc:bsm-99-tN5lxM - - id: nmdc:clsite-99-r9j8vl - type: nmdc:CollectingBiosamplesFromSite - name: soil sample collection - has_input: - - nmdc:frsite-99-78f4bc - has_output: - - nmdc:bsm-99-n3ybxz - - nmdc:bsm-99-b316vq - - nmdc:bsm-99-q9t93w - - id: nmdc:clsite-99-dlm16g - type: nmdc:CollectingBiosamplesFromSite - name: lake water sample collection - has_input: - - nmdc:frsite-99-k4m6j9 - has_output: - - nmdc:bsm-99-t2r77l - - nmdc:bsm-99-x971d3 - - nmdc:bsm-99-c6dlm7 - - id: nmdc:clsite-99-f5k2l6 - type: nmdc:CollectingBiosamplesFromSite - name: human gut sample collection - has_input: - - nmdc:frsite-99-k48dl3 - has_output: - - nmdc:bsm-99-p7k6v9 - - nmdc:bsm-99-bbbbbb - - nmdc:bsm-99-d9j6n9 - - id: nmdc:clsite-99-93z8t7 - type: nmdc:CollectingBiosamplesFromSite - name: soil sample collection from tropical rainforest - has_input: - - nmdc:frsite-99-29dl6v - has_output: - - nmdc:bsm-99-74d83z - - id: nmdc:clsite-99-d9j6n9 - type: nmdc:CollectingBiosamplesFromSite - name: mouse gut sample collection - has_input: - - nmdc:frsite-99-96d7l4 - has_output: - - nmdc:bsm-99-49z38t - - id: nmdc:clsite-99-98f7b2 - type: nmdc:CollectingBiosamplesFromSite - name: human gut sample collection - has_input: - - nmdc:frsite-99-9j6n9t - has_output: - - nmdc:bsm-99-bbbbbb -data_object_set: - - id: nmdc:dobj-99-msdem1 - name: EMSL_49991_Brodie_122_Lipids_POS_09Aug19_Lola-WCSH417820 - description: raw instrument file for nmdc:dgms-99-zUCd5N - file_size_bytes: 1150434379 - url: https://nmdcdemo.emsl.pnnl.gov/proteomics/raw/SpruceW_P19_15_22Jun17_Pippin_17-04-06.raw #url does not yet exist for lcms metabolite data, this is just an example resolvable url - md5_checksum: 3EFB4966125DFA9329ADE5B18EADDA8E - data_object_type: LC-DDA-MS/MS Raw Data - data_category: instrument_data - type: nmdc:DataObject - alternative_identifiers: - - my_emsl:1826381 - - id: nmdc:dobj-99-msdem2 - name: EMSL_49991_Brodie_123_Lipids_Neg_12Aug19_Lola-WCSH417820 - description: raw instrument file for nmdc:dgms-99-zUCd5x - file_size_bytes: 1150434379 - url: https://nmdcdemo.emsl.pnnl.gov/proteomics/raw/SpruceW_P19_15_22Jun17_Pippin_17-04-06.raw #url does not yet exist for lipid data, this is just an example resolvable url - md5_checksum: 3EFB4966125DFA9329ADE5B18EADDA8E - data_object_type: LC-DDA-MS/MS Raw Data - data_category: instrument_data - type: nmdc:DataObject - alternative_identifiers: - - my_emsl:1826333 - - id: nmdc:dobj-99-dkJ8xX - type: nmdc:DataObject - name: 11340.8.202049.GTCTCCT-AAGGAGA.fastq.gz - description: Raw sequencer read data - data_category: instrument_data - file_size_bytes: 9208349052 - data_object_type: Metagenome Raw Reads - - id: nmdc:dobj-99-7zrm55 - type: nmdc:DataObject - name: 11839.4.222578.GAGCTCA-TTGAGCT.fastq.gz - description: Raw sequencer read data - data_category: instrument_data - file_size_bytes: 34243309819 - data_object_type: Metagenome Raw Reads - - id: nmdc:dobj-99-sQQw0I - type: nmdc:DataObject - name: 12660.4.274923.GATCGTAC-GTACGATC.fastq.gz - description: Raw sequencer read data - data_category: instrument_data - file_size_bytes: 7580035314 - data_object_type: Metagenome Raw Reads - - id: nmdc:dobj-70-izwYW6 - type: nmdc:DataObject - name: CoreMS.toml - description: Confiuration toml file for CoreMS - data_category: workflow_parameter_data - data_object_type: Configuration toml - file_size_bytes: 4262400 - - id: nmdc:dobj-80-izwYW6 - type: nmdc:DataObject - name: Froze_Core_2015_S1_20_30_19_Metab_raw_data.raw - description: raw direct infusion FT ICR-MS for Froze_Core_2015_S1_20_30_19 - data_category: instrument_data - data_object_type: Direct Infusion FT ICR-MS Raw Data - file_size_bytes: 3262400 - - id: nmdc:dobj-90-izwYW61 - type: nmdc:DataObject - name: Froze_Core_2015_S1_20_30_19_Metab_raw_data.processed - description: Full scan GC-MS (but not GC QExactive, which is EI-HMS) - data_category: processed_data - data_object_type: Direct Infusion FT-ICR MS Analysis Results - file_size_bytes: 5262400 - - id: nmdc:dobj-12-krhrtjw9 - type: nmdc:DataObject - name: emsl_calibration_run.raw - description: GCMS data file - data_object_type: GC-MS Raw Data - data_category: instrument_data - file_size_bytes: 9208349052 - url: https://emsl_site/emsl_calibration_run.raw - - id: nmdc:dobj-99-74d83z - type: nmdc:DataObject - name: soil metagenome raw reads - description: Raw sequencing reads from soil metagenome sample. - data_object_type: Metagenome Raw Reads - data_category: instrument_data - file_size_bytes: 1234567890 - md5_checksum: e5b511d7874186800c4ac88d593c4209 - url: https://example.com/soil_metagenome.fastq.gz - was_generated_by: nmdc:dgns-99-49z38t - - id: nmdc:dobj-99-38t74d - type: nmdc:DataObject - name: mouse gut metagenome raw reads - description: Raw sequencing reads from mouse gut metagenome sample. - data_object_type: Metagenome Raw Read 1 - data_category: instrument_data - file_size_bytes: 9876543210 - md5_checksum: 9c4984a6377192532692281a81f760a3 - url: https://example.com/mouse_gut_metagenome_R1.fastq.gz - was_generated_by: nmdc:wfmsa-99-96d7l.1 - - id: nmdc:dobj-99-7l49z3 - type: nmdc:DataObject - name: mouse gut metagenome raw reads - description: Raw sequencing reads from mouse gut metagenome sample. - data_object_type: Metagenome Raw Read 2 - data_category: instrument_data - file_size_bytes: 9876543210 - md5_checksum: 8b387395266081701080729a98765f4a - url: https://example.com/mouse_gut_metagenome_R2.fastq.gz - was_generated_by: nmdc:wfmsa-99-96d7l.1 - - id: nmdc:dobj-99-9t74d8 - type: nmdc:DataObject - name: human gut metagenome assembled contigs - description: Assembled contigs from human gut metagenome sample. - data_object_type: Metagenome Raw Reads - data_category: instrument_data - file_size_bytes: 5678901234 - md5_checksum: 7a2938b51609f4c38d75e64a9012b3c8 - url: https://example.com/human_gut_metagenome_contigs.fasta - was_generated_by: nmdc:wfmgas-99-v9w6y.1 - - id: nmdc:dobj-99-6y6j6n - type: nmdc:DataObject - name: human gut metagenome functional annotation - description: Functional annotations for human gut metagenome contigs. - data_object_type: Functional Annotation GFF - data_category: processed_data - file_size_bytes: 4321098765 - md5_checksum: 6b1827a40598e3c27d64f53a8901c2b7 - url: https://example.com/human_gut_metagenome_annotation.gff - was_generated_by: nmdc:wfmgan-99-4d83z.1 - - id: nmdc:dobj-12-jdhk9537 - type: nmdc:DataObject - name: BMI_HY7W2BGXG_Plate19S_13WellG10_R1.fastq.gz - description: Test R1 data - data_object_type: Metagenome Raw Read 1 - data_category: instrument_data - url: https://storage.neonscience.org/neon-microbial-raw-seq-files/2020/BMI_HY7W2BGXG_mms_R1/BMI_HY7W2BGXG_Plate19S_13WellG10_R1.fastq.gz - - id: nmdc:dobj-12-yx0tfp52 - type: nmdc:DataObject - name: W2BGXG_Plate19S_13WellG10_R2.fastq.gz - description: Test R2 data - data_object_type: Metagenome Raw Read 2 - data_category: instrument_data - url: https://storage.neonscience.org/neon-microbial-raw-seq-files/2020/BMI_HY7W2BGXG_mms_R2/BMI_HY7W2BGXG_Plate19S_13WellG10_R2.fastq.gz - - id: nmdc:dobj-12-71q7wv80 - type: nmdc:DataObject - name: 1472_51293.filtered.fastq.gz - description: Test filtered data for NEON - data_object_type: Filtered Sequencing Reads - data_category: processed_data - url: https://data.microbiomedata.org/data/1472_51293/qa/1472_51293.filtered.fastq.gz -material_processing_set: - - id: nmdc:extrp-99-abcdef - type: nmdc:Extraction - name: DNA extraction of NEON sample WREF_072-O-20190618-COMP - description: DNA extraction of NEON sample WREF_072-O-20190618-COMP using SOP BMI_dnaExtractionSOP_v7 - has_input: - - nmdc:procsm-99-123456 - has_output: - - nmdc:procsm-99-101010 - start_date: '2019-99-08' - end_date: '2019-99-08' - qc_status: pass - extraction_targets: - - DNA - input_mass: + has_raw_value: 0.1667 mL + has_numeric_value: 0.1667 + has_unit: mL +- id: nmdc:chcpr-99-01 + type: nmdc:ChemicalConversionProcess + name: Protein_digestion_trypsin + description: Trypsin digestion of proteins from nmdc:procsm-99-02 for analysis + has_input: + - nmdc:procsm-99-02 + has_output: + - nmdc:procsm-99-05 + processing_institution: EMSL + chemical_conversion_category: protease_cleavage + duration: + type: nmdc:QuantityValue + has_raw_value: 3 h + has_numeric_value: 3 + has_unit: h + temperature: + type: nmdc:QuantityValue + has_raw_value: 37 C + has_numeric_value: 37 + has_unit: C + substances_used: + - type: nmdc:PortionOfSubstance + known_as: trypsin + substance_role: ms_proteolytic_enzyme + volume: type: nmdc:QuantityValue - has_numeric_value: 0.25 - has_unit: gram - - id: nmdc:extrp-99-74d83z - type: nmdc:Extraction - name: soil DNA extraction - has_input: - - nmdc:bsm-99-74d83z - has_output: - - nmdc:procsm-99-k4m6j - extraction_targets: - - DNA - input_mass: + has_raw_value: 0.004 mL + has_numeric_value: 0.004 + has_unit: mL +- id: nmdc:dispro-99-02 + type: nmdc:DissolvingProcess + name: Dissolving Lipids + description: Dissolving lipids from nmdc:procsm-99-03 + has_input: + - nmdc:procsm-99-03 + has_output: + - nmdc:procsm-99-06 + processing_institution: EMSL + substances_used: + - type: nmdc:PortionOfSubstance + known_as: chloroform + substance_role: solvent + volume: type: nmdc:QuantityValue - has_numeric_value: 0.25 - has_unit: g - - id: nmdc:extrp-99-96d7l - type: nmdc:Extraction - name: mouse gut DNA extraction - has_input: - - nmdc:bsm-99-49z38t - has_output: - - nmdc:procsm-99-29dl - extraction_targets: - - DNA + has_raw_value: 0.3333 mL + has_numeric_value: 0.3333 + has_unit: mL + - type: nmdc:PortionOfSubstance + known_as: methanol + substance_role: solvent volume: type: nmdc:QuantityValue - has_numeric_value: 100 - has_unit: µL - - id: nmdc:extrp-99-v9w6y - type: nmdc:Extraction - name: human gut DNA extraction - has_input: - - nmdc:bsm-99-bbbbbb - has_output: - - nmdc:procsm-99-3z8t - extraction_targets: - - DNA -field_research_site_set: - - id: nmdc:frsite-99-SPreao - type: nmdc:FieldResearchSite - name: BESC-13-CL1_35_33 - description: Bioscales tree BESC-13-CL1_35_33 - - id: nmdc:frsite-99-h2mYFG - type: nmdc:FieldResearchSite - name: BESC-13-CL2_39_29 - description: Bioscales tree BESC-13-CL2_39_29 - - id: nmdc:frsite-99-78f4bc - type: nmdc:FieldResearchSite - name: Grassland Site A - description: a grassland research site - - id: nmdc:frsite-99-k4m6j9 - type: nmdc:FieldResearchSite - name: Lake B - description: a freshwater lake - - id: nmdc:frsite-99-k48dl3 - type: nmdc:FieldResearchSite - name: Human Subject X - description: a human subject enrolled in a microbiome study - - id: nmdc:frsite-99-29dl6v - type: nmdc:FieldResearchSite - name: Amazon Rainforest Site 1 - description: A research site located in the Amazon rainforest. - lat_lon: - type: nmdc:GeolocationValue - latitude: -3.45678901 - longitude: -65.43210987 - - id: nmdc:frsite-99-96d7l4 - type: nmdc:FieldResearchSite - name: Mouse Cage 1 - description: A standard laboratory mouse cage. - - id: nmdc:frsite-99-9j6n9t - type: nmdc:FieldResearchSite - name: Human Subject Residence - description: The residence of a human subject participating in a microbiome study. -functional_annotation_set: - - type: nmdc:FunctionalAnnotation - has_function: KEGG.ORTHOLOGY:K00001 - subject: nmdc:geneproduct-99-ASDSDGASDGAS - was_generated_by: nmdc:wfmgan-99-4d83z.1 - feature_category: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: SO:0000316 - term: - id: SO:0000316 - type: nmdc:OntologyClass - - type: nmdc:FunctionalAnnotation - has_function: KEGG.ORTHOLOGY:K00002 - subject: nmdc:geneproduct-99-SDGASDGASDG - was_generated_by: nmdc:wfmgan-99-4d83z.1 - feature_category: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: SO:0000316 - term: - id: SO:0000316 - type: nmdc:OntologyClass - - type: