Commit 9726434b authored by Eric Coissac's avatar Eric Coissac

Add patch in to eliminate sequence without taxonomic data

git-svn-id: https://www.grenoble.prabi.fr/svn/LECASofts/ecoPCR/trunk@9 60f365c0-8329-0410-b2a4-ec073aeeaa1d
parent 78205cb1
......@@ -249,7 +249,10 @@ def genbankParser(entry):
Id = _gbParseID.findall(entry)[0]
De = ' '.join(_gbParseDE.findall(entry)[0].split())
Sq = cleanSeq(_gbParseSQ.findall(entry)[0].upper())
Tx = int(_gbParseTX.findall(entry)[0])
try:
Tx = int(_gbParseTX.findall(entry)[0])
except IndexError:
Tx = None
return {'id':Id,'taxid':Tx,'definition':De,'sequence':Sq}
def sequenceIterator(file,parser):
......@@ -354,15 +357,18 @@ def ecoSeqWriter(file,input,taxindex,parser=genbankParser):
progressBar(1, inputsize,reset=True)
for entry in entries:
entry['taxid']=taxindex[entry['taxid']]
if entry['taxid'] is not None:
seqcount+=1
output.write(ecoSeqPacker(entry))
entry['taxid']=taxindex[entry['taxid']]
if entry['taxid'] is not None:
seqcount+=1
output.write(ecoSeqPacker(entry))
else:
skipped.append[entry['id']]
where = universalTell(input)
progressBar(where, inputsize)
print >>sys.stderr," Readed sequences : %d " % seqcount,
else:
skipped.append[entry['id']]
where = universalTell(input)
progressBar(where, inputsize)
print >>sys.stderr," Read sequences : %d " % seqcount,
print >>sys.stderr
output.seek(0,0)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment