Skip to content

Commit

Permalink
refactor var names in list comprehensions
Browse files Browse the repository at this point in the history
  • Loading branch information
@oschwengers
oschwengers committed Oct 15, 2024
1 parent befe6ee commit fe9eece
Show file tree
Hide file tree
Showing 4 changed files with 45 additions and 45 deletions.
44 changes: 22 additions & 22 deletions bakta/main.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -516,21 +516,21 @@ def main():
print(f"\tN ratio: {100 * data['stats']['n_ratio']:.1f} %")
print(f"\tcoding density: {100 * data['stats']['coding_ratio']:.1f} %")
print('\nannotation summary:')
print(f"\ttRNAs: {len([f for f in features if f['type'] == bc.FEATURE_T_RNA])}")
print(f"\ttmRNAs: {len([f for f in features if f['type'] == bc.FEATURE_TM_RNA])}")
print(f"\trRNAs: {len([f for f in features if f['type'] == bc.FEATURE_R_RNA])}")
print(f"\tncRNAs: {len([f for f in features if f['type'] == bc.FEATURE_NC_RNA])}")
print(f"\tncRNA regions: {len([f for f in features if f['type'] == bc.FEATURE_NC_RNA_REGION])}")
print(f"\tCRISPR arrays: {len([f for f in features if f['type'] == bc.FEATURE_CRISPR])}")
cdss = [f for f in features if f['type'] == bc.FEATURE_CDS]
print(f"\ttRNAs: {len([feat for feat in features if feat['type'] == bc.FEATURE_T_RNA])}")
print(f"\ttmRNAs: {len([feat for feat in features if feat['type'] == bc.FEATURE_TM_RNA])}")
print(f"\trRNAs: {len([feat for feat in features if feat['type'] == bc.FEATURE_R_RNA])}")
print(f"\tncRNAs: {len([feat for feat in features if feat['type'] == bc.FEATURE_NC_RNA])}")
print(f"\tncRNA regions: {len([feat for feat in features if feat['type'] == bc.FEATURE_NC_RNA_REGION])}")
print(f"\tCRISPR arrays: {len([feat for feat in features if feat['type'] == bc.FEATURE_CRISPR])}")
cdss = [feat for feat in features if feat['type'] == bc.FEATURE_CDS]
print(f"\tCDSs: {len(cdss)}")
print(f"\t\thypotheticals: {len([cds for cds in cdss if 'hypothetical' in cds])}")
print(f"\t\tpseudogenes: {len([cds for cds in cdss if 'pseudogene' in cds])}")
print(f"\t\tsignal peptides: {len([cds for cds in cdss if bc.FEATURE_SIGNAL_PEPTIDE in cds])}")
print(f"\tsORFs: {len([f for f in features if f['type'] == bc.FEATURE_SORF])}")
print(f"\tgaps: {len([f for f in features if f['type'] == bc.FEATURE_GAP])}")
print(f"\toriCs/oriVs: {len([f for f in features if (f['type'] == bc.FEATURE_ORIC or f['type'] == bc.FEATURE_ORIV)])}")
print(f"\toriTs: {len([f for f in features if f['type'] == bc.FEATURE_ORIT])}")
print(f"\tsORFs: {len([feat for feat in features if feat['type'] == bc.FEATURE_SORF])}")
print(f"\tgaps: {len([feat for feat in features if feat['type'] == bc.FEATURE_GAP])}")
print(f"\toriCs/oriVs: {len([feat for feat in features if (feat['type'] == bc.FEATURE_ORIC or feat['type'] == bc.FEATURE_ORIV)])}")
print(f"\toriTs: {len([feat for feat in features if feat['type'] == bc.FEATURE_ORIT])}")