nmdc:FunctionalAnnotation - has_function: KEGG.ORTHOLOGY:K01198 - subject: nmdc:geneproduct-k2d-7v9t3 - was_generated_by: nmdc:wfmgan-99-4d83z.1 - feature_category: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: SO:0000316 - term: - id: SO:0000316 - type: nmdc:OntologyClass - - type: nmdc:FunctionalAnnotation - has_function: KEGG_PATHWAY:rsk00410 - - type: nmdc:FunctionalAnnotation - has_function: KEGG.REACTION:R00100 - - type: nmdc:FunctionalAnnotation - has_function: RHEA:12345 - - type: nmdc:FunctionalAnnotation - has_function: MetaCyc:RXN-14904 - - type: nmdc:FunctionalAnnotation - has_function: EC:1.1.1.1 - - type: nmdc:FunctionalAnnotation - has_function: GO:0032571 - - type: nmdc:FunctionalAnnotation - has_function: MetaNetX:MNXR101574 - - type: nmdc:FunctionalAnnotation - has_function: SEED:Biotin_biosynthesis - - type: nmdc:FunctionalAnnotation - has_function: KEGG.ORTHOLOGY:K00001 - - type: nmdc:FunctionalAnnotation - has_function: EGGNOG:veNOG12876 - - type: nmdc:FunctionalAnnotation - has_function: PFAM:PF11779 - - type: nmdc:FunctionalAnnotation - has_function: TIGRFAM:TIGR00010 - - type: nmdc:FunctionalAnnotation - has_function: SUPFAM:SSF57615 - - type: nmdc:FunctionalAnnotation - has_function: CATH:1.10.10.200 - - type: nmdc:FunctionalAnnotation - has_function: PANTHER.FAMILY:PTHR12345 -genome_feature_set: - - end: 2000 - seqid: NC_000913.3 - start: 1000 - type: nmdc:GenomeFeature - encodes: nmdc:geneproduct-k2d-7v9t3 - feature_type: CDS - strand: + - feature_category: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: SO:0000316 - term: - id: SO:0000316 - type: nmdc:OntologyClass - - type: nmdc:GenomeFeature - start: 3000 - end: 6000 - seqid: NC_000913.3 - encodes: nmdc:geneproduct-99-ASDSDGASDGAS - feature_type: CDS - strand: + - feature_category: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: SO:0000316 - term: - id: SO:0000316 - type: nmdc:OntologyClass - - type: nmdc:GenomeFeature - start: 10000 - end: 15000 - seqid: NC_000913.3 - encodes: nmdc:geneproduct-99-SDGASDGASDG - feature_type: CDS - strand: + - feature_category: - type: nmdc:ControlledIdentifiedTermValue - has_raw_value: SO:0000316 - term: - id: SO:0000316 - type: nmdc:OntologyClass -material_processing_set: - - id: nmdc:libprp-99-xxx2 - type: nmdc:LibraryPreparation - name: DNA library creation of NEON sample TREE_001-O-20170707-COMP-DNA1 - description: DNA extraction of NEON sample TREE_001-O-20170707-COMP-DNA1 using SOP - BMI_metagenomicsSequencingSOP_v2 - has_input: - - nmdc:procsm-99-abcdef - has_output: - - nmdc:procsm-99-101010 - processing_institution: Battelle - start_date: '2018-09-26' - end_date: '2018-09-26' - library_preparation_kit: KAPA HyperPrep Kit - library_type: DNA - pcr_cycles: 0 - - id: nmdc:libprp-99-xxx1 - type: nmdc:LibraryPreparation - name: RNA library creation of NEON sample TREE_001-O-20170707-COMP-DNA1 - description: RNA extraction of NEON sample TREE_001-O-20170707-COMP-DNA1 using SOP - XX - has_input: - - nmdc:procsm-99-abcdef - has_output: - - nmdc:procsm-99-101010 - processing_institution: Battelle - start_date: '2018-09-26' - end_date: '2018-09-26' - library_preparation_kit: TruSeq RNA Library Prep Kit v2 - library_type: RNA - pcr_cycles: 12 - - id: nmdc:libprp-99-k4m6j - type: nmdc:LibraryPreparation - name: soil DNA library preparation - has_input: - - nmdc:procsm-99-k4m6j - has_output: - - nmdc:procsm-99-96d7 - library_preparation_kit: Illumina DNA Prep - library_type: DNA - pcr_cycles: 12 - - id: nmdc:libprp-99-29dl - type: nmdc:LibraryPreparation - name: mouse gut DNA library preparation - has_input: - - nmdc:procsm-99-29dl - has_output: - - nmdc:procsm-99-38t7 - library_type: DNA - pcr_cycles: 10 - - id: nmdc:libprp-99-3z8t - type: nmdc:LibraryPreparation - name: human gut DNA library preparation - has_input: - - nmdc:procsm-99-3z8t - has_output: - - nmdc:procsm-99-9t7 - library_type: DNA - pcr_cycles: 15 - - id: nmdc:libprp-99-abcdef - type: nmdc:LibraryPreparation - name: DNA library preparation of NEON sample TREE_001-O-20170707-COMP-DNA1 - has_input: - - nmdc:procsm-99-extract - has_output: - - nmdc:procsm-99-library - start_date: '2021-01-15' - end_date: '2021-01-15' - library_type: DNA -workflow_execution_set: - - id: nmdc:wfmag-99-5MiDJM.1 - type: nmdc:MagsAnalysis - name: MAGs activiity 1781_86101 - has_input: - - nmdc:dobj-11-er3d - - nmdc:dobj-11-aer3d - - nmdc:dobj-11-djr3d - has_output: - - nmdc:dobj-11-djkr3 - ended_at_time: '2021-01-10T00:00:00+00:00' - execution_resource: NERSC-Cori - git_url: https://img.jgi.doe.gov - was_informed_by: nmdc:dgns-11-384skd - started_at_time: '2021-01-10T00:00:00+00:00' - binned_contig_num: 489 - input_contig_num: 169782 - low_depth_contig_num: 0 - mags_list: - - type: nmdc:MagBin - bin_name: bins.3 - bin_quality: LQ - completeness: 2.0 - contamination: 0.0 - gene_count: 294 - num_16s: 0 - num_23s: 0 - num_5s: 0 - num_t_rna: 1 - number_of_contig: 11 - too_short_contig_num: 159810 - unbinned_contig_num: 9483 - img_identifiers: - - img.taxon:3300062116 - - id: nmdc:wfmag-99-VOgM5i.1 - type: nmdc:MagsAnalysis - name: MAGs activiity 1781_86089 - has_input: - - nmdc:dobj-11-zdrc - has_output: - - nmdc:dobj-11-adre3 - - nmdc:dobj-11-dr3fb - - nmdc:dobj-11-dr34d - ended_at_time: '2021-01-10T00:00:00+00:00' - execution_resource: NERSC-Cori - git_url: https://img.jgi.doe.gov - was_informed_by: nmdc:dgns-12-348u7d - started_at_time: '2021-01-10T00:00:00+00:00' - binned_contig_num: 206 - input_contig_num: 78376 - low_depth_contig_num: 0 - mags_list: - - type: nmdc:MagBin - bin_name: bins.3 - bin_quality: LQ - completeness: 17.61 - contamination: 0.0 - gene_count: 313 - num_16s: 0 - num_23s: 0 - num_5s: 0 - num_t_rna: 7 - number_of_contig: 58 - too_short_contig_num: 75364 - unbinned_contig_num: 2806 - - id: nmdc:wfmag-6y6-j6n9t.1 - type: nmdc:MagsAnalysis - name: human gut MAGs analysis - has_input: - - nmdc:dobj-99-9t74d - has_output: - - nmdc:dobj-6y6-j6n9t - ended_at_time: '2023-08-01T18:00:00Z' - execution_resource: NERSC-Cori - git_url: https://github.com/microbiomedata/mags_analysis/releases/tag/v1.0.0 - was_informed_by: nmdc:omprc-11-di48df - started_at_time: '2023-08-01T12:00:00Z' - binned_contig_num: 8000 - input_contig_num: 10000 - mags_list: - - type: nmdc:MagBin - bin_name: MAG_2 - bin_quality: medium - completeness: 85.0 - contamination: 5.0 - gene_count: 1500 - number_of_contig: 300 - unbinned_contig_num: 2000 - - id: nmdc:wfmb-99-ABCDEF.1 - type: nmdc:MetabolomicsAnalysis - name: Metabolomics Analysis Activity for nmdc:wfmb-99-ABCDEF.1 - has_input: - - nmdc:dobj-11-34dg - - nmdc:dobj-11-34d - has_output: - - nmdc:dobj-11-dj43d - - nmdc:dobj-11-dajfe - ended_at_time: '2021-09-15T10:13:20+00:00' - execution_resource: NERSC-Cori - git_url: https://example.org/WorkflowExecutionActivity - was_informed_by: nmdc:dgms-11-3u74ds - started_at_time: '2021-08-05T14:48:51+00:00' - metabolomics_analysis_category: gc_ms_metabolomics - - id: nmdc:wfmb-4d8-3z74d.1 - type: nmdc:MetabolomicsAnalysis - name: soil metabolomics analysis - has_input: - - nmdc:dobj-99-74d83z - has_output: - - nmdc:dobj-4d8-3z74d - ended_at_time: '2023-08-02T15:00:00Z' - execution_resource: EMSL - git_url: https://github.com/microbiomedata/metabolomics_analysis/releases/tag/v0.5.0 - was_informed_by: nmdc:omprc-11-di84md - started_at_time: '2023-08-02T09:00:00Z' - has_metabolite_identifications: - - type: nmdc:MetaboliteIdentification - highest_similarity_score: 0.88 - metabolite_identified: CHEBI:16236 - metabolomics_analysis_category: gc_ms_metabolomics - - id: nmdc:wfmgan-99-4d83z.1 - type: nmdc:MetagenomeAnnotation - name: human gut metagenome annotation - has_input: - - nmdc:dobj-99-9t74d - has_output: - - nmdc:dobj-99-6y6j - ended_at_time: '2023-08-03T16:00:00Z' - execution_resource: JGI - git_url: https://github.com/microbiomedata/metagenome_annotation/releases/tag/v2.5.0 - was_informed_by: nmdc:omprc-11-d8484s - started_at_time: '2023-08-03T10:00:00Z' - img_identifiers: - - img.taxon:2763570002 - - id: nmdc:wfmgan-99-101010.1 - alternative_identifiers: - - generic:xxx - description: xxx - end_date: '2019-99-08' - ended_at_time: '2023-08-11T17:00:00Z' - execution_resource: EMSL-RZR - git_url: http://example.com - has_failure_categorization: - - type: nmdc:FailureCategorization - qc_failure_where: MetagenomeAssembly - qc_failure_what: low_read_count - has_input: - - nmdc:dobj-99-7l49x - has_output: - - nmdc:dobj-99-7l49p - img_identifiers: - - img.taxon:3300005610 - name: xxx - was_informed_by: nmdc:omprc-12-a84s8d - processing_institution: JGI - protocol_link: - type: nmdc:Protocol - url: http://example.com - name: xxx - qc_comment: xxx - qc_status: pass - start_date: '2019-99-08' - started_at_time: '2023-08-11T01:00:00Z' - type: nmdc:MetagenomeAnnotation - version: xxx - - id: nmdc:wfmgas-99-B7Vogx.1 - type: nmdc:MetagenomeAssembly - name: Metagenome assembly 1472_51277 - has_input: - - nmdc:dobj-11-djrec - has_output: - - nmdc:dobj-11-11238 - ended_at_time: '2020-03-25T00:00:00+00:00' - execution_resource: LANL-B-div - git_url: https://github.com/microbiomedata/metaAssembly/releases/tag/1.0.0 - was_informed_by: nmdc:omprc-12-a84s8d - asm_score: 3.29 - scaffolds: 429340.0 - scaf_logsum: 303893.0 - scaf_powsum: 32467.0 - scaf_max: 17245.0 - scaf_bp: 192123121.0 - scaf_n50: 132307.0 - scaf_n90: 357156.0 - scaf_l50: 433.0 - scaf_l90: 288.0 - scaf_n_gt50k: 0.0 - scaf_l_gt50k: 0.0 - scaf_pct_gt50k: 0.0 - contigs: 429340.0 - contig_bp: 192123121.0 - ctg_n50: 132307.0 - ctg_l50: 433.0 - ctg_n90: 357156.0 - ctg_l90: 288.0 - ctg_logsum: 303893.0 - ctg_powsum: 32467.0 - ctg_max: 17245.0 - gap_pct: 0.0 - gc_std: 0.09822 - gc_avg: 0.55402 - num_input_reads: 87803950.0 - num_aligned_reads: 63046103.0 - - id: nmdc:wfmgas-99-CvgXTq.1 - type: nmdc:MetagenomeAssembly - name: Metagenome assembly 1472_51278 - has_input: - - nmdc:dobj-11-dfj - has_output: - - nmdc:dobj-11-dfa2ee - ended_at_time: '2020-03-25T00:00:00+00:00' - execution_resource: LANL-B-div - git_url: https://github.com/microbiomedata/metaAssembly/releases/tag/1.0.0 - was_informed_by: nmdc:omprc-12-a84s8d - started_at_time: '2020-03-25T00:00:00+00:00' - asm_score: 3.196 - scaffolds: 747801.0 - scaf_logsum: 483596.0 - scaf_powsum: 51427.0 - scaf_max: 15780.0 - scaf_bp: 333164102.0 - scaf_n50: 235059.0 - scaf_n90: 623912.0 - scaf_l50: 432.0 - scaf_l90: 289.0 - scaf_n_gt50k: 0.0 - scaf_l_gt50k: 0.0 - scaf_pct_gt50k: 0.0 - contigs: 747801.0 - contig_bp: 333164102.0 - ctg_n50: 235059.0 - ctg_l50: 432.0 - ctg_n90: 623912.0 - ctg_l90: 289.0 - ctg_logsum: 483596.0 - ctg_powsum: 51427.0 - ctg_max: 15780.0 - gap_pct: 0.0 - gc_std: 0.09613 - gc_avg: 0.57087 - num_input_reads: 141175680.0 - num_aligned_reads: 95369019.0 - - id: nmdc:wfmgas-99-111111.1 - type: nmdc:MetagenomeAssembly - name: Metagenome assembly 1472_51277 - has_input: - - nmdc:dobj-12-1243 - has_output: - - nmdc:dobj-12-1247 - qc_status: fail - qc_comment: 15% human contamination and assembly size is below 5 MB - has_failure_categorization: - - type: nmdc:FailureCategorization - qc_failure_what: other - qc_failure_where: MetagenomeAssembly - ended_at_time: '2020-03-25T00:00:00+00:00' - execution_resource: LANL-B-div - git_url: https://github.com/microbiomedata/metaAssembly/releases/tag/1.0.0 - was_informed_by: nmdc:omprc-11-fu79d9 - started_at_time: '2020-03-24T00:00:00+00:00' - - id: nmdc:wfmgas-99-v9w6y.1 - type: nmdc:MetagenomeAssembly - name: human gut metagenome assembly - has_input: - - nmdc:dobj-99-7l49z - has_output: - - nmdc:dobj-99-9t74d - ended_at_time: '2023-08-04T14:00:00Z' - execution_resource: NERSC-Perlmutter - git_url: https://github.com/microbiomedata/metagenome_assembly/releases/tag/v1.2.3 - was_informed_by: