Added optional Bwa index parameter to skip bwamem2 index for a faster output

CHANGELOG.md

@@ -23,6 +23,8 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#96](https://github.com/nf-core/seqinspector/pull/96) Added missing citations to citation tool
 - [#103](https://github.com/nf-core/seqinspector/pull/103) Configure full-tests
 - [#110](https://github.com/nf-core/seqinspector/pull/110) Update input schema to accept either tar file or directory as rundir, and fastq messages and patterns.
+- [#127] (https://github.com/nf-core/seqinspector/pull/127) Added alignment tools - bwamem2 - index and mem
+- [#128] (https://github.com/nf-core/seqinspector/pull/128) Added Picard tools - Collect Multiple Mterics to collect QC metrics
 
 ### `Fixed`
 

CITATIONS.md

@@ -28,6 +28,16 @@
 
 - [Seqtk](https://github.com/lh3/seqtk)
 
+- [BWAMEM2](https://ieeexplore.ieee.org/abstract/document/8820962)
+
+> Vasimuddin Md, Misra S, Li H, Aluru S. Efficient Architecture-Aware Acceleration of BWA-MEM for Multicore Systems. In: 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE; 2019:314-324. doi:10.1109/IPDPS.2019.00041
+
+- [SAMTOOLS](https://academic.oup.com/bioinformatics/article/25/16/2078/204688)
+
+> Danecek P, Bonfield JK, Liddle J, et al. Twelve years of SAMtools and BCFtools. GigaScience. 2021;10(2):giab008. doi:10.1093/gigascience/giab008
+
+- [Picard Tools](https://broadinstitute.github.io/picard/)
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)

README.md

@@ -33,7 +33,11 @@
 
 1. Subsample reads ([`Seqtk`](https://github.com/lh3/seqtk))
 2. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
-3. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
+3. Align reads to reference with ([`Bwamem2`](https://github.com/bwa-mem2/bwa-mem2))
+4. Index aligned BAM files ([`SAMtools`](http://github.com/samtools))
+5. Create FASTA index ([`SAMtools`](http://github.com/samtools))
+6. Collect multiple QC metrics ([`Picard CollectMultipleMetrics`](https://broadinstitute.github.io/picard/picard-metric-definitions.html))
+7. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
 
 ## Usage
 

conf/modules.config

@@ -18,11 +18,11 @@ process {
         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
     ]
 
-    withName: SEQTK_SAMPLE {
+    withName: 'SEQTK_SAMPLE' {
         ext.args = '-s100'
     }
 
-    withName: FASTQC {
+    withName: 'FASTQC' {
         ext.args = '--quiet'
     }
 
@@ -36,21 +36,21 @@ process {
     }
 
     withName: 'BWAMEM2_INDEX' {
-        ext.args   = ''
         publishDir = [
             path: { "${params.outdir}/bwamem2_index" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
+
     withName: 'BWAMEM2_MEM' {
-        ext.args   =  ''
         publishDir = [
             path: { "${params.outdir}/bwamem2_mem" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
+
     withName: 'PICARD_COLLECTMULTIPLEMETRICS' {
         ext.args   =  ''
         publishDir = [

