Add new rsID handling

utils.py

@@ -26,6 +26,9 @@ mistakes = {
     'P': ['9']
 }
 
+raw_url = "https://www.ebi.ac.uk/gwas/api/search/downloads/alternative"
+gwas_path = "resources/gwas_catalog.tsv"
+
 def permutate(word):
 
     if len(word) == 0:
@@ -52,32 +55,38 @@ def call(url):
 
     return res
 
-raw_url = "https://www.ebi.ac.uk/gwas/api/search/downloads/alternative"
-gwas_path = "resources/gwas_catalog.tsv"
-
-# Load Raw GWAS files
-if os.path.exists(gwas_path):
-    gwas = pd.read_csv(gwas_path, delimiter='\t')[['DISEASE/TRAIT', 'CHR_ID', 'MAPPED_GENE', 'SNPS', 'P-VALUE', 'OR or BETA']]
-else:
-    data = requests.get(raw_url).content.decode('utf-8')
-    gwas = pd.read_csv(StringIO(data), delimiter='\t')[['DISEASE/TRAIT', 'CHR_ID', 'MAPPED_GENE', 'SNPS', 'P-VALUE', 'OR or BETA']]
-
-# Load Genes and SNPs from GWAS
-gwas_gene_rsid = gwas[['MAPPED_GENE', 'SNPS']]
-gwas_gene_rsid.dropna(inplace=True, ignore_index=True)
-gwas_gene_rsid['MAPPED_GENE'] = gwas_gene_rsid['MAPPED_GENE'].apply(lambda x: x.replace(' ', '').upper())
-
-# Generate Genes and SNPs mapping
-ground_truth = defaultdict(list)
-for i in gwas_gene_rsid.index:
-    gene = gwas_gene_rsid.loc[i, 'MAPPED_GENE']
-    snp = gwas_gene_rsid.loc[i, 'SNPS']
-
-    pattern = r"[,\-]"
-    genes = re.split(pattern, gene)
-    for gene in genes:
-        ground_truth[gene].append(snp)
-        ground_truth[snp].append(gene)
+def generate_raw_files():
+
+    # Load Raw GWAS files
+    if os.path.exists(gwas_path):
+        gwas = pd.read_csv(gwas_path, delimiter='\t')[['DISEASE/TRAIT', 'CHR_ID', 'MAPPED_GENE', 'SNPS', 'P-VALUE', 'OR or BETA']]
+    else:
+        data = requests.get(raw_url).content.decode('utf-8')
+        gwas = pd.read_csv(StringIO(data), delimiter='\t')[['DISEASE/TRAIT', 'CHR_ID', 'MAPPED_GENE', 'SNPS', 'P-VALUE', 'OR or BETA']]
+
+    # Load Genes and SNPs from GWAS
+    gwas_gene_rsid = gwas[['MAPPED_GENE', 'SNPS']]
+    gwas_gene_rsid.dropna(inplace=True, ignore_index=True)
+    gwas_gene_rsid['MAPPED_GENE'] = gwas_gene_rsid['MAPPED_GENE'].apply(lambda x: x.replace(' ', '').upper())
+
+    # Generate Genes and SNPs mapping
+    ground_truth = defaultdict(list)
+    for i in gwas_gene_rsid.index:
+        gene = gwas_gene_rsid.loc[i, 'MAPPED_GENE']
+        snp = gwas_gene_rsid.loc[i, 'SNPS']
+
+        pattern = r"[,x\-]"
+        genes = re.split(pattern, gene)
+        snps = re.split(pattern, snp)
+
+        for gene in genes:
+            for snp in snps:
+                ground_truth[gene].append(snp)
+                ground_truth[snp].append(gene)
+    
+    return gwas, ground_truth
+
+gwas, ground_truth = generate_raw_files()
 
 def integrate(df):