nmdc:omprc-11-fu79d9 - started_at_time: '2023-08-04T08:00:00Z' - asm_score: 0.85 - scaffolds: 1234.0 - scaf_bp: 567890123.0 - ctg_n50: 10000.0 - - id: nmdc:wfmt-99-4d83z.1 - type: nmdc:MetatranscriptomeExpressionAnalysis - name: human gut metatranscriptome expression - has_input: - - nmdc:dobj-99-9t74d - has_output: - - nmdc:dobj-99-6y6j - ended_at_time: '2023-08-03T16:00:00Z' - execution_resource: JGI - git_url: https://github.com/microbiomedata/metatranscriptome_annotation/releases/tag/v2.5.0 - was_informed_by: nmdc:dgns-12-dfa84a - started_at_time: '2023-08-03T10:00:00Z' - img_identifiers: - - img.taxon:2763570002 - - id: nmdc:wfmt-99-74dk4.1 - type: nmdc:MetatranscriptomeExpressionAnalysis - name: soil metatranscriptome expression - has_input: - - nmdc:dobj-99-74d83z - has_output: - - nmdc:dobj-74d-99-k4 - ended_at_time: '2023-08-07T14:30:00Z' - execution_resource: EMSL-RZR - git_url: https://github.com/microbiomedata/metatranscriptome_analysis/releases/tag/v0.7.8 - was_informed_by: nmdc:dgns-12-dfa84a - started_at_time: '2023-08-07T08:30:00Z' - img_identifiers: - - img.taxon:2763570003 - - id: nmdc:wfnom-99-abcdefg.1 - type: nmdc:NomAnalysis - has_input: - - nmdc:dobj-11-djfer - - nmdc:dobj-11-djjr - has_output: - - nmdc:dobj-11-dj4ba - - nmdc:dobj-11-djre4d - ended_at_time: '2018-11-13T20:20:39+00:00' - execution_resource: EMSL-RZR - git_url: xxx - was_informed_by: nmdc:dgns-12-dfa84b - started_at_time: '2018-11-13T20:20:39+00:00' - - id: nmdc:wfnom-3z7-4d83z.1 - type: nmdc:NomAnalysis - name: soil NOM analysis - has_input: - - nmdc:dobj-99-74d83z - has_output: - - nmdc:dobj-3z7-4d83z - ended_at_time: '2023-08-08T15:30:00Z' - execution_resource: EMSL - git_url: https://github.com/microbiomedata/nom_analysis/releases/tag/v0.3.2 - was_informed_by: nmdc:dgms-12-dfa74b - started_at_time: '2023-08-08T09:30:00Z' -data_generation_set: - - id: nmdc:dgms-99-zUCd5N - type: nmdc:MassSpectrometry - eluent_introduction_category: liquid_chromatography - has_mass_spectrometry_configuration: nmdc:mscon-99-oW43DzG1 - has_chromatography_configuration: nmdc:chrcon-99-oW43DzG0 - analyte_category: lipidome - has_input: - - nmdc:procsm-99-0wxpzf08 - start_date: 30-OCT-14 01.00.00.000000000 AM - end_date: 30-OCT-14 01.30.00.000000000 AM - add_date: 07-MAY-24 12.00.00.000000000 AM - mod_date: 07-MAY-24 12.00.00.000000000 AM - has_output: - - nmdc:dobj-99-msdem1 - associated_studies: - - nmdc:sty-99-555xxx - - id: nmdc:dgms-99-zUCd5x - type: nmdc:MassSpectrometry - eluent_introduction_category: liquid_chromatography - analyte_category: lipidome - has_mass_spectrometry_configuration: nmdc:mscon-99-oW43DzG2 - has_chromatography_configuration: nmdc:chrcon-99-oW43DzG0 - has_input: - - nmdc:procsm-99-0wxpzf08 - start_date: 31-OCT-14 01.00.00.000000000 AM - end_date: 31-OCT-14 01.30.00.000000000 AM - add_date: 07-MAY-24 12.00.00.000000000 AM - mod_date: 07-MAY-24 12.00.00.000000000 AM - has_output: - - nmdc:dobj-99-msdem2 - associated_studies: - - nmdc:sty-99-555xxx - - id: nmdc:dgns-99-9XUVVF - type: nmdc:NucleotideSequencing - name: Forest soil microbial communities from Barre Woods Harvard Forest LTER site, - Petersham, Massachusetts, United States - Inc-BW-C-14-O - description: Forest soil from Barre Woods Harvard Forest LTER site was incubated - at 10C with heavy water. Sample is from a control plot at ambient soil temperature, - organic horizon - top 4cm of soil - alternative_identifiers: - - gold:Gp0225767 - has_input: - - nmdc:bsm-99-yellow - has_output: - - nmdc:dobj-99-90125 - processing_institution: JGI - analyte_category: metagenome - associated_studies: - - nmdc:sty-99-31415 - add_date: 17-AUG-17 05.08.38.451000000 PM - mod_date: 16-OCT-20 02.04.01.374000000 AM - ncbi_project_name: Forest soil microbial communities from Barre Woods Harvard Forest - LTER site, Petersham, Massachusetts, United States - Inc-BW-C-14-O - - id: nmdc:dgns-99-dk9vgI - type: nmdc:NucleotideSequencing - name: Permafrost microbial communities from Stordalen Mire, Sweden - 611E1M metaG - description: Permafrost microbial communities from Stordalen Mire, Sweden - alternative_identifiers: - - gold:Gp0208560 - has_input: - - nmdc:bsm-99-green - has_output: - - nmdc:dobj-99-pizza - processing_institution: JGI - analyte_category: metagenome - associated_studies: - - nmdc:sty-99-8675309 - add_date: 17-MAR-17 04.55.44.822000000 PM - mod_date: 22-MAY-20 06.38.19.576000000 PM - ncbi_project_name: Permafrost microbial communities from Stordalen Mire, Sweden - - 611E1M metaG - - id: nmdc:dgns-99-MVW1FV - type: nmdc:NucleotideSequencing - name: Rhizosphere microbial communities from Carex aquatilis grown in University - of Washington, Seatle, WA, United States - 4-1-23 metaG - description: Rhizosphere microbial communities from Carex aquatilis grown in submerged - peat from a thermokarst bog, University of Washington, Seatle, WA, United States - alternative_identifiers: - - gold:Gp0306221 - has_input: - - nmdc:bsm-99-abc123 - has_output: - - nmdc:dobj-99-34bd7z - processing_institution: JGI - analyte_category: metagenome - associated_studies: - - nmdc:sty-99-dya27z - add_date: 29-MAR-18 01.27.30.036000000 PM - mod_date: 04-APR-20 08.26.35.067000000 AM - ncbi_project_name: Rhizosphere microbial communities from Carex aquatilis grown - in University of Washington, Seatle, WA, United States - 4-1-23 metaG - - id: nmdc:dgns-99-zUCd5N - type: nmdc:NucleotideSequencing - name: Thawing permafrost microbial communities from the Arctic, studying carbon - transformations - Permafrost 712P3D - alternative_identifiers: - - gold:Gp0108335 - has_input: - - nmdc:bsm-99-d57d37 - has_output: - - nmdc:dobj-99-9n9n9n - processing_institution: JGI - analyte_category: metagenome - associated_studies: - - nmdc:sty-99-555xxx - add_date: 30-OCT-14 12.00.00.000000000 AM - mod_date: 22-MAY-20 06.13.12.927000000 PM - ncbi_project_name: Thawing permafrost microbial communities from the Arctic, studying - carbon transformations - Permafrost 712P3D - - id: nmdc:dgns-99-gKlQlF - type: nmdc:NucleotideSequencing - name: Thawing permafrost microbial communities from the Arctic, studying carbon - transformations - Permafrost 612S3M - alternative_identifiers: - - gold:Gp0108340 - has_input: - - nmdc:bsm-99-db3835 - has_output: - - nmdc:dobj-99-z57272 - processing_institution: JGI - analyte_category: metagenome - associated_studies: - - nmdc:sty-99-555xxx - add_date: 30-OCT-14 12.00.00.000000000 AM - mod_date: 22-MAY-20 06.10.59.590000000 PM - ncbi_project_name: Thawing permafrost microbial communities from the Arctic, studying - carbon transformations - Permafrost 612S3M - - id: nmdc:dgns-99-5kgIJR - type: nmdc:NucleotideSequencing - name: Thawing permafrost microbial communities from the Arctic, studying carbon - transformations - Permafrost 712S3S - alternative_identifiers: - - gold:Gp0108341 - has_input: - - nmdc:bsm-99-ornge1 - has_output: - - nmdc:dobj-99-thx198 - processing_institution: JGI - analyte_category: metagenome - associated_studies: - - nmdc:sty-99-555xxx - add_date: 30-OCT-14 12.00.00.000000000 AM - mod_date: 22-MAY-20 06.09.46.171000000 PM - ncbi_project_name: Thawing permafrost microbial communities from the Arctic, studying - carbon transformations - Permafrost 712S3S - - id: nmdc:dgns-99-s9xj2r24 - type: nmdc:NucleotideSequencing - name: Test NEON data - has_input: - - nmdc:procsm-99-xyz3 - has_output: - - nmdc:dobj-12-jdhk9537 - - nmdc:dobj-12-yx0tfp52 - instrument_used: - - nmdc:inst-12-yx0tfp52 - processing_institution: Battelle - analyte_category: metagenome - associated_studies: - - nmdc:sty-99-34xj1150 -material_processing_set: - - id: nmdc:poolp-9x9-1x - type: nmdc:Pooling - name: first pooling process - description: xxx - alternative_identifiers: - - generic:xxx - has_input: - - nmdc:procsm-99-xyz1 - - nmdc:procsm-99-xyz2 - has_output: - - nmdc:procsm-99-xyz3 - - id: nmdc:poolp-99-r9j8v - type: nmdc:Pooling - name: soil sample pooling - has_input: - - nmdc:procsm-99-k4m6j - - nmdc:procsm-99-29dl - - nmdc:procsm-99-3z8t - has_output: - - nmdc:procsm-99-t2r77 - - id: nmdc:poolp-99-l6f5k - type: nmdc:Pooling - name: water sample pooling - has_input: - - nmdc:bsm-99-t2r77l - - nmdc:bsm-99-x971d3 - - nmdc:bsm-99-c6dlm7 - has_output: - - nmdc:procsm-99-x971 - - id: nmdc:poolp-99-y6v9w - type: nmdc:Pooling - name: human gut sample pooling - has_input: - - nmdc:bsm-99-p7k6v9 - - nmdc:bsm-99-bbbbbb - - nmdc:bsm-99-d9j6n9 - has_output: - - nmdc:procsm-99-d9j6 - - id: nmdc:poolp-99-abcdef - type: nmdc:Pooling - name: first pooling process - description: This is the first pooling process that has ever occurred on earth - alternative_identifiers: - - generic:ps1_alt_id - has_input: - - nmdc:bsm-99-abcdef1 - - nmdc:bsm-99-abcdef2 - - nmdc:bsm-99-abcdef3 - has_output: - - nmdc:procsm-99-pooled - start_date: '2021-01-14' - end_date: '2021-01-14' + has_raw_value: 0.1667 mL + has_numeric_value: 0.1667 + has_unit: mL +- id: nmdc:extrp-99-abcdef + type: nmdc:Extraction + name: DNA extraction of NEON sample WREF_072-O-20190618-COMP + description: DNA extraction of NEON sample WREF_072-O-20190618-COMP using SOP BMI_dnaExtractionSOP_v7 + has_input: + - nmdc:procsm-99-123456 + has_output: + - nmdc:procsm-99-555555 + start_date: '2019-11-08' + end_date: '2019-11-08' + qc_status: pass + extraction_targets: + - DNA + input_mass: + type: nmdc:QuantityValue + has_numeric_value: 0.25 + has_unit: gram +- id: nmdc:extrp-99-abcdeg + type: nmdc:Extraction + name: DNA extraction of NEON sample WREF_072-O-20190618-COMP + has_input: + - nmdc:procsm-99-123456 + has_output: + - nmdc:procsm-99-987654 +- id: nmdc:libprp-99-123456 + type: nmdc:LibraryPreparation + name: DNA library creation of NEON sample TREE_001-O-20170707-COMP-DNA1 + description: DNA extraction of NEON sample TREE_001-O-20170707-COMP-DNA1 using SOP + BMI_metagenomicsSequencingSOP_v2 + has_input: + - nmdc:bsm-99-987654 + has_output: + - nmdc:procsm-99-555555 + processing_institution: Battelle + start_date: '2018-09-26' + end_date: '2018-09-26' + library_preparation_kit: KAPA HyperPrep Kit + library_type: DNA + pcr_cycles: 0 +- id: nmdc:libprp-99-555555 + type: nmdc:LibraryPreparation + name: RNA library creation of NEON sample TREE_001-O-20170707-COMP-DNA1 + description: RNA extraction of NEON sample TREE_001-O-20170707-COMP-DNA1 using SOP + XX + has_input: + - nmdc:bsm-99-123456 + has_output: + - nmdc:procsm-99-123456 + processing_institution: Battelle + start_date: '2018-09-26' + end_date: '2018-09-26' + library_preparation_kit: TruSeq RNA Library Prep Kit v2 + library_type: RNA + pcr_cycles: 12 +- id: nmdc:libprp-99-555556 + type: nmdc:LibraryPreparation + name: RNA library creation of TREE_001-O-20170707-COMP-RNA + description: RNA extraction of TREE_001-O-20170707-COMP-RNA using SOP 123 + has_input: + - nmdc:bsm-99-123456 + has_output: + - nmdc:procsm-99-123456 + processing_institution: JGI + start_date: '2018-09-26' + end_date: '2018-09-26' + is_stranded: true + library_preparation_kit: TruSeq Stranded mRNA + library_type: RNA + pcr_cycles: 12 + stranded_orientation: sense orientation +- id: nmdc:libprp-99-555557 + type: nmdc:LibraryPreparation + name: RNA library creation of TREE_001-O-20180707-COMP-RNA + description: RNA extraction of TREE_001-O-20180707-COMP-RNA using SOP 127 + has_input: + - nmdc:bsm-99-123457 + has_output: + - nmdc:procsm-99-123457 + processing_institution: JGI + start_date: '2018-09-26' + end_date: '2018-09-26' + is_stranded: true + library_preparation_kit: TruSeq Stranded mRNA + library_type: RNA + pcr_cycles: 12 + stranded_orientation: antisense orientation +- id: nmdc:libprp-99-555558 + type: nmdc:LibraryPreparation + name: RNA library creation of TREE_001-O-20190707-COMP-RNA + description: