Skip to content

Improve the script to get data from AllianceMine #1249

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
dondi merged 3 commits into from
Oct 8, 2025
Merged

Improve the script to get data from AllianceMine #1249

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
9e48bb2
Fixing when merging genes from protein table to the combined gene tab…
ntran18 Oct 7, 2025
d9ec93d
Modify the script to only include what we need when fetching Gene Reg…
ntran18 Oct 7, 2025
3ef34e1
Fixing a worning 'A value is trying to be set on a copy of a slice fr…
ntran18 Oct 7, 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
21 changes: 1 addition & 20 deletions database/network-database/data_services/data_fetcher_service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,13 +60,7 @@ def fetch_data(self):
query.add_view(
"regulatoryRegions.regulator.symbol",
"regulatoryRegions.regulator.secondaryIdentifier", "symbol",
"secondaryIdentifier", "regulatoryRegions.regEvidence.ontologyTerm.name",
"regulatoryRegions.regEvidence.ontologyTerm.identifier",
"regulatoryRegions.experimentCondition",
"regulatoryRegions.strainBackground",
"regulatoryRegions.regulationDirection", "regulatoryRegions.regulationType",
"regulatoryRegions.regulatorType",
"regulatoryRegions.publications.pubMedId", "regulatoryRegions.datasource",
"regulatoryRegions.annotationType", "featureType",
"regulatoryRegions.regulator.featureType"
)
Expand All @@ -90,15 +84,6 @@ def fetch_data(self):
"regulatorSystematicName": row["regulatoryRegions.regulator.secondaryIdentifier"],
"targetStandardName": row["symbol"],
"targetSystematicName": row["secondaryIdentifier"],
"ontologyTermName": row["regulatoryRegions.regEvidence.ontologyTerm.name"],
"ontologyTermIdentifier": row["regulatoryRegions.regEvidence.ontologyTerm.identifier"],
"experimentCondition": row["regulatoryRegions.experimentCondition"],
"strainBackground": row["regulatoryRegions.strainBackground"],
"regulationDirection": row["regulatoryRegions.regulationDirection"],
"regulatoryRegionsRegulationType": row["regulatoryRegions.regulationType"],
"regulatoryRegionsRegulatorType": row["regulatoryRegions.regulatorType"],
"pubMedId": row["regulatoryRegions.publications.pubMedId"],
"datasource": row["regulatoryRegions.datasource"],
"annotationType": row["regulatoryRegions.annotationType"]
})

Expand All @@ -117,12 +102,10 @@ def fetch_data(self):
query.add_view(
"primaryIdentifier", "secondaryIdentifier", "symbol", "name", "sgdAlias",
"interactions.details.annotationType",
"interactions.details.experiment.publication.pubMedId",
"interactions.participant2.symbol",
"interactions.participant2.secondaryIdentifier",
"interactions.details.experiment.interactionDetectionMethods.identifier",
"interactions.details.experiment.name",
"interactions.details.relationshipType", "featureType",
"interactions.details.experiment.name", "featureType",
"interactions.participant2.featureType", "proteins.symbol",
"interactions.participant2.proteins.symbol"
)
Expand Down Expand Up @@ -152,13 +135,11 @@ def fetch_data(self):
"name ": row["name"],
"sgdAlias": row["sgdAlias"],
"annotationType": row["interactions.details.annotationType"],
"pubMedId": row["interactions.details.experiment.publication.pubMedId"],
"gene2StandardName": row["interactions.participant2.symbol"],
"gene2SystematicName": row["interactions.participant2.secondaryIdentifier"],
"protein2StandardName": row["interactions.participant2.proteins.symbol"],
"interactionDetectionMethodsIdentifier": row["interactions.details.experiment.interactionDetectionMethods.identifier"],
"experimentName": row["interactions.details.experiment.name"],
"relationshipType": row["interactions.details.relationshipType"]
})

df = pd.DataFrame(rows_data)
Expand Down
5 changes: 4 additions & 1 deletion database/network-database/data_services/processor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,10 +57,13 @@ def _combine_with_protein_genes(self, genes, proteins):
genes_diff = genes[genes['systematicName'].isin(diff_systematic_names)]
proteins_diff = proteins[proteins['gene_systematic_name'].isin(diff_systematic_names)]

# Protein standard names are in the format of lowercase + "p" but for gene standard name, all letters should be uppercase and remove the trailing "p"
proteins_diff_with_correct_gene_standard_name = proteins_diff.copy()
proteins_diff_with_correct_gene_standard_name['standard_name'] = proteins_diff_with_correct_gene_standard_name['standard_name'].str.rstrip('p').str.upper()
# Combine the differences from both genes and proteins
diff_combined = pd.concat([
genes_diff[['systematicName', 'standardName']],
proteins_diff[['gene_systematic_name', 'standard_name']].rename(
proteins_diff_with_correct_gene_standard_name[['gene_systematic_name', 'standard_name']].rename(
columns={'gene_systematic_name': 'systematicName', 'standard_name': 'standardName'}
)
], ignore_index=True)
Expand Down