conf/seqinspector_v1.0_stage_resources.config

@@ -0,0 +1,72 @@
+process {
+
+
+    // TODO nf-core: Check the defaults for all processes
+    cpus   = { 1      * task.attempt }
+    memory = { 6.GB   * task.attempt }
+    time   = { 4.h    * task.attempt }
+
+    errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' }
+    maxRetries    = 2
+    maxErrors     = '-1'
+
+
+    // Subsampling reads
+    withName: 'SEQTK_SAMPLE' {
+        cpus = 6
+        memory = { 4.GB * task.attempt }
+        time = { 4.h * task.attempt }
+    }
+
+    // Quality control
+    withName: 'FASTQC' {
+        cpus = 2
+        memory = { 36.GB * task.attempt }
+        time = { 8.h * task.attempt }
+    }
+    withName: 'SEQFU_STATS' {
+        cpus = 6
+        memory = { 4.GB * task.attempt }
+        time = { 4.h * task.attempt }
+    }
+    withName: 'FASTQSCREEN_FASTQSCREEN' {
+        cpus = 6
+        memory = { 36.GB * task.attempt }
+        time = { 8.h * task.attempt }
+    }
+
+    // Reference genome processing
+    withName: 'BWAMEM2_INDEX' {
+        cpus = 12
+        memory = { 72.GB * task.attempt }
+        time = { 16.h * task.attempt }
+    }
+    withName: 'BWAMEM2_MEM' {
+        cpus = 6
+        memory = { 35.GB * task.attempt }
+        time = { 16.h * task.attempt }
+    }
+    withName: 'SAMTOOLS_INDEX' {
+        cpus = 6
+        memory = { 4.GB * task.attempt }
+        time = { 4.h * task.attempt }
+    }
+    withName: 'SAMTOOLS_FAIDX' {
+        cpus = 6
+        memory = { 6.GB * task.attempt }
+        time = { 4.h * task.attempt }
+    }
+    // Picard metrics
+    withName: 'PICARD_COLLECTMULTIPLEMETRICS' {
+        cpus = 4
+        memory = { 8.GB * task.attempt }
+        time = { 4.h * task.attempt }
+    }
+
+    // MultiQC aggregation
+    withName: 'MULTIQC_GLOBAL|MULTIQC_PER_TAG' {
+        cpus = 4
+        memory = { 4.GB * task.attempt }
+        time = { 4.h * task.attempt }
+    }
+}

conf/test.config

@@ -10,6 +10,14 @@
 ----------------------------------------------------------------------------------------
 */
 
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
+
 params {
     config_profile_name        = 'Test profile'
     config_profile_description = 'Minimal test dataset to check pipeline function'
@@ -23,5 +31,3 @@ params {
     // Genome references
     genome = 'R64-1-1'
 }
-
-

main.nf

@@ -7,29 +7,24 @@
     Website: https://nf-co.re/seqinspector
     Slack  : https://nfcore.slack.com/channels/seqinspector
 ----------------------------------------------------------------------------------------
-*/
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    IMPORT FUNCTIONS / MODULES / SUBWORKFLOWS / WORKFLOWS
+    GENOME PARAMETER VALUES
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 
-include { SEQINSPECTOR            } from './workflows/seqinspector'
-include { PIPELINE_INITIALISATION } from './subworkflows/local/utils_nfcore_seqinspector_pipeline'
-include { getGenomeAttribute      } from './subworkflows/local/utils_nfcore_seqinspector_pipeline'
-include { PIPELINE_COMPLETION     } from './subworkflows/local/utils_nfcore_seqinspector_pipeline'
+params.fasta = getGenomeAttribute('fasta')
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    GENOME PARAMETER VALUES
+    IMPORT FUNCTIONS / MODULES / SUBWORKFLOWS / WORKFLOWS
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 
-// TODO nf-core: Remove this line if you don't need a FASTA file
-//   This is an example of how to use getGenomeAttribute() to fetch parameters
-//   from igenomes.config using `--genome`
-// params.fasta = getGenomeAttribute('fasta')
+include { SEQINSPECTOR            } from './workflows/seqinspector'
+include { PIPELINE_INITIALISATION } from './subworkflows/local/utils_nfcore_seqinspector_pipeline'
+include { PIPELINE_COMPLETION     } from './subworkflows/local/utils_nfcore_seqinspector_pipeline'
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -41,7 +36,6 @@ include { PIPELINE_COMPLETION     } from './subworkflows/local/utils_nfcore_seqi
 // WORKFLOW: Run main analysis pipeline depending on type of input
 //
 workflow NFCORE_SEQINSPECTOR {
-
     take:
     samplesheet // channel: samplesheet read in from --input
 
@@ -51,13 +45,14 @@ workflow NFCORE_SEQINSPECTOR {
     // WORKFLOW: Run pipeline
     //
 
-    SEQINSPECTOR (
-        samplesheet
+    SEQINSPECTOR(
+        samplesheet,
+        params.fasta,
     )
-    emit:
-    global_report   = SEQINSPECTOR.out.global_report    // channel: /path/to/multiqc_report.html
-    grouped_reports = SEQINSPECTOR.out.grouped_reports  // channel: /path/to/multiqc_report.html
 