RNA extraction of TREE_001-O-20190707-COMP-RNA using SOP 130 + has_input: + - nmdc:bsm-99-123458 + has_output: + - nmdc:procsm-99-123459 + processing_institution: JGI + start_date: '2018-09-26' + end_date: '2018-09-26' + is_stranded: false + library_preparation_kit: TruSeq standard mRNA + library_type: RNA + pcr_cycles: 12 +- id: nmdc:libprp-99-abcdef + type: nmdc:LibraryPreparation + name: DNA library preparation of NEON sample TREE_001-O-20170707-COMP-DNA1 + has_input: + - nmdc:procsm-99-extract + has_output: + - nmdc:procsm-99-library + start_date: '2021-01-15' + end_date: '2021-01-15' + library_type: DNA +- id: nmdc:poolp-99-abcdef + type: nmdc:Pooling + name: first pooling process + description: This is the first pooling process that has ever occurred on earth + has_input: + - nmdc:bsm-99-abcdef1 + - nmdc:bsm-99-abcdef2 + - nmdc:bsm-99-abcdef3 + has_output: + - nmdc:procsm-99-xyz1 + start_date: '2021-01-14' + end_date: '2021-01-14' +- id: nmdc:extrp-99-abcdeh + type: nmdc:Extraction + name: DNA extraction of NEON sample WREF_072-O-20190618-COMP + description: DNA extraction of NEON sample WREF_072-O-20190618-COMP using SOP BMI_dnaExtractionSOP_v7 + has_input: + - nmdc:procsm-99-123456 + has_output: + - nmdc:procsm-99-555555 + start_date: '2019-11-08' + end_date: '2019-11-08' + qc_status: pass + extraction_targets: + - DNA + input_mass: + type: nmdc:QuantityValue + has_numeric_value: 0.25 + has_unit: gram +- id: nmdc:poolp-00-123456 + type: nmdc:Pooling + has_input: + - nmdc:bsm-00-111111 + - nmdc:bsm-00-222222 + has_output: + - nmdc:procsm-00-123456 +- id: nmdc:extrp-00-999999 + type: nmdc:Extraction + has_input: + - nmdc:bsm-00-435737 + has_output: + - nmdc:procsm-00-0938548 +- id: nmdc:libprp-00-999999 + type: nmdc:LibraryPreparation + has_input: + - nmdc:procsm-00-0938548 + has_output: + - nmdc:procsm-00-sdsdll +- id: nmdc:poolp-9x9-1x + type: nmdc:Pooling + name: first pooling process + description: xxx + alternative_identifiers: + - generic:xxx + has_input: + - nmdc:bsm-99-123456 + - nmdc:bsm-99-987654 + has_output: + - nmdc:procsm-99-555555 +- id: nmdc:poolp-9x9-1y + type: nmdc:Pooling + name: first pooling process + has_input: + - nmdc:bsm-99-abcdef1 + - nmdc:bsm-99-abcdef2 + - nmdc:bsm-99-abcdef3 + has_output: + - nmdc:procsm-99-xyz2 processed_sample_set: - - id: nmdc:procsm-99-k4m6j - type: nmdc:ProcessedSample - name: soil DNA extract - biomaterial_purity: - type: nmdc:QuantityValue - has_numeric_value: 1.8 - has_unit: 260/280 - dna_concentration: 123.0 - - id: nmdc:procsm-99-29dl - type: nmdc:ProcessedSample - name: mouse gut DNA extract - - id: nmdc:procsm-99-3z8t - type: nmdc:ProcessedSample - name: human gut DNA extract - - id: nmdc:procsm-99-96d7 - type: nmdc:ProcessedSample - name: soil DNA library - - id: nmdc:procsm-99-38t7 - type: nmdc:ProcessedSample - name: mouse gut DNA library - - id: nmdc:procsm-99-9t7 - type: nmdc:ProcessedSample - name: human gut DNA library - - id: nmdc:procsm-99-t2r77 - type: nmdc:ProcessedSample - name: pooled soil sample - - id: nmdc:procsm-99-x971 - type: nmdc:ProcessedSample - name: pooled water sample - - id: nmdc:procsm-99-d9j6 - type: nmdc:ProcessedSample - name: pooled human gut sample - - id: nmdc:procsm-99-dtTMNb - type: nmdc:ProcessedSample - name: WOOD_024-M-20190715-COMP-DNA1 - description: Extracted DNA from WOOD_024-M-20190715-COMP - biomaterial_purity: - type: nmdc:QuantityValue - has_numeric_value: 2 - external_database_identifiers: - - neon.identifier:19S_31_2826 - - id: nmdc:procsm-99-xyz1 - type: nmdc:ProcessedSample - name: first processed sample set - - id: nmdc:procsm-99-xyz2 - type: nmdc:ProcessedSample - name: first DNA extract - - id: nmdc:procsm-99-xyz3 - type: nmdc:ProcessedSample - name: first library -workflow_execution_set: - - id: nmdc:wfrbt-99-74d83.1 - type: nmdc:ReadBasedTaxonomyAnalysis - name: soil read-based taxonomy analysis - has_input: - - nmdc:dobj-99-74d83z - has_output: - - nmdc:dobj-99-74d83 - ended_at_time: '2023-08-09T16:30:00Z' - execution_resource: LANL-B-div - git_url: https://github.com/microbiomedata/read_based_taxonomy_analysis/releases/tag/v0.4.5 - was_informed_by: nmdc:dgns-11-sdkr82 - started_at_time: '2023-08-09T10:30:00Z' - - id: nmdc:wfrqc-12-63da5n74.1 - type: nmdc:ReadQcAnalysis - name: 'TEST Read QC Activity for nmdc:wfrqc-12-63da5n74 ' - has_input: - - nmdc:dobj-12-jdhk9537 - - nmdc:dobj-12-yx0tfp52 - has_output: - - nmdc:dobj-12-71q7wv80 - - nmdc:dobj-12-y236qp68 - ended_at_time: '2023-03-23T17:17:05.111725+00:00' - execution_resource: NERSC-Cori - git_url: https://github.com/microbiomedata/ReadsQC - was_informed_by: nmdc:omprc-12-38fk74 - started_at_time: '2023-03-23T17:17:05.111689+00:00' - version: b1.0.7 - - id: nmdc:wfrqc-99-hemh0a87.1 - type: nmdc:ReadQcAnalysis - name: Read QC Activity for nmdc:wfrqc-99-hemh0a87.1 - has_input: - - nmdc:dobj-99-1k62bt83 - - nmdc:dobj-99-e8hs8y25 - qc_status: fail - qc_comment: Failure during call-stage to interleave fastq files - has_failure_categorization: - - type: nmdc:FailureCategorization - qc_failure_what: malformed_data - qc_failure_where: ReadQcAnalysis - ended_at_time: '2023-08-30T13:26:02.892410+00:00' - execution_resource: NERSC-Perlmutter - git_url: https://github.com/microbiomedata/ReadsQC - was_informed_by: nmdc:omprc-11-di48s4 - started_at_time: '2023-08-29T19:41:47.365957+00:00' - version: v1.0.8 - - id: nmdc:wfrqc-99-hemh0a88.1 - type: nmdc:ReadQcAnalysis - name: Read QC Activity for nmdc:wfrqc-99-hemh0a88.1 - has_input: - - nmdc:dobj-99-1k62bt83 - - nmdc:dobj-99-e8hs8y25 - has_output: - - nmdc:dobj-99-e8hs8y26 - - nmdc:dobj-99-e8hs8y27 - - nmdc:dobj-99-e8hs8y28 - qc_status: pass - qc_comment: Number of output reads from readqc is above threshold (6000000 > 1000000) - ended_at_time: '2023-08-30T13:26:02.892410+00:00' - execution_resource: NERSC-Perlmutter - git_url: https://github.com/microbiomedata/ReadsQC - was_informed_by: nmdc:dgns-11-2947fa - started_at_time: '2023-08-29T19:41:47.365957+00:00' - version: v1.0.8 - - id: nmdc:wfrqc-99-hemh0a90.1 - type: nmdc:ReadQcAnalysis - name: Read QC Activity for nmdc:wfrqc-99-hemh0a87.1 - has_input: - - nmdc:dobj-99-1k62bt83 - - nmdc:dobj-99-e8hs8y25 - has_output: - - nmdc:dobj-99-e8hs8y26 - - nmdc:dobj-99-e8hs8y27 - - nmdc:dobj-99-e8hs8y28 - qc_status: fail - qc_comment: Most data removed for artifacts - has_failure_categorization: - - type: nmdc:FailureCategorization - qc_failure_what: low_read_count - qc_failure_where: ReadQcAnalysis - ended_at_time: '2023-08-30T13:26:02.892410+00:00' - execution_resource: NERSC-Perlmutter - git_url: https://github.com/microbiomedata/ReadsQC - was_informed_by: nmdc:dgns-11-d84da8 - started_at_time: '2023-08-29T19:41:47.365957+00:00' - version: v1.0.8 - - id: nmdc:wfrqc-99-7l49z.1 - type: nmdc:ReadQcAnalysis - name: mouse gut read QC analysis - has_input: - - nmdc:dobj-99-38t74d - - nmdc:dobj-99-7l49z3 - has_output: - - nmdc:dobj-99-7l49z - ended_at_time: '2023-08-10T15:00:00Z' - execution_resource: JGI - git_url: https://github.com/microbiomedata/read_qc_analysis/releases/tag/v0.2.1 - was_informed_by: nmdc:dgns-11-xc988a - started_at_time: '2023-08-10T09:00:00Z' - input_read_count: 10000000.0 - output_read_count: 9000000.0 +- id: nmdc:procsm-99-01 + type: nmdc:ProcessedSample + name: methanol_extracted_metabolites + description: metabolites in methanol from MPLEx + sampled_portion: + - methanol_layer +- id: nmdc:procsm-99-02 + type: nmdc:ProcessedSample + name: extracted_proteins + description: protein interlayer from MPLEx + sampled_portion: + - interlayer +- id: nmdc:procsm-99-03 + type: nmdc:ProcessedSample + name: chloroform_extracted_lipids + description: lipids in chloroform from MPLEx +- id: nmdc:procsm-99-04 + type: nmdc:ProcessedSample + name: resuspended_metabolites + description: resuspended metabolites for GC-MS + sampled_portion: + - methanol_layer +- id: nmdc:procsm-99-05 + type: nmdc:ProcessedSample + name: trypsin_digested_proteins + description: digested proteins for LC-MS + sampled_portion: + - interlayer +- id: nmdc:procsm-99-06 + type: nmdc:ProcessedSample + name: resuspended_lipids + description: resuspended lipids for LC-MS +- id: nmdc:procsm-99-dtTMNb + type: nmdc:ProcessedSample + name: WOOD_024-M-20190715-COMP-DNA1 + description: Extracted DNA from WOOD_024-M-20190715-COMP +- id: nmdc:procsm-99-xyz1 + type: nmdc:ProcessedSample + name: first processed sample set +- id: nmdc:procsm-99-xyz2 + type: nmdc:ProcessedSample + name: first DNA extract +- id: nmdc:procsm-99-xyz3 + type: nmdc:ProcessedSample + name: first library +- id: nmdc:procsm-99-xyz4 + type: nmdc:ProcessedSample + name: first processed sample set +- id: nmdc:procsm-99-xyz5 + type: nmdc:ProcessedSample + name: first DNA extract +- id: nmdc:procsm-99-xyz6 + type: nmdc:ProcessedSample + name: first library +- id: nmdc:procsm-99-dtTMNc + type: nmdc:ProcessedSample + name: WOOD_024-M-20190715-COMP-DNA1 + description: Extracted DNA from WOOD_024-M-20190715-COMP + biomaterial_purity: + type: nmdc:QuantityValue + has_numeric_value: 2 + external_database_identifiers: + - neon.identifier:19S_31_2826 + sampled_portion: + - supernatant +- id: nmdc:procsm-99-dtTMNd + type: nmdc:ProcessedSample study_set: - - id: nmdc:sty-99-oJmAOs - type: nmdc:Study - name: Forest soil microbial communities from Barre Woods Harvard Forest LTER site, - Petersham, Massachusetts, United States - description: The goal of this study is to learn the molecular mechanisms underlying - changes in the temperature sensitive respiration response of forest soils to long-term - experimental warming - study_category: consortium - gold_study_identifiers: - - gold:Gs121212 - ecosystem: Environmental - ecosystem_category: Terrestrial - ecosystem_subtype: Unclassified - ecosystem_type: Soil - specific_ecosystem: Forest Soil - associated_dois: - - doi_value: doi:10.25585/1488215 - doi_category: dataset_doi - type: nmdc:Doi - doi_provider: osti - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Jeffrey Blanchard - - id: nmdc:sty-99-3bQQ4j - type: nmdc:Study - name: Rhizosphere microbial communities from Carex aquatilis grown in University - of Washington, Seatle, WA, United States - description: The goal of this study is to advance understanding of the response - of methane production and methane oxidation to changes in plant productivity so - that modeled representations of these processes and interactions can be improved. - study_category: research_study - gold_study_identifiers: - - gold:Gs0134277 - ecosystem: Host-associated - ecosystem_category: Plants - ecosystem_subtype: Rhizosphere - ecosystem_type: Roots - specific_ecosystem: Soil - associated_dois: - - doi_value: doi:10.25585/1488209 - doi_category: dataset_doi - type: nmdc:Doi - doi_provider: osti - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Rebecca Neumann - - id: nmdc:sty-99-boww8R - type: nmdc:Study - name: Avena fatua rhizosphere microbial communities from Hopland, California, USA, - for root-enhanced decomposition of organic matter studies - description: Using analytical expertise at both the JGI and EMSL, we plan to follow - successional patterns of protein expression by root-associated microorganisms. - This work builds on foundational research we are conducting with the common California - grassland plant, Avena fatua, grown in Hopland, CA soil (FOA DE-PS02-09ER09-25). - Using our 16-chamber 13C labeling facility at UC Berkeley, we have shown that - elevated CO2 increased the amount of C allocated belowground, and increased the - yield of root biomass. The rhizosphere microbial community undergoes a succession - as the root grows, senesces, and dies. In elevated CO2 treatments, we also detect - a greater amount of