Skip to content
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

[pull] master from PGScatalog:master #151

Merged
merged 2 commits into from
Dec 3, 2024
Merged

[pull] master from PGScatalog:master #151

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0a8aeca
Search the cohort 'long name' (column 'Cohort Name') in the Cohort Re…
ens-lgil Nov 28, 2024
062c31f
Merge pull request #398 from ens-lgil/feature/gwas_cohorts_2
fyvon Dec 3, 2024
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
15 changes: 15 additions & 0 deletions curation/template_parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@ def __init__(self):
self.parsed_publication = None
self.parsed_scores = {}
self.parsed_cohorts = {}
self.parsed_cohorts_long_names = {}
self.parsed_samples_scores = []
self.parsed_samples_testing = []
self.parsed_performances = []
Expand Down Expand Up @@ -89,6 +90,9 @@ def extract_cohorts(self):
if cohort_id in self.parsed_cohorts:
self.report_warning(spreadsheet_name, f'Ambiguity found in the Cohort spreadsheet: the cohort ID "{cohort_name}" has been found more than once!')
self.parsed_cohorts[cohort_id] = parsed_cohort
if parsed_cohort.name_long:
cohort_long_name = parsed_cohort.name_long.upper()
self.parsed_cohorts_long_names[cohort_long_name] = cohort_id
self.update_report(parsed_cohort)


Expand Down Expand Up @@ -275,6 +279,11 @@ def get_sample_data(self, sample_info, current_schema, spreadsheet_name, samples
cohort_id = cohort.upper()
if cohort_id in self.parsed_cohorts:
cohorts_list.append(self.parsed_cohorts[cohort_id])
# Check if the cohort name corresponds to a cohort long name on the Cohort Refr. spreadsheet
elif cohort_id in self.parsed_cohorts_long_names.keys():
new_cohort_id = self.parsed_cohorts_long_names[cohort_id]
cohorts_list.append(self.parsed_cohorts[new_cohort_id])
self.report_warning(spreadsheet_name, f'Warning: the sample cohort "{cohort}" has been found in the Cohort Refr. spreadsheet as "{new_cohort_id}"')
else:
self.report_error(spreadsheet_name, f'Error: the sample cohort "{cohort}" cannot be found in the Cohort Refr. spreadsheet')
val = cohorts_list
Expand Down Expand Up @@ -331,6 +340,12 @@ def get_gwas_study(self,gcst_id:str,spreadsheet_cohorts:list,spreadsheet_name:st
if cohort_id in self.parsed_cohorts:
if cohort_id not in spreadsheet_cohorts_names:
cohorts_list.append(self.parsed_cohorts[cohort_id])
# Check if the cohort name corresponds to a cohort long name on the Cohort Refr. spreadsheet
elif cohort_id in self.parsed_cohorts_long_names.keys():
new_cohort_id = self.parsed_cohorts_long_names[cohort_id]
if new_cohort_id not in spreadsheet_cohorts_names:
cohorts_list.append(self.parsed_cohorts[new_cohort_id])
self.report_warning(spreadsheet_name, f'Warning: the GWAS Catalog sample cohort "{cohort}" has been found in the Cohort Refr. spreadsheet as "{new_cohort_id}"')
else:
self.report_error(spreadsheet_name, f'Error: the GWAS Catalog sample cohort "{cohort}" cannot be found in the Cohort Refr. spreadsheet')
# Print a message if the list of Cohorts from the spreadsheet and from GWAS Catalog (REST API) have been merged.
Expand Down
Loading