Skip to content

fix: six bugs that break FORMAT_KEGG_DB and KEGG annotation pipeline #485

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ruben1294 wants to merge 3 commits into
base: dev
Choose a base branch
from
Open

fix: six bugs that break FORMAT_KEGG_DB and KEGG annotation pipeline #485

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
743bf8e
fix(format-kegg-db): three bugs in format_kegg_database.py
ruben1294 Feb 24, 2026
3afbce8
fix(format-kegg-db): two bugs in format_kegg_db.nf
ruben1294 Feb 24, 2026
f4b2394
fix(dram): pass boolean string to FORMAT_KEGG_DB skip_gene_ko_link
ruben1294 Feb 24, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions bin/format_kegg_database.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,6 @@
from glob import glob
import logging
import subprocess
from skbio import write as write_sequence, read as read_sequence
from collections import defaultdict
import gzip
import argparse
Expand Down Expand Up @@ -64,6 +63,7 @@ def process_kegg(
download_date = get_iso_date()
if gene_ko_link_loc is not None and Path(gene_ko_link_loc).exists():
# add KOs to end of header where KO is not already there
from skbio import write as write_sequence
kegg_mod_loc = path.join(output_dir, "kegg.mod.fa")
write_sequence(
generate_modified_kegg_fasta(kegg_loc, gene_ko_link_loc),
Expand All @@ -73,7 +73,7 @@ def process_kegg(
else:
kegg_mod_loc = kegg_loc
# make mmseqsdb from modified kegg fasta
kegg_mmseqs_db = path.join(output_dir, "kegg.%s.mmsdb" % download_date)
kegg_mmseqs_db = path.join(output_dir, "kegg.mmsdb")
create_mmseqs(
kegg_mod_loc,
kegg_mmseqs_db,
Expand Down Expand Up @@ -114,6 +114,7 @@ def generate_modified_kegg_fasta(kegg_fasta, gene_ko_link_loc=None):
Takes kegg fasta file and gene ko link file, adds kos not already in headers to headers
Whish I knew about this, oh well I may split this out.
"""
from skbio import write as write_sequence, read as read_sequence
genes_ko_dict = defaultdict(list)
if gene_ko_link_loc is not None:
if gene_ko_link_loc.endswith(".gz"):
Expand Down Expand Up @@ -150,9 +151,8 @@ def main():
)
parser.add_argument(
"--skip_gene_ko_link",
type=bool,
action="store_true",
help="Skip gene KO link processing. If not passed in, `--gene_ko_link_loc` is required",
default=False,
)
parser.add_argument(
"--output_dir", type=str, help="Path to the output directory", default="kegg"
Expand Down
4 changes: 2 additions & 2 deletions modules/local/database/format_kegg_db.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ process FORMAT_KEGG_DB {
errorStrategy 'finish'

conda "${moduleDir}/environment.yml"
container "community.wave.seqera.io/library/python_scikit-bio_scipy:0f89a100e990daf2"
container "community.wave.seqera.io/library/python_pandas_hmmer_mmseqs2_pruned:d2c88b719ab1322c"

tag { ch_kegg_pep }

Expand All @@ -19,7 +19,7 @@ process FORMAT_KEGG_DB {

script:
"""
if [ ${skip_gene_ko_link} ]; then
if [ "${skip_gene_ko_link}" = "true" ]; then
echo "No Gene KO Link file provided. Running KEGG DB formatting without"
format_kegg_database.py --kegg_loc ${ch_kegg_pep} --download_date ${kegg_download_date} --threads ${params.threads} --output_dir kegg --skip_gene_ko_link
else
Expand Down
2 changes: 1 addition & 1 deletion workflows/dram.nf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -212,7 +212,7 @@ workflow DRAM {

gene_ko_link_f = params.gene_ko_link_loc && file(params.gene_ko_link_loc).exists() ? file(params.gene_ko_link_loc) : default_sheet
kegg_download_date = params.kegg_download_date ? params.kegg_download_date : "''"
skip_gene_ko_link = params.skip_gene_ko_link ? 1 : 0
skip_gene_ko_link = params.skip_gene_ko_link ? "true" : "false"
FORMAT_KEGG_DB( kegg_pep_f, gene_ko_link_f, kegg_download_date, skip_gene_ko_link )

} else if (params.merge_annotations){
Expand Down