Update build system to pyproject.toml and hatchling

Author: kieranr51

bin/overlap_ss.sh

@@ -200,18 +200,6 @@ Flags:
   -V, --version         Print version number then exit.
 ```
 
-## Same Strand Overlap
-
-If you wish to detect same strand overlaps, you can use the `overlap_ss` script that is installed in the same environment as this pipeline. This uses a number of bash programs to create files that show where two sets of small RNA that appear on the same strand overlap.
-
-To use this script you need two sets of small RNA as FASTA or FASTQ files, one for the base and one for the overlap, plus the genome of the species of interest. You can then run the script in the following way:
-
-```
-$ overlap_ss genome.fasta smallRNA1.fastq smallRNA2.fastq
-```
-
-This script will then create output in the output directory specified in `config.toml` under the directory `samestrand_overlap/`.
-
 ## miRNA
 
 TODO

docs/other-tasks.md

@@ -12,14 +12,10 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 from .__main__ import main
-from .ss_overlap import main_ssoverlap
 from .label_for_unitas import label_for_unitas_cli
 
 def climain():
     main()
 
-def ssoverlap_main():
-    main_ssoverlap()
-
 def labelforunitas_main():
     label_for_unitas_cli()

hlsmallrna/__init__.py

@@ -280,7 +280,7 @@ def process_fa_out(path_to_fa_out, output, feature, scaffold_index=None):
         writer.writerow(['Chrom', 'Name', 'Start', 'End'])
         writer.writerows(antisense_targets)
 
-if __name__ == '__main__':
+def main():
     parser = ArgumentParser(description='Convert common bioinformatics file formats into coordinate file to plot')
 
     parser.add_argument('-a', '--fasta', action='store_true', help='Treat input as a FASTA file')

bin/build_coord_files hlsmallrna/bin/build_coord_files.pybin/build_coord_files renamed to hlsmallrna/bin/build_coord_files.py

@@ -166,7 +166,7 @@ def extract_noncoding(genome, gff_path, output='result.fasta'):
 
     SeqIO.write(extract_fragments(genome_data, coordinates, mRNA_start, mRNA_end), output, 'fasta')
 
-if __name__ == '__main__':
+def main():
     parser = ArgumentParser('')
 
     parser.add_argument('genome', help='FASTA containing the genome to extract from')

bin/extract_nc hlsmallrna/bin/extract_nc.pybin/extract_nc renamed to hlsmallrna/bin/extract_nc.py

@@ -17,24 +17,25 @@
 
 from Bio import SeqIO
 
-parser = ArgumentParser(description='Simple script to reverse complement a FASTA file')
-
-parser.add_argument('-i', '--input', help='FASTA file to reverse complement')
-parser.add_argument('-o', '--output', help='FASTA file to write to')
-
-args = parser.parse_args()
-
-if args.input is None or args.output is None:
-    raise Exception('Both -i and -o need to be set to run this')
-
 def reverse_complement(seq):
     revcomp = seq.reverse_complement()
     revcomp.id = seq.id
     revcomp.description = seq.description
 
     return revcomp
 
-seqs = SeqIO.parse(args.input, 'fasta')
-seqs = map(reverse_complement, seqs)
+def main():
+    parser = ArgumentParser(description='Simple script to reverse complement a FASTA file')
+
+    parser.add_argument('-i', '--input', help='FASTA file to reverse complement')
+    parser.add_argument('-o', '--output', help='FASTA file to write to')
+
+    args = parser.parse_args()
+
+    if args.input is None or args.output is None:
+        raise Exception('Both -i and -o need to be set to run this')
+        
+    seqs = SeqIO.parse(args.input, 'fasta')
+    seqs = map(reverse_complement, seqs)
 
-SeqIO.write(seqs, args.output, 'fasta')
+    SeqIO.write(seqs, args.output, 'fasta')