Skip to content

Fix issues with some NCBI GenBank (INPHARED) entries #131

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

Merged
gbouras13 merged 2 commits into from
May 28, 2026
Merged

Fix issues with some NCBI GenBank (INPHARED) entries #131

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
89cc7da
fix issue with NCBI GenBank GBK having a CDS with no translation (pse…
gbouras13 May 26, 2026
ffadecb
fix issue NCBI annotation with no product
gbouras13 May 26, 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
25 changes: 19 additions & 6 deletions src/phold/results/topfunction.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -427,12 +427,25 @@ def calculate_topfunctions_results(
updated_cds_dict[record_id][cds_id].qualifiers["phrog"][0] = (
result_dict[record_id][cds_id]["phrog"]
)
updated_cds_dict[record_id][cds_id].qualifiers["product"][0] = (
result_dict[record_id][cds_id]["product"]
)
updated_cds_dict[record_id][cds_id].qualifiers["function"][
0
] = result_dict[record_id][cds_id]["function"]

# Handle missing product qualifier - see https://www.ncbi.nlm.nih.gov/nuccore/OY726582.1/ CAJ1523274.1
if "product" not in updated_cds_dict[record_id][cds_id].qualifiers:
updated_cds_dict[record_id][cds_id].qualifiers["product"] = [
result_dict[record_id][cds_id]["product"]
]
else:
updated_cds_dict[record_id][cds_id].qualifiers["product"][0] = (
result_dict[record_id][cds_id]["product"]
)
# Handle missing function qualifier
if "function" not in updated_cds_dict[record_id][cds_id].qualifiers:
updated_cds_dict[record_id][cds_id].qualifiers["function"] = [
result_dict[record_id][cds_id]["function"]
]
else:
updated_cds_dict[record_id][cds_id].qualifiers["function"][0] = (
result_dict[record_id][cds_id]["function"]
)

# pharokka has a phrog (or genbank doesn't exist)
else:
Expand Down
46 changes: 31 additions & 15 deletions src/phold/subcommands/compare.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,23 +139,39 @@ def subcommand_compare(
cds_feature.qualifiers["ID"][0]
] = cds_feature

# not pharokka - must be from genbank (supported only)
# not pharokka - must be from ncbi genbank (supported only)
except:
try:
# add these extra fields to make it all play nice
cds_feature.qualifiers["ID"] = cds_feature.qualifiers[
"protein_id"
]
cds_feature.qualifiers["function"] = []
cds_feature.qualifiers["function"].append(
"unknown function"
)
cds_feature.qualifiers["phrog"] = []
cds_feature.qualifiers["phrog"].append("No_PHROG")

cds_dict[record_id][
cds_feature.qualifiers["ID"][0]
] = cds_feature
# some NCBI Genbank CDS are actually pseudos
# e.g. OM418625

# CDS 19638..19895
# /locus_tag="CPT_lambdaimm21_023"
# /pseudogene="unknown"
# /codon_start=1
# /transl_table=11
# /product="tail fiber protein stf"
if "pseudogene" in cds_feature.qualifiers:

#logger.warning(f"Skipping pseudogene: {cds_feature}")
continue
else:

# add these extra fields to make it all play nice
cds_feature.qualifiers["ID"] = cds_feature.qualifiers[
"protein_id"
]
cds_feature.qualifiers["function"] = []
cds_feature.qualifiers["function"].append(
"unknown function"
)
cds_feature.qualifiers["phrog"] = []
cds_feature.qualifiers["phrog"].append("No_PHROG")

cds_dict[record_id][
cds_feature.qualifiers["ID"][0]
] = cds_feature

except:
logger.error(
Expand All @@ -175,7 +191,7 @@ def subcommand_compare(

i = 1
for non_cds_feature in record.features:
if non_cds_feature.type != "CDS":
if non_cds_feature.type != "CDS" or (non_cds_feature.type == "CDS" and "pseudogene" in cds_feature.qualifiers): # captures the pseudos
try:
non_cds_dict[record_id][
non_cds_feature.qualifiers["ID"][0]
Expand Down
25 changes: 25 additions & 0 deletions src/phold/subcommands/predict.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,6 +104,31 @@ def subcommand_predict(
# due to the weird list issue when parsing from genbank file
if fasta_flag is False:

# cds_feature.qualifiers["translation"] = cds_feature.qualifiers[
# "translation"
# ][0]

# some NCBI Genbank CDS are actually pseudos
# e.g. OM418625

# CDS 19638..19895
# /locus_tag="CPT_lambdaimm21_023"
# /pseudogene="unknown"
# /codon_start=1
# /transl_table=11
# /product="tail fiber protein stf"

if (
"translation" not in cds_feature.qualifiers
or len(cds_feature.qualifiers["translation"]) == 0
):
logger.warning(
f"Skipping CDS without provided translation in input, likely a pseudogene"
)
logger.warning(f"CDS: {cds_feature}"
)
continue

cds_feature.qualifiers["translation"] = cds_feature.qualifiers[
"translation"
][0]
Expand Down
2 changes: 1 addition & 1 deletion src/phold/utils/VERSION
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
1.2.5
1.2.6
Loading
Loading