root-derived 13C in the mineral-associated heavy fraction - of the soil, which is commonly assumed to reflect longer term stabilization. \n - \nIn our JGI-EMSL project, we will follow over time how roots impact the functional - capacity of the rhizosphere microbiome to enzymatically mediate decomposition - processes. We hypothesize that root-exudate stimulation of soil microbial populations - results in elevated expression of biomolecules (transcripts, enzymes, metabolites) - for the decomposition of macromolecular C compounds. - study_category: research_study - gold_study_identifiers: - - gold:Gs999999 - ecosystem: Host-associated - ecosystem_category: Plants - ecosystem_subtype: Soil - ecosystem_type: Rhizosphere - specific_ecosystem: Unclassified - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Mary Firestone - - id: nmdc:sty-99-hfaLvo - type: nmdc:Study - name: Cyanobacterial communities from the Joint Genome Institute, California, USA - description: 'We propose to utilize the unique resources at EMSL and the JGI to +- id: nmdc:sty-11-r2h77870 + type: nmdc:Study + study_category: research_study + gnps_task_identifiers: + - gnps.task:4b848c342a4f4abc871bdf8a09a60807 + - gnps.task:51cc733a80ed41139ecdd1bedf3c01af + - gnps.task:8062948726c543dba53ec58c0f1ebb25 + - gnps.task:f8efbde4cc154db6a4cf269072d42d40 + jgi_portal_study_identifiers: + - jgi.proposal:507130 +- id: nmdc:sty-99-FkQIsc + type: nmdc:Study + name: Permafrost microbial communities from Stordalen Mire, Sweden + description: Thawing permafrost is one of the largest soil carbon pools on the planet. + The goal of this project is to study microbial communities that participate in + the soil carbon cycle. + study_category: research_study + gold_study_identifiers: + - gold:Gs123456789 + ecosystem: Environmental + ecosystem_category: Terrestrial + ecosystem_subtype: Wetlands + ecosystem_type: Soil + specific_ecosystem: Permafrost + associated_dois: + - doi_value: doi:10.25585/1488217 + doi_category: dataset_doi + type: nmdc:Doi + doi_provider: osti + principal_investigator: + type: nmdc:PersonValue + has_raw_value: Virginia Rich +- id: nmdc:sty-99-oJmAOs + type: nmdc:Study + name: Forest soil microbial communities from Barre Woods Harvard Forest LTER site, + Petersham, Massachusetts, United States + description: The goal of this study is to learn the molecular mechanisms underlying + changes in the temperature sensitive respiration response of forest soils to long-term + experimental warming + study_category: consortium + gold_study_identifiers: + - gold:Gs121212 + ecosystem: Environmental + ecosystem_category: Terrestrial + ecosystem_subtype: Unclassified + ecosystem_type: Soil + specific_ecosystem: Forest Soil + associated_dois: + - doi_value: doi:10.25585/1488215 + doi_category: dataset_doi + type: nmdc:Doi + doi_provider: osti + principal_investigator: + type: nmdc:PersonValue + has_raw_value: Jeffrey Blanchard +- id: nmdc:sty-99-3bQQ4j + type: nmdc:Study + name: Rhizosphere microbial communities from Carex aquatilis grown in University + of Washington, Seatle, WA, United States + description: The goal of this study is to advance understanding of the response + of methane production and methane oxidation to changes in plant productivity so + that modeled representations of these processes and interactions can be improved. + study_category: research_study + gold_study_identifiers: + - gold:Gs0134277 + ecosystem: Host-associated + ecosystem_category: Plants + ecosystem_subtype: Rhizosphere + ecosystem_type: Roots + specific_ecosystem: Soil + associated_dois: + - doi_value: doi:10.25585/1488209 + doi_category: dataset_doi + type: nmdc:Doi + doi_provider: osti + principal_investigator: + type: nmdc:PersonValue + has_raw_value: Rebecca Neumann +- id: nmdc:sty-11-34xj1152 + type: nmdc:Study + name: NEON Parent Consortium + description: The parent consortium of all the NEON consortia + study_category: consortium +- id: nmdc:sty-11-34xj1150 + type: nmdc:Study + name: 'National Ecological Observatory Network: soil metagenomes (DP1.10107.001)' + description: The National Science Foundation's National Ecological Observatory Network + (NEON) is a continental-scale observation facility operated by Battelle and designed + to collect long-term open access ecological data to better understand how U.S. + ecosystems are changing. + study_category: consortium + gold_study_identifiers: + - gold:Gs0144570 + - gold:Gs0161344 + funding_sources: + - 'NSF#1724433 National Ecological Observatory Network: Operations Activities' + part_of: + - nmdc:sty-11-34xj1152 + principal_investigator: + type: nmdc:PersonValue + has_raw_value: Kate Thibault + email: kthibault@battelleecology.org + name: Kate Thibault + orcid: orcid:0000-0003-3477-6424 + profile_image_url: https://portal.nersc.gov/project/m3408/profile_images/thibault_katy.jpg + study_image: + - type: nmdc:ImageValue + url: https://portal.nersc.gov/project/m3408/profile_images/nmdc_sty-11-34xj1150.jpg + title: 'National Ecological Observatory Network: soil metagenomes (DP1.10107.001)' + websites: + - https://www.neonscience.org/ + - https://data.neonscience.org/data-products/DP1.10107.001 + - https://data.neonscience.org/api/v0/documents/NEON.DOC.014048vO + - https://data.neonscience.org/api/v0/documents/NEON_metagenomes_userGuide_vE.pdf +- id: nmdc:sty-11-hht5sb92 + type: nmdc:Study + name: 'National Ecological Observatory Network: surface water metagenomes (DP1.20281.001)' + description: The National Science Foundation's National Ecological Observatory Network + (NEON) is a continental-scale observation facility operated by Battelle and designed + to collect long-term open access ecological data to better understand how U.S. + ecosystems are changing. + study_category: consortium + funding_sources: + - 'NSF#1724433 National Ecological Observatory Network: Operations Activities' + part_of: + - nmdc:sty-11-34xj1152 + principal_investigator: + type: nmdc:PersonValue + has_raw_value: Kate Thibault + email: kthibault@battelleecology.org + name: Kate Thibault + orcid: orcid:0000-0003-3477-6424 + study_image: + - type: nmdc:ImageValue + url: https://portal.nersc.gov/project/m3408/profile_images/nmdc_sty-11-34xj1150.jpg + title: 'National Ecological Observatory Network: surface water metagenomes (DP1.20281.001)' + websites: + - https://www.neonscience.org/ + - https://data.neonscience.org/data-products/DP1.20281.001 + - https://data.neonscience.org/api/v0/documents/NEON_metagenomes_userGuide_vE.pdf +- id: nmdc:sty-11-pzmd0x14 + type: nmdc:Study + name: 'National Ecological Observatory Network: benthic metagenomes (DP1.20279.001)' + description: The National Science Foundation's National Ecological Observatory Network + (NEON) is a continental-scale observation facility operated by Battelle and designed + to collect long-term open access ecological data to better understand how U.S. + ecosystems are changing. + study_category: consortium + funding_sources: + - 'NSF#1724433 National Ecological Observatory Network: Operations Activities' + part_of: + - nmdc:sty-11-34xj1152 + principal_investigator: + type: nmdc:PersonValue + email: kthibault@battelleecology.org + name: Kate Thibault + orcid: orcid:0000-0003-3477-6424 + study_image: + - type: nmdc:ImageValue + url: https://portal.nersc.gov/project/m3408/profile_images/nmdc_sty-11-34xj1150.jpg + title: 'National Ecological Observatory Network: benthic metagenomes (DP1.20279.001)' + websites: + - https://www.neonscience.org/ + - https://data.neonscience.org/data-products/DP1.20279.001 + - https://data.neonscience.org/api/v0/documents/NEON_metagenomes_userGuide_vE.pdf +- id: nmdc:sty-99-FkQIsd + type: nmdc:Study + name: Permafrost microbial communities from Stordalen Mire, Sweden + description: Thawing permafrost is one of the largest soil carbon pools on the planet. + The goal of this project is to study microbial communities that participate in + the soil carbon cycle. + study_category: research_study + gnps_task_identifiers: + - gnps.task:4b848c342a4f4abc871bdf8a09a60807 + gold_study_identifiers: + - gold:Gs123456789 + ecosystem: Environmental + ecosystem_category: Terrestrial + ecosystem_subtype: Wetlands + ecosystem_type: Soil + specific_ecosystem: Permafrost + associated_dois: + - doi_value: doi:10.25585/1487763 + doi_category: award_doi + type: nmdc:Doi + doi_provider: jgi + - doi_value: doi:10.25585/1487765 + doi_category: award_doi + type: nmdc:Doi + doi_provider: emsl + - doi_value: doi:10.21/FQSQT4T3 + doi_category: publication_doi + type: nmdc:Doi + doi_provider: jgi + - doi_value: doi:10.1016/j.foodchem.2008.11.065 + doi_category: publication_doi + type: nmdc:Doi + - doi_value: doi:10.1333/s00897980202a + doi_category: dataset_doi + type: nmdc:Doi + doi_provider: ess_dive + - doi_value: doi:10.1093/acprof:oso/9780195159561.001.1 + doi_category: dataset_doi + type: nmdc:Doi + doi_provider: massive + - doi_value: doi:10.6084/m9.figshare.c.7373842 + doi_category: dataset_doi + type: nmdc:Doi + doi_provider: figshare + principal_investigator: + type: nmdc:PersonValue + has_raw_value: Virginia Rich +- id: nmdc:sty-99-FkQIse + type: nmdc:Study + name: Permafrost microbial communities from Stordalen Mire, Sweden + description: Thawing permafrost is one of the largest soil carbon pools on the planet. + The goal of this project is to study microbial communities that participate in + the soil carbon cycle. + study_category: research_study + gnps_task_identifiers: + - gnps.task:4b848c342a4f4abc871bdf8a09a60807 + gold_study_identifiers: + - gold:Gs123456789 + ecosystem: Environmental + ecosystem_category: Terrestrial + ecosystem_subtype: Wetlands + ecosystem_type: Soil + specific_ecosystem: Permafrost + associated_dois: + - doi_value: doi:10.25585/1488217 + doi_category: award_doi + type: nmdc:Doi + doi_provider: emsl + principal_investigator: + type: nmdc:PersonValue + has_raw_value: Virginia Rich +- id: nmdc:sty-99-boww8R + type: nmdc:Study + name: Avena fatua rhizosphere microbial communities from Hopland, California, USA, + for root-enhanced decomposition of organic matter studies + description: Using analytical expertise at both the JGI and EMSL, we plan to follow + successional patterns of protein expression by root-associated microorganisms. + This work builds on foundational research we are conducting with the common California + grassland plant, Avena fatua, grown in Hopland, CA soil (FOA DE-PS02-09ER09-25). + Using our 16-chamber 13C labeling facility at UC Berkeley, we have shown that + elevated CO2 increased the amount of C allocated belowground, and increased the + yield of root biomass. The rhizosphere microbial community undergoes a succession + as the root grows, senesces, and dies. In elevated CO2 treatments, we also detect + a greater amount of root-derived 13C in the mineral-associated heavy fraction + of the soil, which is commonly assumed to reflect longer term stabilization. \n + \nIn our JGI-EMSL project, we will follow over time how roots impact the functional + capacity of the rhizosphere microbiome to enzymatically mediate decomposition + processes. We hypothesize that root-exudate stimulation of soil microbial populations + results in elevated expression of biomolecules (transcripts, enzymes, metabolites) + for the decomposition of macromolecular C compounds. + study_category: research_study + gold_study_identifiers: + - gold:Gs999999 + ecosystem: Host-associated + ecosystem_category: Plants + ecosystem_subtype: Soil + ecosystem_type: Rhizosphere + specific_ecosystem: Unclassified + principal_investigator: + type: nmdc:PersonValue + has_raw_value: Mary Firestone +- id: nmdc:sty-99-hfaLvo + type: nmdc:Study + name: Cyanobacterial