Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- humancoords = dict()
- gzed = urllib.urlopen(HUMANCOORDS_REMOTE_FILE).read()
- content = gzip.GzipFile(fileobj=StringIO.StringIO(gzed))
- lines = (x.strip() for x in content)
- data = (x.split("\t") for x in lines)
- filtered = (x for x in data if x[11]=="GENE" and x[12]=="Primary Assembly")
- for ar in filtered:
- humanid = ar[10].replace("GeneID:", "") # GeneID:100131754
- humancoords[humanid] = (ar[1], ar[2], ar[3], ar[4])
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement