Enable API validation

process.py

@@ -203,7 +203,7 @@ class Process():
         df['SNPs'] = df['SNPs'].str.lower()
 
         # Check if there is two gene names
-        sym = [',', '-', '/', '|']
+        sym = [',', '/', '|']
         for i in df.index:
             gene = df.loc[i, 'Genes']
             for s in sym:
@@ -238,60 +238,60 @@ class Process():
         df_clean = df.copy()
 
         # # Validate genes and SNPs with APIs
-        # def permutate(word):
+        def permutate(word):
 
-        #     if len(word) == 0:
-        #         return ['']
+            if len(word) == 0:
+                return ['']
 
-        #     change = []
-        #     res = permutate(word[1:])
+            change = []
+            res = permutate(word[1:])
 
-        #     if word[0] in mistakes:
-        #         change = [mistakes[word[0]] + r for r in res]
+            if word[0] in mistakes:
+                change = [mistakes[word[0]] + r for r in res]
 
-        #     return [word[0] + r for r in res] + change
+            return [word[0] + r for r in res] + change
         
-        # def call(url):
-
-        #     while True:
-        #         try:
-        #             res = requests.get(url)
-        #             time.sleep(1)
-        #             break
-        #         except Exception as e:
-        #             print(e)
-
-        #     return res
-
-        # mistakes = {'I': '1', 'O': '0'} # Common mistakes need to be maintained
-        # dbsnp = {}
-
-        # for i in df.index:
-        #     snp = df.loc[i, 'SNPs']
-        #     gene = df.loc[i, 'Genes']
-
-        #     if snp not in dbsnp:
-        #         res = call(f'https://www.ebi.ac.uk/gwas/rest/api/singleNucleotidePolymorphisms/{snp}/')
-        #         try:
-        #             res = res.json()
-        #             dbsnp[snp] = [r['gene']['geneName'] for r in res['genomicContexts']]
-        #         except:
-        #             dbsnp[snp] = []
-
-        #         res = call(f'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=snp&retmode=json&id={snp[2:]}').json()['result'][snp[2:]]
-        #         if 'error' not in res:
-        #             dbsnp[snp].extend([r['name'] for r in res['genes']])
-
-        #         dbsnp[snp] = list(set(dbsnp[snp]))
-
-        #     if gene not in dbsnp[snp]:
-        #         for other in permutate(gene):
-        #             if other in dbsnp[snp]:
-        #                 df.loc[i, 'Genes'] = other
-        #                 print(f'{gene} corrected to {other}')
-        #                 break
-        #         else:
-        #             df = df.drop(i)
+        def call(url):
+
+            while True:
+                try:
+                    res = requests.get(url)
+                    time.sleep(1)
+                    break
+                except Exception as e:
+                    print(e)
+
+            return res
+
+        mistakes = {'I': '1', 'O': '0'} # Common mistakes need to be maintained
+        dbsnp = {}
+
+        for i in df.index:
+            snp = df.loc[i, 'SNPs']
+            gene = df.loc[i, 'Genes']
+
+            if snp not in dbsnp:
+                res = call(f'https://www.ebi.ac.uk/gwas/rest/api/singleNucleotidePolymorphisms/{snp}/')
+                try:
+                    res = res.json()
+                    dbsnp[snp] = [r['gene']['geneName'] for r in res['genomicContexts']]
+                except:
+                    dbsnp[snp] = []
+
+                res = call(f'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=snp&retmode=json&id={snp[2:]}').json()['result'][snp[2:]]
+                if 'error' not in res:
+                    dbsnp[snp].extend([r['name'] for r in res['genes']])
+
+                dbsnp[snp] = list(set(dbsnp[snp]))
+
+            if gene not in dbsnp[snp]:
+                for other in permutate(gene):
+                    if other in dbsnp[snp]:
+                        df.loc[i, 'Genes'] = other
+                        print(f'{gene} corrected to {other}')
+                        break
+                else:
+                    df = df.drop(i)
 
         # df.reset_index(drop=True, inplace=True)
         df_no_llm = df.copy()