communities from the Joint Genome Institute, California, USA + description: 'We propose to utilize the unique resources at EMSL and the JGI to obtain a better understanding of the phylogenetic and functional diversity of cyanobacteria that have been collected from DOE mission relevant environments (e.g. alkaline and acidic hot springs, and hypersaline terrestrial and water habitats) @@ -4277,22 +2723,22 @@ study_set: we will generate metaproteomic and metametabolomic data from 10 selected axenic and 10 mixed cultures. We will request access and support to and with mass spectrometry, NMR spectrometry, and computation time on Chinook from EMSL.' - study_category: research_study - gold_study_identifiers: - - gold:Gs999999 - ecosystem: Host-associated - ecosystem_category: Microbial - ecosystem_subtype: Unclassified - ecosystem_type: Bacteria - specific_ecosystem: Unclassified - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Matthias Hess - - id: nmdc:sty-99-dkDZYe - type: nmdc:Study - name: Thawing permafrost microbial communities from the Arctic, studying carbon - transformations - description: 'A fundamental challenge of microbial environmental science is to understand + study_category: research_study + gold_study_identifiers: + - gold:Gs999999 + ecosystem: Host-associated + ecosystem_category: Microbial + ecosystem_subtype: Unclassified + ecosystem_type: Bacteria + specific_ecosystem: Unclassified + principal_investigator: + type: nmdc:PersonValue + has_raw_value: Matthias Hess +- id: nmdc:sty-99-dkDZYe + type: nmdc:Study + name: Thawing permafrost microbial communities from the Arctic, studying carbon + transformations + description: 'A fundamental challenge of microbial environmental science is to understand how earth systems will respond to climate change. A parallel challenge in biology is to unverstand how information encoded in organismal genes manifests as biogeochemical processes at ecosystem-to-global scales. These grand challenges intersect in the @@ -4300,388 +2746,537 @@ study_set: processes and a key driver of climate through the greenhouse gases carbon dioxide (CO2) and methane (CH4). A key aspect of these challenges is the C cycle implications of the predicted dramatic shrinkage in northern permafrost in the coming century. ' - study_category: research_study - gold_study_identifiers: - - gold:Gs999999 - ecosystem: Environmental - ecosystem_category: Terrestrial - ecosystem_subtype: Wetlands - ecosystem_type: Soil - specific_ecosystem: Permafrost - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Virginia Rich - - id: nmdc:sty-99-34xj1152 - type: nmdc:Study - name: NEON Parent Consortium - description: The parent consortium of all the NEON consortia - study_category: consortium - - id: nmdc:sty-99-34xj1150 - type: nmdc:Study - name: 'National Ecological Observatory Network: soil metagenomes (DP1.10107.001)' - description: The National Science Foundation's National Ecological Observatory Network - (NEON) is a continental-scale observation facility operated by Battelle and designed - to collect long-term open access ecological data to better understand how U.S. - ecosystems are changing. - study_category: consortium - gold_study_identifiers: - - gold:Gs0144570 - - gold:Gs0161344 - funding_sources: - - 'NSF#1724433 National Ecological Observatory Network: Operations Activities' - part_of: - - nmdc:sty-99-34xj1152 - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Kate Thibault - email: kthibault@battelleecology.org - name: Kate Thibault - orcid: orcid:0000-0003-3477-6424 - profile_image_url: https://portal.nersc.gov/project/m3408/profile_images/thibault_katy.jpg - study_image: - - type: nmdc:ImageValue - url: https://portal.nersc.gov/project/m3408/profile_images/nmdc_sty-99-34xj1150.jpg - title: 'National Ecological Observatory Network: soil metagenomes (DP1.10107.001)' - websites: - - https://www.neonscience.org/ - - https://data.neonscience.org/data-products/DP1.10107.001 - - https://data.neonscience.org/api/v0/documents/NEON.DOC.014048vO - - https://data.neonscience.org/api/v0/documents/NEON_metagenomes_userGuide_vE.pdf - - id: nmdc:sty-99-hht5sb92 - type: nmdc:Study - name: 'National Ecological Observatory Network: surface water metagenomes (DP1.20281.001)' - description: The National Science Foundation's National Ecological Observatory Network - (NEON) is a continental-scale observation facility operated by Battelle and designed - to collect long-term open access ecological data to better understand how U.S. - ecosystems are changing. - study_category: consortium - funding_sources: - - 'NSF#1724433 National Ecological Observatory Network: Operations Activities' - part_of: - - nmdc:sty-99-34xj1152 - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Kate Thibault - email: kthibault@battelleecology.org - name: Kate Thibault - orcid: orcid:0000-0003-3477-6424 - study_image: - - type: nmdc:ImageValue - url: https://portal.nersc.gov/project/m3408/profile_images/nmdc_sty-99-34xj1150.jpg - title: 'National Ecological Observatory Network: surface water metagenomes (DP1.20281.001)' - websites: - - https://www.neonscience.org/ - - https://data.neonscience.org/data-products/DP1.20281.001 - - https://data.neonscience.org/api/v0/documents/NEON_metagenomes_userGuide_vE.pdf - - id: nmdc:sty-99-pzmd0x14 - type: nmdc:Study - name: 'National Ecological Observatory Network: benthic metagenomes (DP1.20279.001)' - description: The National Science Foundation's National Ecological Observatory Network - (NEON) is a continental-scale observation facility operated by Battelle and designed - to collect long-term open access ecological data to better understand how U.S. - ecosystems are changing. - study_category: consortium - funding_sources: - - 'NSF#1724433 National Ecological Observatory Network: Operations Activities' - part_of: - - nmdc:sty-99-34xj1152 - principal_investigator: - type: nmdc:PersonValue - email: kthibault@battelleecology.org - name: Kate Thibault - orcid: orcid:0000-0003-3477-6424 - study_image: - - type: nmdc:ImageValue - url: https://portal.nersc.gov/project/m3408/profile_images/nmdc_sty-99-34xj1150.jpg - title: 'National Ecological Observatory Network: benthic metagenomes (DP1.20279.001)' - websites: - - https://www.neonscience.org/ - - https://data.neonscience.org/data-products/DP1.20279.001 - - https://data.neonscience.org/api/v0/documents/NEON_metagenomes_userGuide_vE.pdf - - id: nmdc:sty-99-b27v55 - type: nmdc:Study - name: Grassland Microbiome Study - description: A study of microbial diversity in grassland soils - study_category: research_study - has_credit_associations: - - applies_to_person: - type: nmdc:PersonValue - has_raw_value: John Smith - email: john.smith@example.org - name: John Smith - orcid: 0000-0002-9876-5432 - applied_roles: - - Data curation - type: prov:Association - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Jane Doe - email: jane.doe@example.org - name: Jane Doe - orcid: 0000-0001-2345-6789 - - id: nmdc:sty-99-t9w6g8 - type: nmdc:Study - name: Freshwater Lake Microbiome Study - description: A study of the microbiome of a freshwater lake - study_category: research_study - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Bob Jones - email: bob.jones@example.org - name: Bob Jones - orcid: 0000-0003-4567-8901 - - id: nmdc:sty-99-q4g1z3 - type: nmdc:Study - name: Human Gut Microbiome Project - description: A large-scale study of the human gut microbiome - study_category: consortium - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Alice Lee - email: alice.lee@example.org - name: Alice Lee - orcid: 0000-0004-7890-1234 - - id: nmdc:sty-99-r2h77870 - type: nmdc:Study - study_category: research_study - gnps_task_identifiers: - - gnps.task:4b848c342a4f4abc871bdf8a09a60807 - - gnps.task:51cc733a80ed41139ecdd1bedf3c01af - - gnps.task:8062948726c543dba53ec58c0f1ebb25 - - gnps.task:f8efbde4cc154db6a4cf269072d42d40 - jgi_portal_study_identifiers: - - jgi.proposal:507130 - - id: nmdc:sty-99-FkQIsc - type: nmdc:Study - name: Permafrost microbial communities from Stordalen Mire, Sweden - description: Thawing permafrost is one of the largest soil carbon pools on the planet. - The goal of this project is to study microbial communities that participate in - the soil carbon cycle. - study_category: research_study - gnps_task_identifiers: - - gnps.task:4b848c342a4f4abc871bdf8a09a60807 - gold_study_identifiers: - - gold:Gs123456789 - ecosystem: Environmental - ecosystem_category: Terrestrial - ecosystem_subtype: Wetlands - ecosystem_type: Soil - specific_ecosystem: Permafrost - associated_dois: - - doi_value: doi:10.25585/1487763 - doi_category: award_doi - type: nmdc:Doi - doi_provider: jgi - - doi_value: doi:10.25585/1487765 - doi_category: award_doi - type: nmdc:Doi - doi_provider: emsl - - doi_value: doi:10.21/FQSQT4T3 - doi_category: publication_doi - type: nmdc:Doi - doi_provider: jgi - - doi_value: doi:10.1016/j.foodchem.2008.11.065 - doi_category: publication_doi - type: nmdc:Doi - - doi_value: doi:10.1333/s00897980202a - doi_category: dataset_doi - type: nmdc:Doi - doi_provider: ess_dive - - doi_value: doi:10.1093/acprof:oso/9780195159561.001.1 - doi_category: dataset_doi - type: nmdc:Doi - doi_provider: massive - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Virginia Rich - - id: nmdc:sty-99-VDYg7R - type: nmdc:Study - study_category: research_study - - id: nmdc:sty-99-w8v82N - type: nmdc:Study - study_category: research_study - - id: nmdc:sty-99-Zv8LJB - type: nmdc:Study - study_category: research_study - - id: nmdc:sty-99-dl968v - type: nmdc:Study - name: Host-Microbe Interactions in the Gut - description: A study investigating the interactions between the gut microbiome and - host health in mice and humans. - study_category: research_study - associated_dois: - - doi_value: doi:10.1038/s41598-023-38765-4 - doi_category: publication_doi - type: nmdc:Doi - - doi_value: doi:10.46936/10.25585/60001234 - doi_category: award_doi - type: nmdc:Doi - doi_provider: emsl - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Dr. Sarah Jones - email: sarah.jones@example.org - name: Dr. Sarah Jones - orcid: 0000-0005-8901-2345 - websites: - - https://joneslab.example.org/ - - id: nmdc:sty-99-z3t9g4 - type: nmdc:Study - name: Human Gut Microbiome Diversity - description: A study exploring the diversity of the human gut microbiome across - different populations. - study_category: consortium - homepage_website: - - https://humanmicrobiome.org/ - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Dr. Michael Lee - email: michael.lee@example.org - name: Dr. Michael Lee - orcid: 0000-0006-9012-3456 - - id: nmdc:sty-99-jX2z3c - type: nmdc:Study - name: Poplar Common Garden Microbial Communities - description: This study investigates the microbial communities associated with poplar - trees in a common garden experiment. - study_category: research_study - related_identifiers: gold:Gs0000001 - alternative_names: - - Poplar Microbiome Project - - Clatskanie Poplar Experiment - associated_dois: - - doi_value: doi:10.1000/fake.doi - doi_category: publication_doi - type: nmdc:Doi - funding_sources: - - National Science Foundation (award no. 9999999) - principal_investigator: - type: nmdc:PersonValue - has_raw_value: FirstName LastName - email: first.last@example.org - name: FirstName LastName - orcid: 0000-0000-0000-0000 - - id: nmdc:sty-99-8n4V9N - type: nmdc:Study - name: Coastal Redwood Rhizosphere Microbiome - description: This study explores the diversity and function of the microbial community - in the rhizosphere of coastal redwood trees. - study_category: research_study - alternative_titles: - - Microbial Ecology of Redwood Forests - - Redwood