Mercurial > repos > brinkmanlab > make_unique_id
comparison make_unique_id.py @ 1:061c3402a977 draft
"planemo upload for repository https://github.com/brinkmanlab/galaxy-tools/tree/master/make_unique_id commit b661895b5e2dff7235eb32476602c3b93411a42e"
author | brinkmanlab |
---|---|
date | Mon, 15 Jun 2020 18:48:27 -0400 |
parents | a3a09dd8d09a |
children | c8bda09480ae |
comparison
equal
deleted
inserted
replaced
0:a3a09dd8d09a | 1:061c3402a977 |
---|---|
27 | 27 |
28 format = sys.argv[1] | 28 format = sys.argv[1] |
29 ids = defaultdict(int) | 29 ids = defaultdict(int) |
30 | 30 |
31 def makeUnique(seq): | 31 def makeUnique(seq): |
32 count = ids[seq.id] | 32 newid = seq.id[:28] # Genbank has a max length for the id and sequence length number, truncate the sequence id if too long |
33 ids[seq.id] += 1 | 33 count = ids[newid] |
34 ids[newid] += 1 | |
34 if count: | 35 if count: |
35 suffix = "_" + str(count) | 36 suffix = "_" + str(count) |
36 newid = seq.id | |
37 seqlenlen = len(str(len(seq))) | 37 seqlenlen = len(str(len(seq))) |
38 if len(newid) + len(suffix) + 1 + seqlenlen > 28: | 38 if len(newid) + len(suffix) + 1 + seqlenlen > 28: |
39 # Genbank has a max length for the id and sequence length number, truncate the sequence id if too long | |
40 newid = newid[:27 - seqlenlen - len(suffix)] | 39 newid = newid[:27 - seqlenlen - len(suffix)] |
41 | 40 |
42 print(f"{seq.id}\t{newid}{suffix}") | 41 newid += suffix |
43 seq.id = newid + suffix | |
44 seq.name += suffix | 42 seq.name += suffix |
45 | 43 |
44 if seq.id != newid: | |
45 print(f"{seq.id}\t{newid}") | |
46 | |
47 seq.id = newid | |
46 return seq | 48 return seq |
47 | 49 |
48 | 50 |
49 paths = iter(sys.argv[2:]) | 51 paths = iter(sys.argv[2:]) |
50 | 52 |