############################################################################
# Write output files
Expand Down Expand Up @@ -609,21 +609,21 @@ def main():
fh_out.write(f"N ratio: {100 * data['stats']['n_ratio']:.1f}\n")
fh_out.write(f"coding density: {100 * data['stats']['coding_ratio']:.1f}\n")
fh_out.write('\nAnnotation:\n')
fh_out.write(f"tRNAs: {len([f for f in features if f['type'] == bc.FEATURE_T_RNA])}\n")
fh_out.write(f"tmRNAs: {len([f for f in features if f['type'] == bc.FEATURE_TM_RNA])}\n")
fh_out.write(f"rRNAs: {len([f for f in features if f['type'] == bc.FEATURE_R_RNA])}\n")
fh_out.write(f"ncRNAs: {len([f for f in features if f['type'] == bc.FEATURE_NC_RNA])}\n")
fh_out.write(f"ncRNA regions: {len([f for f in features if f['type'] == bc.FEATURE_NC_RNA_REGION])}\n")
fh_out.write(f"CRISPR arrays: {len([f for f in features if f['type'] == bc.FEATURE_CRISPR])}\n")
fh_out.write(f"tRNAs: {len([feat for feat in features if feat['type'] == bc.FEATURE_T_RNA])}\n")
fh_out.write(f"tmRNAs: {len([feat for feat in features if feat['type'] == bc.FEATURE_TM_RNA])}\n")
fh_out.write(f"rRNAs: {len([feat for feat in features if feat['type'] == bc.FEATURE_R_RNA])}\n")
fh_out.write(f"ncRNAs: {len([feat for feat in features if feat['type'] == bc.FEATURE_NC_RNA])}\n")
fh_out.write(f"ncRNA regions: {len([feat for feat in features if feat['type'] == bc.FEATURE_NC_RNA_REGION])}\n")
fh_out.write(f"CRISPR arrays: {len([feat for feat in features if feat['type'] == bc.FEATURE_CRISPR])}\n")
fh_out.write(f"CDSs: {len(cdss)}\n")
fh_out.write(f"pseudogenes: {len([cds for cds in cdss if 'pseudogene' in cds])}\n")
fh_out.write(f"hypotheticals: {len([cds for cds in cdss if 'hypothetical' in cds])}\n")
fh_out.write(f"signal peptides: {len([cds for cds in cdss if bc.FEATURE_SIGNAL_PEPTIDE in cds])}\n")
fh_out.write(f"sORFs: {len([f for f in features if f['type'] == bc.FEATURE_SORF])}\n")
fh_out.write(f"gaps: {len([f for f in features if f['type'] == bc.FEATURE_GAP])}\n")
fh_out.write(f"oriCs: {len([f for f in features if f['type'] == bc.FEATURE_ORIC])}\n")
fh_out.write(f"oriVs: {len([f for f in features if f['type'] == bc.FEATURE_ORIV])}\n")
fh_out.write(f"oriTs: {len([f for f in features if f['type'] == bc.FEATURE_ORIT])}\n")
fh_out.write(f"sORFs: {len([feat for feat in features if feat['type'] == bc.FEATURE_SORF])}\n")
fh_out.write(f"gaps: {len([feat for feat in features if feat['type'] == bc.FEATURE_GAP])}\n")
fh_out.write(f"oriCs: {len([feat for feat in features if feat['type'] == bc.FEATURE_ORIC])}\n")
fh_out.write(f"oriVs: {len([feat for feat in features if feat['type'] == bc.FEATURE_ORIV])}\n")
fh_out.write(f"oriTs: {len([feat for feat in features if feat['type'] == bc.FEATURE_ORIT])}\n")
fh_out.write('\nBakta:\n')
fh_out.write(f'Software: v{bakta.__version__}\n')
fh_out.write(f"Database: v{cfg.db_info['major']}.{cfg.db_info['minor']}, {cfg.db_info['type']}\n")
Expand Down
14 changes: 7 additions & 7 deletions bakta/proteins.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -199,12 +199,12 @@ def map_aa_columns(feat: dict) -> Sequence[str]:
str(feat['length']),
gene,
feat['product'],
','.join([k.replace('EC:', '') for k in feat['db_xrefs'] if 'EC:' in k]),
','.join([k for k in feat['db_xrefs'] if 'GO:' in k]),
','.join([k.replace('COG:', '') for k in feat['db_xrefs'] if 'COG:' in k]),
','.join([k.replace('RefSeq:', '') for k in feat['db_xrefs'] if 'RefSeq:' in k]),
','.join([k.replace('UniParc:', '') for k in feat['db_xrefs'] if 'UniParc:' in k]),
','.join([k.replace('UniRef:', '') for k in feat['db_xrefs'] if 'UniRef' in k])
','.join([dbxref.replace('EC:', '') for dbxref in feat['db_xrefs'] if 'EC:' in dbxref]),
','.join([dbxref for dbxref in feat['db_xrefs'] if 'GO:' in dbxref]),
','.join([dbxref.replace('COG:', '') for dbxref in feat['db_xrefs'] if 'COG:' in dbxref]),
','.join([dbxref.replace('RefSeq:', '') for dbxref in feat['db_xrefs'] if 'RefSeq:' in dbxref]),
','.join([dbxref.replace('UniParc:', '') for dbxref in feat['db_xrefs'] if 'UniParc:' in dbxref]),
','.join([dbxref.replace('UniRef:', '') for dbxref in feat['db_xrefs'] if 'UniRef' in dbxref])
]


