diff --git a/downloads-generation/data_curated/curate_ms_by_pmid.py b/downloads-generation/data_curated/curate_ms_by_pmid.py index 46645ff695404f9506c7b904d9a605ab9c3e7404..a8f312dc88aef0bd2c3d03e4444f0ad39cbd4ffe 100755 --- a/downloads-generation/data_curated/curate_ms_by_pmid.py +++ b/downloads-generation/data_curated/curate_ms_by_pmid.py @@ -806,7 +806,10 @@ def handle_pmid_31844290(*filenames): method='ffill') sample_info = sample_info.loc[sample_info.index.isin(allele_table.index)] sample_info = sample_info.loc[allele_table.index] - sample_info["hla"] = [" ".join(row) for _, row in allele_table.iterrows()] + sample_info["hla"] = [ + " ".join(row).replace("HLA-A*31:0102", "HLA-A*31:01") # fix a typo + for _, row in allele_table.iterrows() + ] sample_info["sample_type"] = sample_info['Cancer type'].map({ 'CLL': "B-CELL", 'GBM': "GLIOBLASTOMA_TISSUE",