avrilcoghlan · March 4, 2022 11:33 · Mar 4, 2022
diff --git a/format_blastp_output_for_chembl_singleproteintargetsonly.py b/format_blastp_output_for_chembl_singleproteintargetsonly.py
@@ -0,0 +1,35 @@
+import os
+import sys
+from collections import defaultdict
+import FiftyHG_Chembl
+
+#====================================================================#
+
+def main():
+
+    # find the blast output files:  
+    blastoutput = defaultdict()
+    mydir = os.getcwd() # the current directory
+    myfiles = os.listdir(mydir)
+    for myfile in myfiles:
+        if myfile.endswith('.txt2'): # eg. schistosoma_mansoni.txt2
+            # find the species name:
+            temp = myfile.split('.txt2')
+            species = temp[0] # eg. schistosoma_mansoni
+            # read in the list of uniprot ids in chembl single-protein targets:
+            singleproteintargetfile = os.path.join(mydir, 'chembl_single_protein_targets_uniprot_ids')
+            assert(os.path.exists(singleproteintargetfile)) 
+            singleproteintargets = FiftyHG_Chembl.read_single_protein_targets(singleproteintargetfile) # returns a set of uniprot ids in targets
+            # parse and format this blast output file, to just take the blast matches to single-protein chembl targets:
+            myfile = os.path.join(mydir, myfile)
+            output_file = '%sb' % myfile 
+            print('Making file',output_file)
+            if not os.path.exists(output_file):  
+                FiftyHG_Chembl.reformat_blast_output_singleproteintargetsonly(myfile,species,singleproteintargets,output_file)                 
+
+#====================================================================#
+
+if __name__=="__main__":
+    main()
+
+#====================================================================#
No results found