clean up grammar file for clarity

allele_auto_fix.py

@@ -209,9 +209,9 @@ class Formatter(argparse.ArgumentDefaultsHelpFormatter, argparse.RawDescriptionH
         pass
 
     parser = argparse.ArgumentParser(description=__doc__, formatter_class=Formatter)
-    parser.add_argument('--genome', default='data/genome.pickle', help='genome dictionary built from contig files.')
-    parser.add_argument('--coordinate_changes_dict', default='data/coordinate_changes_dict.json')
-    parser.add_argument('--allele_results', default='results/allele_results.tsv')
+    parser.add_argument('--genome', default='data/genome.pickle', help='input: genome dictionary built from contig files (see load_genome.py).')
+    parser.add_argument('--coordinate_changes_dict', default='data/coordinate_changes_dict.json', help='input: protein modification dictionary (see build_alignment_dict_from_genome.py -PomBase- or build_alignment_dict_from_peptides.py -SGD- )')
+    parser.add_argument('--allele_results', default='results/allele_results.tsv', help='input: file output by allele_qc.py')
     parser.add_argument('--output_dir', default='results/', help='output directory, will create files allele_auto_fix.tsv, allele_cannot_fix_sequence_errors.tsv, allele_cannot_fix_other_errors.tsv')
 
     args = parser.parse_args()

allele_qc.py

@@ -7,6 +7,8 @@
 
 Only the subset of alleles that needs fixing, only the columns 'allele_description' and 'change_description_to'.
 results/allele_results_errors_summarised.tsv
+
+The extra columns created are described in the readme.md.
 """
 
 from models import SyntaxRule, AllowedTypes

allele_transvar.py

@@ -1,3 +1,10 @@
+"""
+Uses transvar to represent the allele modifications in standard variant nomenclature.
+
+Removes all lines with sequence errors (needs_fixing == True).
+
+"""
+
 import pandas
 import pickle
 import argparse
@@ -117,12 +124,12 @@ class Formatter(argparse.ArgumentDefaultsHelpFormatter, argparse.RawDescriptionH
         pass
 
     parser = argparse.ArgumentParser(description=__doc__, formatter_class=Formatter)
-    parser.add_argument('--genome', default='data/genome.pickle', help='genome dictionary built from contig files.')
-    parser.add_argument('--allele_results', default='results/allele_results.tsv')
-    parser.add_argument('--exclude_transcripts', default='data/frame_shifted_transcripts.tsv')
-    parser.add_argument('--genome_fasta', default='data/pombe_genome.fa')
-    parser.add_argument('--transvardb', default='data/pombe_genome.gtf.transvardb')
-    parser.add_argument('--output', default='results/allele_results_transvar.tsv')
+    parser.add_argument('--genome', default='data/genome.pickle', help='input: genome dictionary built from contig files. (see load_genome.py)')
+    parser.add_argument('--allele_results', default='results/allele_results.tsv', help='input: output of allele_qc.py')
+    parser.add_argument('--exclude_transcripts', default='data/frame_shifted_transcripts.tsv', help='input: transcripts to exclude from transvar because they are known to be problematic')
+    parser.add_argument('--genome_fasta', default='data/pombe_genome.fa', help='input: genome fasta file used by transvar')
+    parser.add_argument('--transvardb', default='data/pombe_genome.gtf.transvardb', help='input: path of transvardb file')
+    parser.add_argument('--output', default='results/allele_results_transvar.tsv', help='output: file with extra column with transvar coordinates')
 
     parser.add_argument('--sgd_mode', type=bool, default=False, help='Skip transcripts that don\'t work and fix allele types, this arg should be removed in the future.')
 

docker_start.sh

@@ -1,7 +1,7 @@
 set -e
 # No longer needed, since data folder is committed to git
 # bash get_data.sh
-# python build_alignment_dict.py
+# python build_alignment_dict_from_genome.py
 . transvar_env_vars.sh
 bash set_up_transvar.sh
 uvicorn api:app --host 0.0.0.0 --port 80

get_data.sh

@@ -84,6 +84,9 @@ gzip -fd data/pombase-chado.modifications.gz
 curl -kL http://purl.obolibrary.org/obo/mod.obo -o data/mod.obo
 python make_mod_dict.py
 
-# Download the pombase genome fasta (for transvar)
+# Download the pombase genome fasta and gtf files (for transvar)
 curl -k https://curation.pombase.org/dumps/latest_build/fasta/chromosomes/Schizosaccharomyces_pombe_all_chromosomes.fa.gz -o data/pombe_genome.fa.gz
 gzip -fd data/pombe_genome.fa.gz
+
+# TODO
+# curl -k path/to/gtf_file/in/nightly/release -o data/pombe_genome.gtf