Reorganization

makeAnotations.py → annotate/makeAnotations.py

@@ -2,9 +2,9 @@
 # -*- coding: utf-8 -*-
 import glob,re,argparse
 
-#from taxadb.schema import *
-#from taxadb import accession
-#from taxadb import taxid
+from taxadb.schema import *
+from taxadb import accession
+from taxadb import taxid
 
 parser = argparse.ArgumentParser()
 parser.add_argument("hmmDB", help="hmm file")
@@ -55,15 +55,19 @@ print("\nReading acc number from gathered data")
 for currCluster in allHMM.keys():
     accs = []
     for ca in allHMM[currCluster]["annotations"]:
-        print(ca)
-        accs.append(ca.split("|")[3].split(".")[0])
-    #allHMM[currCluster]["taxid"] = accession.taxid(accs, args.taxadb, Prot)
-    allHMM[currCluster]["taxid"] = "1234"
+        accs.append(re.findall("[A-Z0-9\._]{5,10}",ca)[0].split(".")[0])
+    allHMM[currCluster]["taxid"] = []
+    currAcc = 0
+    # proceeding by lots, to avoid `too many SQL variables` issue
+    while currAcc < len(accs):
+        allHMM[currCluster]["taxid"].append(accession.taxid(accs[currAcc:(min(currAcc+50,len(accs)-1))], args.taxadb, Prot))
+        currAcc += 50
     # from taxid family
     allHMM[currCluster]["families"] = {}
-    for ct in allHMM[currCluster]["taxid"]:
-        #lineage = taxid.lineage_name(ct[1], args.taxadb)
-        lineage = (1234,"ABCD")
+    # deloting
+    for ctgen in allHMM[currCluster]["taxid"]:
+        for ct in ctgen:
+            lineage = taxid.lineage_name(ct[1], args.taxadb)
             family = lineage[2]
             if family not in allHMM[currCluster]["families"].keys():
                 allHMM[currCluster]["families"][family] = 1
@@ -81,4 +85,4 @@ for currCluster in allHMM.keys():
     currAnnot.write("FAMILIES\t" + str(allHMM[currCluster]["families"]) + "\n")
     currAnnot.write("FASTA SEQUENCE TITLES:\n")
     for currST in allHMM[currCluster]["annotations"]:
-        currAnnot.write(currST+"\n")
+        currAnnot.write(currST)