def getAlleleCount(bamfile, snpfile, outfile):
brcparams = Box()
brcparams.f = ref
brcparams.w = 0
brcparams.l = snpfile
brcparams[''] = bamfile
cmd = '{bamrc} {args} > {outfile!r}'.format(
bamrc = bamrc, args = cmdargs(brcparams, equal = ' '), outfile = outfile + '.tmp')
runcmd(cmd)
# reformated output to desired format
reader = TsvReader(outfile + '.tmp', cnames = False)
snper = TsvReader(snpfile, cnames = False)
#chr1 564773 C 14 =:0:0.00:0.00:0.00:0:0:0.00:0.00:0.00:0:0.00:0.00:0.00 A:0:0.00:0.00:0.00:0:0:0.00:0.00:0.00:0:0.00:0.00:0.00 C:14:... G:0:... T:0:... N:0:...
writer = TsvWriter(outfile)
writer.cnames = ['Chrm', 'pos', 'A', 'C', 'G', 'T', 'Total', 'refCount', 'mutCount']
for r in reader:
while True:
try:
snp = next(snper)
except StopIteration:
break
# use the end position, in case it's 0-based
if snp[0] == r[0] and snp[2] == r[1]:
counts = dict(
A = r[5].split(':', 2)[1],
C = r[6].split(':', 2)[1],
G = r[7].split(':', 2)[1],
T = r[8].split(':', 2)[1]
)
rec = TsvRecord()
rec.Chrm = r[0]
rec.pos = r[1]
rec.Total = r[3]
rec.A = counts['A']
rec.C = counts['C']
rec.G = counts['G']
rec.T = counts['T']
# if reference allele is unknown, assuming all are ref alleles
rec.refCount = counts.get(snp[6].upper(), r[3])
# if mut allele is unknown, assuming no mutations happened
rec.mutCount = counts.get(snp[7].upper(), 0)
writer.write(rec)
# go to next snp
break
else:
# go to next r
continue
writer.close()
# save the data file
# expfile
"""
S1 S2 .. Sn
G1 ...
G2 ...
"""
expreader = TsvReader(expfile)
expdata = [r for r in expreader if r[0] in genes or r[0] in tfs]
expreader.close()
datawriter = TsvWriter(outdata)
for i, cname in enumerate(expreader.cnames):
if i == 0:
# genes + tfs
datawriter.cnames = [r[0] for r in expdata]
datawriter.writeHead()
else:
datawriter.write([cname] + [r[i] for r in expdata])
datawriter.close()
del expdata
genes = [g for g in genes if g in datawriter.cnames]
tfs = [g for g in tfs if g in datawriter.cnames]
genetfs = {g: [tf for tf in gtfs if tf in tfs] for g, gtfs in genetfs.items() if g in genes}
# save the group file
# mutfile
"""
S1 S2 .. Sn
M1 ... (0/1/2/NA)
from bioprocs.utils.tsvio2 import TsvWriter, TsvRecord
from gff import Gff
infile = {{i.infile | quote}}
outfile = {{o.outfile | quote}}
attr2name = {{args.attr2name}}
keepinfo = {{args.keepinfo | repr}}
writer = TsvWriter(outfile)
writer.cnames = ['CHR', 'START', 'END', 'NAME', 'SCORE', 'STRAND']
if keepinfo:
writer.cnames.append('ORIGINAL')
def getNameFromAttrs(attrs):
if attr2name:
return attr2name(**attrs)
for key in sorted(attrs.keys()):
if key in writer.cnames:
continue
if 'id' in key.lower():
return attrs[key]
if 'name' in key.lower():
return attrs[key]
return attrs[key]
gff = Gff(infile)
for record in gff:
r = TsvRecord()
r.CHR = record['seqid']
r.START = record['start']
r.END = record['end']
outfile = {{ o.outfile | quote}}
outdir = {{ o.outdir | quote}}
params = {{ args.params | repr}}
idxfile = {{ args.idxfile | quote}}
kallisto = {{ args.kallisto | quote}}
nthread = {{ args.nthread | repr}}
shell.TOOLS.kallisto = kallisto
params.i = idxfile
params.o = outdir
params.t = nthread
params._ = [fq1, fq2]
kallisto = shell.Shell(subcmd = True).kallisto
kallisto.quant(**params).run()
imfile = path.join(outdir, 'abundance.tsv')
reader = TsvReader(imfile)
writer = TsvWriter(outfile)
writer.cnames = ['target_id', 'est_counts']
writer.writeHead()
for r in reader:
r.target_id = r.target_id.split('::')[0]
try:
r.est_counts = int(round(float(r.est_counts)))
except TypeError:
r.est_counts = 0
writer.write(r)
writer.close()
logger.info('%s motifs loaded', len(motifs))
if tool == 'meme':
cmdparams = []
params.thresh = pval
params.verbosity = 4
for motif, name in motifs.items():
params.oc = path.join(outdir, name + '.' + re.sub(r'[^\w_]', '', motif))
params.motif = motif
params[""] = [tfmotifs, sfile]
cmdparams.append((meme, cmdargs(params, dash = '--', equal = ' ')))
Parallel(nthread, raiseExc = True).run('{} {}', cmdparams)
writer = TsvWriter(outfile)
writer.cnames = [
"CHR", "START", "END", "NAME", "SCORE", "STRAND", "MOTIF", "SEQ", "STARTONSEQ",
"STOPONSEQ", "RAWSCORE", "PVAL", "QVAL", "MATCHEDSEQ", "UCSCLINK"
]
writer.writeHead(callback = lambda cnames: "#" + "\t".join(cnames))
def rowfactory(r):
r.PVAL = float(r['p-value'])
if r.PVAL >= pval:
return None
r.RAWSCORE = r.score
try:
r.SCORE = int(float(r.score) * 10)
except TypeError:
r.SCORE = 0
r.STRAND = r.strand
r.MOTIF = r.motif_id
# split motif_alt_id
)))
for _ in range(dist):
writer.write(next(reader))
writer.close()
para = Parallel(nthread, raiseExc = True)
para.run(getAlleleCount, [
(tumbam, path.join(
thdir, '{bname}.thread{i}.snp'.format(bname = asbname, i = i)
), path.join(
thdir, '{tumbn}.thread{i}.bamrc'.format(tumbn = path.basename(tumbam), i = i)
)) for i in range(nthread)
])
# merge to tumsnp
writer = TsvWriter(tumsnp)
writer.cnames = ['Chrm', 'pos', 'A', 'C', 'G', 'T', 'Total', 'refCount', 'mutCount']
writer.writeHead(lambda cn: "#" + "\t".join(cn))
for i in range(nthread):
subrc = path.join(
thdir, '{tumbn}.thread{i}.bamrc'.format(tumbn = path.basename(tumbam), i = i)
)
reader = TsvReader(subrc, cnames = False)
for r in reader:
writer.write(r.values())
reader.close()
writer.close()
# normal
para.run(getAlleleCount, [
(normbam, path.join(
thdir, '{bname}.thread{i}.snp'.format(bname = asbname, i = i)