-
Notifications
You must be signed in to change notification settings - Fork 10
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pgenome:~/project/moa11 into moa.0.11
- Loading branch information
Showing
6 changed files
with
251 additions
and
33 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,44 @@ | ||
#!/usr/bin/env python | ||
|
||
import os | ||
import re | ||
import sys | ||
import argparse | ||
|
||
parser = argparse.ArgumentParser() | ||
parser.add_argument('fastq') | ||
parser.add_argument('output') | ||
parser.add_argument('-n', dest='non', help='nubmer NNNs to cut a fastq file', | ||
type=int, default=10) | ||
|
||
args = parser.parse_args() | ||
|
||
F = open(args.fastq) | ||
G = open(args.output, 'w') | ||
|
||
splitter = re.compile('n{'+str(args.non)+',}', re.I) | ||
|
||
header = F.readline() | ||
assert(header[0] == '@') | ||
header = header[1:].split()[0] | ||
print 'header', header | ||
|
||
seq = [] | ||
for line in F: | ||
if line[0] == '+': break | ||
seq.append(line.strip()) | ||
seq = "".join(seq) | ||
print 'read %d nt' % len(seq) | ||
|
||
contigs = splitter.split(seq) | ||
for i, c in enumerate(contigs): | ||
G.write(">%s_%s\n" % (header, i)) | ||
while c: | ||
G.write("%s\n" % c[:80]) | ||
c = c[80:] | ||
|
||
print "wrote %d contigs to %s" % (len(contigs), sys.argv[2]) | ||
|
||
F.close() | ||
G.close() | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,128 @@ | ||
#!/usr/bin/env python | ||
|
||
import os | ||
import sys | ||
import gzip | ||
import time | ||
import cPickle | ||
import argparse | ||
import collections | ||
import numpy as np | ||
|
||
seqs = {} | ||
types = [] | ||
|
||
parser = argparse.ArgumentParser(description='Do fancy region stuff based on GFFs.') | ||
|
||
parser.add_argument('-b', dest='base', help='basename for output', default='gff_regionify') | ||
parser.add_argument('lengths', help='file with the lengths of all sequences') | ||
parser.add_argument('gff', help='input gff') | ||
parser.add_argument('--vcf', dest='vcf', help='vcf file to categorize') | ||
|
||
args = parser.parse_args() | ||
|
||
starttime= time.time() | ||
|
||
print 'creating numpy structure' | ||
totn = 0 | ||
with open(args.lengths) as F: | ||
for i, line in enumerate(F): | ||
si, ln = line.split() | ||
ln = int(ln) | ||
totn += ln | ||
seqs[si] = np.zeros(ln, dtype=np.uint16) | ||
if (i+1) % 72 == 0: | ||
sys.stdout.write('\r%d ' % i) | ||
sys.stdout.flush() | ||
print 'generated space for %d nt' % totn | ||
|
||
print 'loading annotations' | ||
with open(args.gff) as F: | ||
for i, line in enumerate(F): | ||
line = line.strip() | ||
if not line: continue | ||
if line[0] == '#': continue | ||
ls = line.strip().split() | ||
atype = ls[2] | ||
|
||
if not atype in types: | ||
print 'adding type', atype | ||
types.append(atype) | ||
|
||
sqid = ls[0] | ||
start = int(ls[3]) | ||
stop = int(ls[4]) | ||
seqs[sqid][start-1:stop-1] = \ | ||
np.bitwise_or(seqs[sqid][start-1:stop-1], 2 ** types.index(atype)) | ||
|
||
if i % (72*9) == 0 and i > 1000: | ||
sys.stdout.write('\r%d ' % i) | ||
sys.stdout.flush() | ||
|
||
print 'summarizing' | ||
summ = collections.defaultdict(int) | ||
tlen = 0 | ||
for j, sid in enumerate(seqs): | ||
tlen += len(seqs[sid]) | ||
for i, t in enumerate(types): | ||
summ[t] += len(np.nonzero(np.bitwise_and(seqs[sid], 2 ** i))[0]) | ||
if j % 72 == 0: | ||
sys.stdout.write('\r%d ' % i) | ||
sys.stdout.flush() | ||
|
||
with open(args.base + '.wg.stats', 'w') as F: | ||
print "total\t%s" % (tlen) | ||
F.write("total\t%s\n" % (tlen)) | ||
for t in summ: | ||
print "%s\t%s" % (t, summ[t]) | ||
F.write("%s\t%s\n" % (t, summ[t])) | ||
|
||
if not args.vcf: | ||
sys.exit() | ||
|
||
def vcfreader(filename): | ||
with open(filename) as F: | ||
for line in F: | ||
line = line.strip() | ||
if not line: continue | ||
if line[0] == '#': continue | ||
ls = line.split() | ||
if len(ls) < 2: continue | ||
yield ls[0], int(ls[1]) | ||
|
||
|
||
vsumm = collections.defaultdict(int) | ||
vcfi = 0 | ||
print '\nProcessing VCF %s' % args.vcf | ||
for sid, pos in vcfreader(args.vcf): | ||
pos = pos -1 #vcf is 1 based!! | ||
try: | ||
m = seqs[sid][pos] | ||
except IndexError: | ||
print "cannot find mask value for %s/%s" % pos, sid | ||
raise | ||
vcfi += 1 | ||
for i, t in enumerate(types): | ||
inni = np.bitwise_and(m, 2 ** i) | ||
if inni > 0: | ||
#print "%s:%s mask %2d type %2d/%10s inni %d" % ( | ||
# sid, pos, m, i, t, inni) | ||
vsumm[t] += 1 | ||
|
||
if vcfi % 72 == 0: | ||
sys.stdout.write('\r%d' % vcfi) | ||
sys.stdout.flush() | ||
|
||
with open(args.base + '.vcf.stats', 'w') as F: | ||
print "total\t%s" % (vcfi) | ||
F.write("total\t%s\n" % (vcfi)) | ||
for t in vsumm: | ||
print "%s\t%s" % (t, vsumm[t]) | ||
F.write("%s\t%s\n" % (t, vsumm[t])) | ||
|
||
|
||
|
||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.