Root Microbiome - associated_dois: - - doi_value: doi:10.2000/fake.doi - doi_category: dataset_doi - type: nmdc:Doi - doi_provider: edi - funding_sources: - - Save the Redwoods League (grant no. 12345) - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Jane Doe - name: Jane Doe - orcid: 0000-0000-0000-0001 - - id: nmdc:sty-99-4m7Q2b - type: nmdc:Study - name: Microbiome of the Built Environment - description: This research study aims to characterize the microbial communities - found in various built environments, including homes, offices, and hospitals. - study_category: research_study - alternative_names: - - Indoor Microbiome Project - - Built Environment Microorganisms - associated_dois: - - doi_value: doi:10.3000/fake.doi - doi_category: publication_doi - type: nmdc:Doi - funding_sources: - - Alfred P. Sloan Foundation (grant no. 67890) - principal_investigator: - type: nmdc:PersonValue - has_raw_value: Bob Smith - email: bob.smith@example.org - name: Bob Smith - orcid: 0000-0000-0000-0002 -instrument_set: - - id: nmdc:inst-12-dtTMNb - type: nmdc:Instrument - name: Illumina NovaSeq - vendor: illumina - model: novaseq_6000 - - id: nmdc:inst-12-dtTMN3 - type: nmdc:Instrument - name: my favorite Orbitrap - model: exploris_480 -calibration_set: - - id: nmdc:calib-99-zUCd5Q - type: nmdc:CalibrationInformation - internal_calibration: false - calibration_target: retention_index - calibration_object: nmdc:dobj-12-krhrtjw9 - calibration_standard: fames - -configuration_set: - - id: nmdc:mscon-99-oW43DzG1 - name: EMSL lipidomics mass spectrometry method, positive polarity - description: Mass spectrometry method used by EMSL for lipidomics analysis, positive polarity - type: nmdc:MassSpectrometryConfiguration - mass_spectrometry_acquisition_strategy: data_dependent_acquisition - mass_spectrum_collection_modes: - - full_profile - - centroid - resolution_categories: - - high - - low - mass_analyzers: - - Orbitrap - - ion_trap - ionization_source: electrospray_ionization - polarity_mode: positive - - id: nmdc:mscon-99-oW43DzG2 - name: EMSL lipidomics mass spectrometry method, negative polarity - description: Mass spectrometry method used by EMSL for lipidomics analysis, negative polarity - type: nmdc:MassSpectrometryConfiguration - mass_spectrometry_acquisition_strategy: data_dependent_acquisition - mass_spectrum_collection_modes: - - full_profile - - centroid - resolution_categories: - - high - - low - mass_analyzers: - - Orbitrap - - ion_trap - ionization_source: electrospray_ionization - polarity_mode: negative - - id: nmdc:chrcon-99-oW43DzG0 - name: EMSL LC method for non-polar metabolites - description: LC method for non-polar metabolites used by EMSL - type: nmdc:ChromatographyConfiguration - chromatographic_category: liquid_chromatography - stationary_phase: C18 - temperature: - type: nmdc:QuantityValue - has_numeric_value: 30 - has_unit: Cel - ordered_mobile_phases: - - type: nmdc:MobilePhaseSegment - duration: - type: nmdc:QuantityValue - has_unit: min - has_numeric_value: 60 - substances_used: - - known_as: glucose - type: nmdc:PortionOfSubstance - final_concentration: - type: nmdc:QuantityValue - has_unit: '%' - has_numeric_value: 10 - - type: nmdc:MobilePhaseSegment - substances_used: - - known_as: water - type: nmdc:PortionOfSubstance - final_concentration: - type: nmdc:QuantityValue - has_unit: mM - has_numeric_value: 15 + study_category: research_study + gold_study_identifiers: + - gold:Gs999999 + ecosystem: Environmental + ecosystem_category: Terrestrial + ecosystem_subtype: Wetlands + ecosystem_type: Soil + specific_ecosystem: Permafrost + principal_investigator: + type: nmdc:PersonValue + has_raw_value: Virginia Rich +workflow_execution_set: +- id: nmdc:wfmgas-11-d11daf11.1 + type: nmdc:MetagenomeAssembly + name: Metagenome assembly 1472_51277 + has_input: + - nmdc:dobj-12-d11daf13 + has_output: + - nmdc:dobj-12-d11daf14 + qc_status: fail + qc_comment: 15% human contamination and assembly size is below 5 MB + has_failure_categorization: + - type: nmdc:FailureCategorization + qc_failure_what: assembly_size_too_small + qc_failure_where: MetagenomeAssembly + - type: nmdc:FailureCategorization + qc_failure_what: other + qc_failure_where: MetagenomeAssembly + execution_resource: LANL-B-div + git_url: https://github.com/microbiomedata/metaAssembly/releases/tag/1.0.0 + started_at_time: '2020-03-24T00:00:00+00:00' + was_informed_by: nmdc:omprc-11-di893a + ended_at_time: '2020-03-25T00:00:00+00:00' +- id: nmdc:wfmb-99-ABCDEF.1 + type: nmdc:MetabolomicsAnalysis + name: Metabolomics Analysis Activity for nmdc:wfmb-99-ABCDEF.1 + has_input: + - nmdc:dobj-70-izwYW6 + - nmdc:dobj-80-izwYW6 + has_output: + - nmdc:dobj-90-izwYW61 + execution_resource: NERSC-Cori + git_url: https://example.org/WorkflowExecutionActivity + started_at_time: '2021-08-05T14:48:51+00:00' + was_informed_by: nmdc:dgms-11-sdi48a + ended_at_time: '2021-09-15T10:13:20+00:00' + metabolomics_analysis_category: gc_ms_metabolomics +- id: nmdc:wfmb-99-ABCDEF.2 + type: nmdc:MetabolomicsAnalysis + name: Metabolomics Analysis Activity for nmdc:wfmb-99-ABCDEF.1 + has_input: + - nmdc:dobj-99-xxxxxx1 + - nmdc:dobj-99-xxxxxx2 + has_output: + - nmdc:dobj-99-xxxxxx3 + - nmdc:dobj-99-xxxxxx4 + execution_resource: NERSC-Cori + git_url: https://example.org/WorkflowExecutionActivity + started_at_time: '2021-08-05T14:48:51+00:00' + was_informed_by: nmdc:dgms-11-djad84 + ended_at_time: '2021-09-15T10:13:20+00:00' + metabolomics_analysis_category: gc_ms_metabolomics +- id: nmdc:wfrqc-11-hemh0a87.1 + type: nmdc:ReadQcAnalysis + name: Read QC Activity for nmdc:wfrqc-11-hemh0a87.1 + has_input: + - nmdc:dobj-11-1k62bt83 + - nmdc:dobj-11-e8hs8y25 + qc_status: fail + qc_comment: Failure during call-stage to interleave fastq files + has_failure_categorization: + - type: nmdc:FailureCategorization + qc_failure_what: malformed_data + qc_failure_where: ReadQcAnalysis + execution_resource: NERSC-Perlmutter + git_url: https://github.com/microbiomedata/ReadsQC + started_at_time: '2023-08-29T19:41:47.365957+00:00' + was_informed_by: nmdc:dgns-11-dkd74a + ended_at_time: '2023-08-30T13:26:02.892410+00:00' + version: v1.0.8 +- id: nmdc:wfrqc-11-hemh0a88.1 + type: nmdc:ReadQcAnalysis + name: Read QC Activity for nmdc:wfrqc-11-hemh0a88.1 + has_input: + - nmdc:dobj-11-1k62bt83 + - nmdc:dobj-11-e8hs8y25 + has_output: + - nmdc:dobj-11-e8hs8y26 + - nmdc:dobj-11-e8hs8y27 + - nmdc:dobj-11-e8hs8y28 + qc_status: pass + qc_comment: Number of output reads from readqc is above threshold (6000000 > 1000000) + execution_resource: NERSC-Perlmutter + git_url: https://github.com/microbiomedata/ReadsQC + started_at_time: '2023-08-29T19:41:47.365957+00:00' + was_informed_by: nmdc:omprc-11-d9ra7y + ended_at_time: '2023-08-30T13:26:02.892410+00:00' + version: v1.0.8 +- id: nmdc:wfrqc-11-hemh0a90.1 + type: nmdc:ReadQcAnalysis + name: Read QC Activity for nmdc:wfrqc-11-hemh0a87.1 + has_input: + - nmdc:dobj-11-1k62bt83 + - nmdc:dobj-11-e8hs8y25 + has_output: + - nmdc:dobj-11-e8hs8y26 + - nmdc:dobj-11-e8hs8y27 + - nmdc:dobj-11-e8hs8y28 + qc_status: fail + qc_comment: Most data removed for artifacts + has_failure_categorization: + - type: nmdc:FailureCategorization + qc_failure_what: low_read_count + qc_failure_where: ReadQcAnalysis + execution_resource: NERSC-Perlmutter + git_url: https://github.com/microbiomedata/ReadsQC + started_at_time: '2023-08-29T19:41:47.365957+00:00' + was_informed_by: nmdc:dgns-11-dkf85s + ended_at_time: '2023-08-30T13:26:02.892410+00:00' + version: v1.0.8 +- id: nmdc:wfrqc-12-63da5n74.1 + type: nmdc:ReadQcAnalysis + name: 'TEST Read QC Activity for nmdc:wfrqc-12-63da5n74.1 ' + has_input: + - nmdc:dobj-12-jdhk9537 + - nmdc:dobj-12-yx0tfp52 + has_output: + - nmdc:dobj-12-71q7wv80 + - nmdc:dobj-12-y236qp68 + execution_resource: NERSC-Cori + git_url: https://github.com/microbiomedata/ReadsQC + started_at_time: '2023-03-23T17:17:05.111689+00:00' + was_informed_by: nmdc:dgns-11-2398d4 + ended_at_time: '2023-03-23T17:17:05.111725+00:00' + version: b1.0.7 +- id: nmdc:wfmb-11-q0czdv62.1 + type: nmdc:MetabolomicsAnalysis + name: Lipidomics analysis for Blanch_Nat_Lip_C_7_AB_M_07_POS_23Jan18_Brandi-WCSH5801.raw + description: Analysis of raw mass spectrometry data for the annotation of lipids. + has_input: + - nmdc:dobj-11-r3xkmv70 + - nmdc:dobj-11-kc4ff319 + has_output: + - nmdc:dobj-11-h5z5w905 + - nmdc:dobj-11-j6kfna43 + processing_institution: EMSL + execution_resource: EMSL-RZR + git_url: https://github.com/microbiomedata/metaMS/wdl/metaMS_lipidomics.wdl + started_at_time: '2024-12-19 09:25:09' + was_informed_by: nmdc:dgms-11-vfzh1754 + ended_at_time: '2024-12-19 03:09:58' + version: 1.0.0 + metabolomics_analysis_category: lc_ms_lipidomics +- id: nmdc:wfmag-11-bweaz670.1 + type: nmdc:MagsAnalysis + name: MAGs activiity 1781_86101 + has_input: + - nmdc:dobj-11-bweaz681 + - nmdc:dobj-11-bweaz682 + - nmdc:dobj-11-bweaz683 + has_output: + - nmdc:dobj-11-bweaz684 + - nmdc:dobj-11-bweaz685 + - nmdc:dobj-11-bweaz686 + - nmdc:dobj-11-bweaz683 + execution_resource: NERSC-Cori + git_url: https://img.jgi.doe.gov + started_at_time: '2021-01-10T00:00:00+00:00' + was_informed_by: nmdc:dgns-11-dkr84a + ended_at_time: '2021-01-10T00:00:00+00:00' + binned_contig_num: 489 + input_contig_num: 169782 + low_depth_contig_num: 0 + mags_list: + - bin_name: bins.1 + type: nmdc:MagBin + bin_quality: LQ + completeness: 11.42 + contamination: 0.21 + gene_count: 250 + num_16s: 0 + num_23s: 0 + num_5s: 1 + num_t_rna: 1 + number_of_contig: 52 + - bin_name: bins.2 + type: nmdc:MagBin + bin_quality: LQ + completeness: 51.25 + contamination: 10.34 + gene_count: 2548 + num_16s: 0 + num_23s: 0 + num_5s: 1 + num_t_rna: 26 + number_of_contig: 426 + - bin_name: bins.3 + type: nmdc:MagBin + bin_quality: LQ + completeness: 2.0 + contamination: 0.0 + gene_count: 294 + num_16s: 0 + num_23s: 0 + num_5s: 0 + num_t_rna: 1 + number_of_contig: 11 + too_short_contig_num: 159810 + unbinned_contig_num: 9483 + img_identifiers: + - img.taxon:3300062116 +- id: nmdc:wfmag-11-0abycm66.1 + type: nmdc:MagsAnalysis + name: MAGs activiity 1781_86089 + has_input: + - nmdc:dobj-11-0abycm50 + - nmdc:dobj-11-0abycm51 + - nmdc:dobj-11-0abycm52 + has_output: + - nmdc:dobj-11-0abycm53 + - nmdc:dobj-11-0abycm54 + - nmdc:dobj-11-0abycm55 + - nmdc:dobj-11-0abycm56 + execution_resource: NERSC-Cori + git_url: https://img.jgi.doe.gov + started_at_time: '2021-01-10T00:00:00+00:00' + was_informed_by: nmdc:omprc-11-adrj47 + ended_at_time: '2021-01-10T00:00:00+00:00' + binned_contig_num: 206 + input_contig_num: 78376 + low_depth_contig_num: 0 + mags_list: + - bin_name: bins.1 + type: nmdc:MagBin + bin_quality: LQ + completeness: 25.86 + contamination: 0.0 + gene_count: 401 + num_16s: 0 + num_23s: 0 + num_5s: 0 + num_t_rna: 4 + number_of_contig: 74 + - bin_name: bins.2 + type: nmdc:MagBin + bin_quality: LQ + completeness: 0.0 + contamination: 0.0 + gene_count: 383 + num_16s: 0 + num_23s: 0 + num_5s: 0 + num_t_rna: 5 + number_of_contig: 74 + - bin_name: bins.3 + type: nmdc:MagBin + bin_quality: LQ + completeness: 17.61 + contamination: 0.0 + gene_count: 313 + num_16s: 0 + num_23s: 0 + num_5s: 0 + num_t_rna: 7 + number_of_contig: 58 + too_short_contig_num: 75364 + unbinned_contig_num: 2806 +- id: nmdc:wfmb-13-r954ws43.1 + type: nmdc:MetabolomicsAnalysis + has_input: + - nmdc:dobj-13-f3b04f08 + has_output: + - nmdc:dobj-13-hrf1h918 + execution_resource: EMSL-RZR + git_url: https://github.com/microbiomedata/metaMS + started_at_time: '2021-01-07T23:54:40Z' + was_informed_by: nmdc:dgms-13-122e4240 + ended_at_time: '2021-01-07T23:54:40Z' + metabolomics_analysis_category: gc_ms_metabolomics + uses_calibration: nmdc:calib-14-93cjjw92 +- id: nmdc:wfmgas-99-B7Vogx.1 + type: nmdc:MetagenomeAssembly + name: Metagenome assembly for nmdc:omprc-12-x123fa + has_input: + - nmdc:dobj-11-547rwq84 + has_output: + - nmdc:dobj-11-547rwq85 + - nmdc:dobj-11-547rwq86 + - nmdc:dobj-11-547rwq87 + - nmdc:dobj-11-547rwq88 + - nmdc:dobj-11-547rwq89 + execution_resource: LANL-B-div + git_url: https://github.com/microbiomedata/metaAssembly/releases/tag/1.0.0 + started_at_time: '2020-03-24T00:00:00+00:00' + was_informed_by: nmdc:omprc-12-x123fa + ended_at_time: '2020-03-25T00:00:00+00:00' + asm_score: 3.29 + scaffolds: 429340.0 + scaf_logsum: 303893.0 + scaf_powsum: 32467.0 + scaf_max: 17245.0 + scaf_bp: 192123121.0 + scaf_n50: 132307.0 + scaf_n90: 357156.0 + scaf_l50: 433.0 + scaf_l90: 288.0 + scaf_n_gt50k: 0.0 + scaf_l_gt50k: 0.0 + scaf_pct_gt50k: 0.0 + contigs: 429340.0 + contig_bp: 192123121.0 + ctg_n50: 132307.0 + ctg_l50: 433.0 + ctg_n90: 357156.0 + ctg_l90: 288.0 + ctg_logsum: 303893.0 + ctg_powsum: 32467.0 + ctg_max: 17245.0 + gap_pct: 0.0 + gc_std: 0.09822 + gc_avg: 0.55402 + num_input_reads: 87803950.0 + num_aligned_reads: 63046103.0 +- id: nmdc:wfmgas-99-CvgXTq.2 + type: nmdc:MetagenomeAssembly + name: Metagenome assembly 1472_51278 + has_input: + - nmdc:dobj-11-548rwq96 + has_output: + - nmdc:dobj-11-548rwq96 + - nmdc:dobj-11-548rwq97 + - nmdc:dobj-11-548rwq98 + - nmdc:dobj-11-548rwq99 + - nmdc:dobj-11-548rwq93 + execution_resource: LANL-B-div + git_url: https://github.com/microbiomedata/metaAssembly/releases/tag/1.0.0 + started_at_time: '2020-03-25T00:00:00+00:00' + was_informed_by: nmdc:omprc-12-x123fa + ended_at_time: '2020-03-25T00:00:00+00:00' + asm_score: 3.196 + scaffolds: 747801.0 + scaf_logsum: 483596.0 + scaf_powsum: 51427.0 + scaf_max: 15780.0 + scaf_bp: 333164102.0 + scaf_n50: 235059.0 + scaf_n90: 623912.0 + scaf_l50: 432.0 + scaf_l90: 289.0 + scaf_n_gt50k: 0.0 + scaf_l_gt50k: 0.0 + scaf_pct_gt50k: 0.0 + contigs: 747801.0 + contig_bp: 333164102.0 + ctg_n50: 235059.0 + ctg_l50: 432.0 + ctg_n90: 623912.0 + ctg_l90: 289.0 + ctg_logsum: 483596.0 + ctg_powsum: 51427.0 + ctg_max: 15780.0 + gap_pct: 0.0 + gc_std: 0.09613 + gc_avg: 0.57087 + num_input_reads: 141175680.0 + num_aligned_reads: 95369019.0 +- id: nmdc:wfmgas-99-1vjxjy88.2 + type: nmdc:MetagenomeAssembly + name: Metagenome assembly 1472_51279 + has_input: + - nmdc:dobj-11-1vjxjy81 + has_output: + - nmdc:dobj-99-xxxxx1 + - nmdc:dobj-99-xxxxx2 + - nmdc:dobj-99-xxxxx3 + - nmdc:dobj-99-xxxxx4 + - nmdc:dobj-99-xxxxx5 + execution_resource: LANL-B-div + git_url: https://github.com/microbiomedata/metaAssembly/releases/tag/1.0.0 + started_at_time: '2020-03-25T00:00:00+00:00' + was_informed_by: nmdc:omprc-12-x123fa + ended_at_time: '2020-03-25T00:00:00+00:00' + asm_score: 3.527 + scaffolds: 607951.0 + scaf_logsum: 475574.0 + scaf_powsum: 50819.0 + scaf_max: 26906.0 + scaf_bp: 279001661.0 + scaf_n50: 183452.0 + scaf_n90: 505179.0 + scaf_l50: 449.0 + scaf_l90: 290.0 + scaf_n_gt50k: 0.0 + scaf_l_gt50k: 0.0 + scaf_pct_gt50k: 0.0 + contigs: 607951.0 + contig_bp: 279001661.0 + ctg_n50: 183452.0 + ctg_l50: 449.0 + ctg_n90: 505179.0 + ctg_l90: 290.0 + ctg_logsum: 475574.0 + ctg_powsum: 50819.0 + ctg_max: 26906.0 + gap_pct: 0.0 + gc_std: 0.09898 + gc_avg: 0.55832 + num_input_reads: 116129794.0 + num_aligned_reads: 79146088.0 +- id: nmdc:wfrqc-11-23984.1 + type: nmdc:ReadQcAnalysis + has_input: + - nmdc:dobj-11-547rwq96 + has_output: + - nmdc:dobj-11-547rwq97 + - nmdc:dobj-11-547rwq98 + execution_resource: LANL-B-div + git_url: https://github.com/microbiomedata/metaT_ReadsQC + started_at_time: '2023-08-05T14:48:51+00:00' + was_informed_by: nmdc:omprc-11-547rwq95 + ended_at_time: '2021-08-05T14:48:51+00:00' + version: v0.0.1 +- id: nmdc:wfmtas-11-23986.1 + type: nmdc:MetatranscriptomeAssembly + has_input: + - nmdc:dobj-11-547rwq97 + has_output: + - nmdc:dobj-11-547rwq72 + - nmdc:dobj-11-547rwq73 + execution_resource: LANL-B-div + git_url: https://github.com/microbiomedata/metaT_Assembly/releases + started_at_time: '2024-07-06T14:48:51+00:00' + was_informed_by: nmdc:omprc-11-547rwq95 + ended_at_time: '2024-07-06T14:48:51+00:00' + version: v0.0.1 +- id: nmdc:wfmtan-11-23987.1 + type: nmdc:MetatranscriptomeAnnotation + has_input: + - nmdc:dobj-11-547rwq72 + has_output: + - nmdc:dobj-11-547rwq75 + - nmdc:dobj-11-547rwq77 + execution_resource: LANL-B-div + git_url: https://github.com/microbiomedata/mg_annotation + started_at_time: '2024-07-07T14:48:51+00:00' + was_informed_by: nmdc:omprc-11-547rwq95 + ended_at_time: '2024-07-07T14:48:51+00:00' + version: v1.1.1 +- id: nmdc:wfmtex-11-23989.1 + type: nmdc:MetatranscriptomeExpressionAnalysis + has_input: + - nmdc:dobj-11-547rwq75 + - nmdc:dobj-11-547rwq77 + - nmdc:dobj-11-547rwq73 + has_output: + - nmdc:dobj-11-547rwq82 + - nmdc:dobj-11-547rwq83 + - nmdc:dobj-11-547rwq84 + execution_resource: LANL-B-div + git_url: https://github.com/microbiomedata/metaT_ReadCounts + started_at_time: '2024-07-08T14:48:51+00:00' + was_informed_by: nmdc:omprc-11-547rwq95 + ended_at_time: '2024-07-08T14:48:51+00:00' + version: v0.0.1 +- id: nmdc:wfrqc-12-63da5n74.2 + type: nmdc:ReadQcAnalysis + name: 'TEST Read QC Activity for nmdc:wfrqc-12-63da5n74.1 ' + has_input: + - nmdc:dobj-12-jdhk9537 + - nmdc:dobj-12-yx0tfp52 + has_output: + - nmdc:dobj-12-71q7wv80 + - nmdc:dobj-12-y236qp68 + execution_resource: NERSC-Cori + git_url: https://github.com/microbiomedata/ReadsQC + started_at_time: '2023-03-23T17:17:05.111689+00:00' + was_informed_by: nmdc:dgns-11-s9xj2r24 + ended_at_time: '2023-03-23T17:17:05.111725+00:00' + version: b1.0.7 +- id: nmdc:wfnom-11-547rwq94.1 + type: nmdc:NomAnalysis + alternative_identifiers: + - nmdc:wfnom-11-547rwq94 + has_input: + - nmdc:dobj-11-647rwq94 + - nmdc:dobj-11-647rwq96 + has_output: + - nmdc:dobj-11-647rwq97 + - nmdc:dobj-11-647rwq98 + execution_resource: LANL-B-div + git_url: xxx + started_at_time: '2018-11-13T20:20:39+00:00' + was_informed_by: nmdc:dgms-11-sd2d94 + ended_at_time: '2018-11-13T20:20:39+00:00' +- id: nmdc:wfnom-11-547rwq94.2 + type: nmdc:NomAnalysis + has_input: + - nmdc:dobj-11-647rwq94 + - nmdc:dobj-11-647rwq96 + has_output: + - nmdc:dobj-11-647rwq97 + - nmdc:dobj-11-647rwq98 + execution_resource: EMSL-RZR + git_url: xxx + started_at_time: '2018-11-13T20:20:39+00:00' + was_informed_by: nmdc:dgms-11-djr98s + ended_at_time: '2018-11-13T20:20:39+00:00' +- id: nmdc:wfnom-11-zs6pnn44.1 + type: nmdc:NomAnalysis + alternative_identifiers: + - nmdc:wfnom-11-zs6pnn44 + has_input: + - nmdc:dobj-11-cp4p5602 + has_output: + - nmdc:dobj-11-wkvtnj47 + execution_resource: EMSL-RZR + git_url: https://github.com/microbiomedata/enviroMS + started_at_time: '2024-03-10 23:25:16' + was_informed_by: nmdc:omprc-11-0003fm52 + ended_at_time: '2024-03-10 23:25:16' + uses_calibration: nmdc:calib-14-hhn3qb47 +- id: nmdc:wfmsa-11-547rwq94.1 + type: nmdc:MetagenomeSequencing + name: Sequencing Activity for my awesome project + has_input: + - nmdc:bsm-11-547rwq94 + has_output: + - nmdc:dobj-11-547rwq74 + execution_resource: JGI + git_url: https://github.com/microbiomedata/RawSequencingData + started_at_time: '2021-08-05T14:48:51+00:00' + was_informed_by: nmdc:dgns-11-448dfa + ended_at_time: '2021-09-15T10:13:20+00:00' + version: v1.0.0 diff --git a/src/scripts/interleave_yaml.py b/src/scripts/interleave_yaml.py index 0f948e619b..b3161f95b6 100644 --- a/src/scripts/interleave_yaml.py +++ b/src/scripts/interleave_yaml.py @@ -3,7 +3,6 @@ import os import glob import yaml - from linkml_runtime import SchemaView from linkml_runtime.dumpers import yaml_dumper from linkml_runtime.loaders import yaml_loader @@ -11,6 +10,48 @@ from collections import defaultdict +def increment_id(original_id, slot_id_tracker): + """ + Increment an ID by one digit or letter to make it unique. + + Args: + original_id: The original ID that needs to be incremented + slot_id_tracker: Set of existing IDs to avoid collisions + + Returns: + A new unique ID + """ + # Try incrementing the last character + if original_id and len(original_id) > 0: + last_char = original_id[-1] + base_id = original_id[:-1] + + # If last character is a digit, increment it + if last_char.isdigit(): + new_digit = str(int(last_char) + 1) + new_id = base_id + new_digit + # If last character is a letter, increment it + elif last_char.isalpha(): + if last_char.lower() == 'z': + # If 'z' or 'Z', append 'a' or 'A' + new_id = original_id + ('a' if last_char.islower() else 'A') + else: + new_char = chr(ord(last_char) + 1) + new_id = base_id + new_char + else: + # If last character is neither digit nor letter, append '1' + new_id = original_id + '1' + + # Check if the new ID is still unique, if not, recursively increment + if new_id in slot_id_tracker: + return increment_id(new_id, slot_id_tracker) + else: + return new_id + else: + # If original_id is empty, return a default + return original_id + '1' + + @click.command() @click.option('--directory-path', default='src/data/valid', help='Path to the directory containing YAML files.') @click.option('--output-file', default='interleaved.yaml', help='Output file to save the interleaved YAML.') @@ -24,7 +65,8 @@ def process_yaml(directory_path, output_file, schema_file): file_paths = glob.glob(os.path.join(directory_path, 'Database-*.yaml')) file_paths.sort() output_file_path = os.path.abspath(output_file) # Ensure the path is absolute - file_paths = [file for file in file_paths if file != output_file_path] + interleaved_file_path = os.path.join(directory_path, 'Database-interleaved.yaml') + file_paths = [file for file in file_paths if os.path.abspath(file) != output_file_path and os.path.abspath(file) != interleaved_file_path] if os.path.exists(output_file_path): click.echo(f"Output file {output_file_path} already exists. Please remove it or specify a different file.") @@ -36,6 +78,11 @@ def process_yaml(directory_path, output_file, schema_file): database_slot_names = [slot.name for slot in database_slots] database_slot_names.sort() + # Track duplicate IDs for reporting and resolution + duplicate_ids = defaultdict(list) + slot_id_tracker = defaultdict(set) + id_modifications = defaultdict(list) + # pprint.pprint(database_slot_names) # print(schema_view.schema.name) @@ -52,12 +99,47 @@ def process_yaml(directory_path, output_file, schema_file): if payload: if slot not in collector.__dict__: collector.__dict__[slot] = [] + + # Check for duplicate IDs within this slot and resolve them + for item in payload: + if hasattr(item, 'id') and item.id: + original_id = item.id + if original_id in slot_id_tracker[slot]: + # Record the original duplicate + duplicate_ids[slot].append(original_id) + # Generate a new unique ID + new_id = increment_id(original_id, slot_id_tracker[slot]) + # Update the item's ID + item.id = new_id + # Track the modification + id_modifications[slot].append(f"{original_id} -> {new_id}") + # Add the new ID to the tracker + slot_id_tracker[slot].add(new_id) + else: + slot_id_tracker[slot].add(original_id) + collector.__dict__[slot].extend(payload) + # Report duplicate IDs found and resolved + if duplicate_ids: + click.echo("\n⚠️ Duplicate IDs found and resolved:") + for slot, ids in duplicate_ids.items(): + click.echo(f" {slot}: {sorted(set(ids))}") + + click.echo("\n🔧 ID modifications made:") + for slot, modifications in id_modifications.items(): + click.echo(f" {slot}:") + for modification in modifications: + click.echo(f" {modification}") + else: + click.echo("\n✅ No duplicate IDs found") + # Dump the interleaved content into YAML format interleaved_content = yaml_dumper.dumps(collector) # print(interleaved_content) yaml_dumper.dump(collector, output_file_path) + + click.echo(f"\nInterleaved YAML saved to: {output_file_path}") if __name__ == '__main__':