Expand All @@ -214,7 +214,7 @@ def map_hypothetical_columns(feat: dict) -> Sequence[str]:
str(feat['length']),
f"{(feat['seq_stats']['molecular_weight']/1000):.1f}" if feat['seq_stats']['molecular_weight'] else 'NA'
f"{feat['seq_stats']['isoelectric_point']:.1f}" if feat['seq_stats']['isoelectric_point'] else 'NA'
','.join([k.replace('PFAM:', '') for k in feat['db_xrefs'] if 'PFAM:' in k])
','.join([dbxref.replace('PFAM:', '') for dbxref in feat['db_xrefs'] if 'PFAM:' in dbxref])
]


Expand Down
28 changes: 14 additions & 14 deletions scripts/collect-annotation-stats.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -82,20 +82,20 @@
f"{100 * data['stats']['n_ratio']:.1f}",
f"{data['stats']['n50']}",
f"{100 * data['stats']['coding_ratio']:.1f}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_T_RNA])}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_TM_RNA])}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_R_RNA])}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_NC_RNA])}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_NC_RNA_REGION])}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_CRISPR])}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_CDS])}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_CDS and 'hypothetical' in f])}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_CDS and 'pseudogene' in f])}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_SORF])}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_GAP])}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_ORIC])}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_ORIV])}",
f"{len([f for f in data['features'] if f['type'] == bc.FEATURE_ORIT])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_T_RNA])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_TM_RNA])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_R_RNA])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_NC_RNA])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_NC_RNA_REGION])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_CRISPR])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_CDS])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_CDS and 'hypothetical' in feat])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_CDS and 'pseudogene' in feat])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_SORF])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_GAP])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_ORIC])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_ORIV])}",
f"{len([feat for feat in data['features'] if feat['type'] == bc.FEATURE_ORIT])}",
]
output_line = '\t'.join(stats)
print(output_line)
Expand Down
4 changes: 2 additions & 2 deletions test/test_bakta.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ def test_bakta_plasmid(tmpdir):
bc.FEATURE_ORIT: 0
}
for type, count in feature_counts_expected.items():
assert len([f for f in features if f['type'] == type]) == count
assert len([feat for feat in features if feat['type'] == type]) == count


@pytest.mark.parametrize(
Expand Down Expand Up @@ -142,5 +142,5 @@ def test_bakta_genome(db, tmpdir):
bc.FEATURE_ORIT: 0
}
for type, count in feature_counts_expected.items():
assert len([f for f in features if f['type'] == type]) == count
assert len([feat for feat in features if feat['type'] == type]) == count

0 comments on commit fe9eece

Please sign in to comment.