+    emit:
+    global_report   = SEQINSPECTOR.out.global_report // channel: /path/to/multiqc_report.html
+    grouped_reports = SEQINSPECTOR.out.grouped_reports // channel: /path/to/multiqc_report.html
 }
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -67,32 +62,30 @@ workflow NFCORE_SEQINSPECTOR {
 
 workflow {
 
-    main:
-
 
     //
     // SUBWORKFLOW: Run initialisation tasks
     //
 
-    PIPELINE_INITIALISATION (
+    PIPELINE_INITIALISATION(
         params.version,
         params.validate_params,
         params.monochrome_logs,
         args,
         params.outdir,
-        params.input
+        params.input,
     )
 
     //
     // WORKFLOW: Run main workflow
     //
-    NFCORE_SEQINSPECTOR (
-        PIPELINE_INITIALISATION.out.samplesheet,
+    NFCORE_SEQINSPECTOR(
+        PIPELINE_INITIALISATION.out.samplesheet
     )
     //
     // SUBWORKFLOW: Run completion tasks
     //
-    PIPELINE_COMPLETION (
+    PIPELINE_COMPLETION(
         params.email,
         params.email_on_fail,
         params.plaintext_email,
@@ -105,6 +98,19 @@ workflow {
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    THE END
+    FUNCTIONS
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
+
+//
+// Get attribute from genome config file e.g. fasta
+//
+
+def getGenomeAttribute(attribute) {
+    if (params.genomes && params.genome && params.genomes.containsKey(params.genome)) {
+        if (params.genomes[params.genome].containsKey(attribute)) {
+            return params.genomes[params.genome][attribute]
+        }
+    }
+    return null
+}

modules.json

@@ -42,21 +42,6 @@
                         "git_sha": "7b50cb7be890e4b28cffb82e438cc6a8d7805d3f",
                         "installed_by": ["modules"]
                     },
-                    "picard/collectmultiplemetrics": {
-                        "branch": "master",
-                        "git_sha": "df124e87c74d8b40285199f8cc20151f5aa57255",
-                        "installed_by": ["modules"]
-                    },
-                    "samtools/faidx": {
-                        "branch": "master",
-                        "git_sha": "c8be52dba1166c678e74cda9c3a3c221635c8bb1",
-                        "installed_by": ["modules"]
-                    },
-                    "samtools/index": {
-                        "branch": "master",
-                        "git_sha": "c8be52dba1166c678e74cda9c3a3c221635c8bb1",
-                        "installed_by": ["modules"]
-                    },
                     "seqfu/stats": {
                         "branch": "master",
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",

nextflow.config

@@ -16,10 +16,10 @@ params {
     skip_tools                 = ''
     // References
     genome                     = null
-    fasta                      = null
     igenomes_base              = 's3://ngi-igenomes/igenomes/'
     igenomes_ignore            = false
     sort_bam                   = true
+    bwa_index                  = null
 
     // Fastqscreen options
     fastq_screen_references    = "${projectDir}/assets/example_fastq_screen_references.csv"

nextflow_schema.json

@@ -51,7 +51,7 @@
                 "skip_tools": {
                     "type": "string",
                     "description": "Comma-separated string of tools to skip",
-                    "pattern": "^((fastqc|fastqscreen|seqfu_stats|seqtk_sample|bwamem2_index|bwamem2_mem|picard_collectmultiplemetrics|samtools_faidx|samtools_index)?,?)*(?<!,)$"
+                    "pattern": "^((fastqc|fastqscreen|seqfu_stats|seqtk_sample|bwamem2_index|bwamem2_mem)?,?)*(?<!,)$"
                 }
             }
         },
@@ -94,7 +94,7 @@
                 },
                 "fastq_screen_references": {
                     "type": "string",
-                    "default": "${projectDir}/assets/example_fastq_screen_references.csv",
+                    "default": "/Users/agrimabhatt/seqinspector/assets/example_fastq_screen_references.csv",
                     "fa_icon": "fas fa-search",
                     "description": "A .csv of reference genomes to be mapped against by FastQ Screen"
                 }
@@ -214,7 +214,8 @@
                 "modules_testdata_base_path": {
                     "type": "string",
                     "description": "Base path / URL for data used in the modules",
-                    "hidden": true
+                    "hidden": true,
+                    "default": "s3://ngi-igenomes/testdata/nf-core/modules/"
                 },
                 "multiqc_config": {
                     "type": "string",
@@ -270,5 +271,10 @@
         {
             "$ref": "#/$defs/generic_options"
         }
-    ]
+    ],
+    "properties": {
+        "bwa_index": {
+            "type": "string"
+        }
+    }
 }