added new column in uniprot_nosql

KarrLab · Feb 3, 2020 · 5e22f6b · 5e22f6b
1 parent e50aefb
commit 5e22f6b
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 3 deletions.
diff --git a/datanator/data_source/gene_ortholog.py b/datanator/data_source/gene_ortholog.py
@@ -187,7 +187,7 @@ def main():
     )['datanator']['mongodb']['server']
     manager = KeggGeneOrtholog(server, collection_str=collection_str, username=username,
     password=password, des_db=des_db)
-    manager.load_data(skip=157723)
+    manager.load_data(skip=158673)
 
 if __name__ == '__main__':
     main()
diff --git a/datanator/data_source/uniprot_nosql.py b/datanator/data_source/uniprot_nosql.py
@@ -49,7 +49,7 @@ def load_uniprot(self, query=False, msg='', species=None):
             msg (:obj:`str`, optional): Query message. Defaults to ''.
             species (:obj:`list`, optional): species information to extract from df and loaded into uniprot. Defaults to None.
         """
-        fields = '&columns=id,entry name,genes(PREFERRED),protein names,sequence,length,mass,ec,database(GeneID),reviewed,organism-id,database(KO),genes(ALTERNATIVE),genes(ORF),genes(OLN),database(EMBL),database(RefSeq)'
+        fields = '&columns=id,entry name,genes(PREFERRED),protein names,sequence,length,mass,ec,database(GeneID),reviewed,organism-id,database(KO),genes(ALTERNATIVE),genes(ORF),genes(OLN),database(EMBL),database(RefSeq),Cross-reference (KEGG)'
         if not query:
             url = self.url + fields
         else:
@@ -76,9 +76,10 @@ def load_uniprot(self, query=False, msg='', species=None):
         data.columns = [
             'uniprot_id', 'entry_name', 'gene_name', 'protein_name', 'canonical_sequence', 'length', 'mass',
             'ec_number', 'entrez_id', 'status', 'ncbi_taxonomy_id', 'ko_number', 'gene_name_alt',
-            'gene_name_orf', 'gene_name_oln', 'sequence_embl', 'sequence_refseq'
+            'gene_name_orf', 'gene_name_oln', 'sequence_embl', 'sequence_refseq', 'kegg_org_gene'
         ]
         data['entrez_id'] = data['entrez_id'].astype(str).str.replace(';', '')
+        data['kegg_org_gene'] = data['kegg_org_gene'].astype(str).str.replace(';', '')
 
         try:
             data['mass'] = data['mass'].str.replace(',', '')