Skip to content

Adjust pGlyco parser for variable column headers #74

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

Adjust pGlyco parser for variable column headers #74

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
c69e29c
adjust pglyco parser for variable column names
StSchulze Sep 12, 2025
ad04a1b
Merge branch 'update/pglyco_parser' of https://github.com/computation…
StSchulze Sep 12, 2025
131f329
Merge branch 'dev' into update/pglyco_parser
StSchulze Sep 12, 2025
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
71 changes: 33 additions & 38 deletions pyiohat/parsers/ident/pglyco_3_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,60 +22,55 @@ def __init__(self, *args, **kwargs):
self.df = pd.read_csv(self.input_file, delimiter="\t")
self.df.dropna(axis=1, how="all", inplace=True)
self.mapping_dict = {
"GlySpec": "pglyco:GlySpec",
"PepSpec": "pglyco:PepSpec",
# "GlySpec": "pglyco:GlySpec",
# "PepSpec": "pglyco:PepSpec",
"RawName": "raw_data_location",
"Scan": "spectrum_id",
"RT": "retention_time_seconds",
"PrecursorMH": "pglyco:PrecursorMH",
# "PrecursorMH": "pglyco:PrecursorMH",
"PrecursorMZ": "exp_mz",
"Charge": "charge",
"Rank": "rank",
"Peptide": "sequence",
"Mod": "modifications",
"PeptideMH": "pglyco:PeptideMH",
"Glycan(H,N,A,F)": "pglyco:Glycan(H,N,A,F)",
# "PeptideMH": "pglyco:PeptideMH",
# "Glycan(H,N,A,F)": "pglyco:Glycan(H,N,A,F)",
"GlycanComposition": "glycan_composition",
"PlausibleStruct": "pglyco:PlausibleStruct",
"GlyID": "pglyco:GlyID",
"GlyFrag": "pglyco:GlyFrag",
"GlyMass": "pglyco:GlyMass",
"GlySite": "pglyco:GlySite",
"TotalScore": "pglyco:TotalScore",
"PepScore": "pglyco:PepScore",
"GlyScore": "pglyco:GlyScore",
"CoreMatched": "pglyco:CoreMatched",
"MassDeviation": "pglyco:MassDeviation",
"PPM": "pglyco:PPM",
"GlyIonRatio": "pglyco:GlyIonRatio",
"byIonRatio": "pglyco:byIonRatio",
"czIonRatio": "pglyco:czIonRatio",
# "PlausibleStruct": "pglyco:PlausibleStruct",
# "GlyID": "pglyco:GlyID",
# "GlyFrag": "pglyco:GlyFrag",
# "GlyMass": "pglyco:GlyMass",
# "GlySite": "pglyco:GlySite",
# "TotalScore": "pglyco:TotalScore",
# "PepScore": "pglyco:PepScore",
# "GlyScore": "pglyco:GlyScore",
# "CoreMatched": "pglyco:CoreMatched",
# "MassDeviation": "pglyco:MassDeviation",
# "PPM": "pglyco:PPM",
# "GlyIonRatio": "pglyco:GlyIonRatio",
# "byIonRatio": "pglyco:byIonRatio",
# "czIonRatio": "pglyco:czIonRatio",
"GlyDecoy": "glycan_is_decoy",
"PepDecoy": "peptide_is_decoy",
"Ion_163.06": "pglyco:Ion_163.06",
"Ion_366.14": "pglyco:Ion_366.14",
"Ion_204.09": "pglyco:Ion_204.09",
"Ion_138.05": "pglyco:Ion_138.05",
"Ion_292.10": "pglyco:Ion_292.10",
"Ion_274.09": "pglyco:Ion_274.09",
# "Ion_163.06": "pglyco:Ion_163.06",
# "Ion_366.14": "pglyco:Ion_366.14",
# "Ion_204.09": "pglyco:Ion_204.09",
# "Ion_138.05": "pglyco:Ion_138.05",
# "Ion_292.10": "pglyco:Ion_292.10",
# "Ion_274.09": "pglyco:Ion_274.09",
}
# self.mapping_dict = {
# v: k
# for k, v in self.param_mapper.get_default_params(style=self.style)[
# "header_translations"
# ]["translated_value"].items()
# }
# pprint(f"mapping dict")
# pprint(self.mapping_dict)

original_columns = set(self.df.columns)
self.df.rename(columns=self.mapping_dict, inplace=True)
# pprint(f"renamed df")
# pprint(self.df)
unmapped_columns = original_columns.difference(self.mapping_dict.keys())
prefix_mapping_dict = {col: f"pglyco:{col}" for col in unmapped_columns}
self.df.rename(columns=prefix_mapping_dict, inplace=True)
self.df.columns = self.df.columns.str.lstrip(" ")
if not "modifications" in self.df.columns:
self.df["modifications"] = ""
self.reference_dict.update({k: None for k in self.mapping_dict.values()})
self.reference_dict.update({k: None for k in self.df.columns.tolist()})
self.metadata = {
"File Origin": "pGlyco",
"File Origin": "pglyco_3",
"Version": [3.0, 3.1],
"bigger_scores_better": True,
"validation_score_field": "pglyco:TotalScore",
Expand Down Expand Up @@ -113,7 +108,7 @@ def check_parser_compatibility(cls, file):
"Peptide",
"Mod",
"PeptideMH",
"Glycan(H,N,A,F)",
# "Glycan(H,N,A,F)",
"GlycanComposition",
"PlausibleStruct",
"GlyID",
Expand Down
2 changes: 1 addition & 1 deletion tests/ident/test_engine_parser_pglyco_3.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,7 @@ def test_engine_parsers_pglyco_metadata():
],
},
)
assert parser.metadata["File Origin"] == "pGlyco"
assert parser.metadata["File Origin"] == "pglyco_3"


def test_engine_parsers_pglyco_check_parser_compatibility():
Expand Down