def _pred_gene(ps): ### trans
'''Main function of ORF prediction in given transcript
'''
g, candidates, pf = ps
es, j = [], [0, 0]
tpfs = {} #trans profiles
genome = fa.Fa(genomefapath)
has_tis = len(tisbampaths) > 0
load = True
if candidates is not None:
if len(candidates) == 0: return es, j, tpfs, g
if len(pf) >= len(candidates): load = False
if len(pf) >= len(g.trans): load = False
if load:
tismbl = ribo.multiRiboGene(g,
tisbampaths,
offdict=tisoffdict,
compatible=compatible,
mis=compatiblemis,
paired=paired)
ribombl = ribo.multiRiboGene(g,
ribobampaths,
offdict=riboffdict,
compatible=compatible,
mis=compatiblemis,
paired=paired)
for t in g.trans:
#if candidates is not None and t.id not in candidates : continue
tl = t.cdna_length()
if tl < ribo.minTransLen: continue # return es, j, tpfs, g ##
#ttis = ribo.multiRibo(t, tisbampaths, offdict = tisoffdict, compatible = compatible)
#tribo = ribo.multiRibo(t, ribobampaths, offdict = riboffdict, compatible = compatible)
if not load:
if t.id in pf:
tispf, ribopf = pf[t.id]
ttis = ribo.Ribo(t)
tribo = ribo.Ribo(t)
if has_tis: ttis.dict2cnts(tispf)
tribo.dict2cnts(ribopf)
else:
print(
'Warning: transcript {} {} {} not in input trans profile! '
.format(t.gid, t.id, t.symbol))
continue
else:
ttis = ribo.Ribo(t,
bamload=tismbl,
compatible=compatible,
mis=compatiblemis)
tribo = ribo.Ribo(t,
bamload=ribombl,
compatible=compatible,
mis=compatiblemis)
score = ttis.abdscore()
ip = ribo.pidx(score, slp)
if verbose >= 2: print(io.tabjoin(g.id, t.id, ttis.total, tribo.total))
cds1 = t.cds_start(cdna=True)
cds2 = t.cds_stop(cdna=True)
tsq = genome.transSeq(t)
if transprofile is not None:
tid = '{}\t{}\t{}'.format(t.gid, t.id, t.symbol)
tpfs[tid] = '{}\t{}'.format(ttis.cnts_dict_str(),
tribo.cnts_dict_str())
if has_tis and tis2ribo: tribo.merge(ttis) ##
# user provided candidates
if candidates is not None:
if t.id not in candidates: continue
for tis, stop in candidates[t.id]:
j[0] += 1
j[1] += 1
if has_tis: tp = ttis.tis_test(tis, paras[ip][0], paras[ip][1])
else: tp = None
if enrichtest: rp = tribo.enrich_test(tis, stop)
else: rp = tribo.frame_test(tis, stop)
if tp is not None and tp > tpth: continue
if rp > fpth: continue # or fisher > fspth
minp = rp
if tp is not None and tp < minp: minp = tp
if minp > minpth: continue
fsp, fss = stat.fisher_method([tp, rp]) #
if fsp > fspth: continue
has_stop = tsq[stop - 3:stop] in orf.cstop
e = getResult(t, tis, stop, cds1, cds2, tsq,
[ip, ttis.cnts[tis], tp, rp, 'N', fsp], has_stop)
es.append(e)
else: #all possible ORFs
orfs = orf.orflist(tsq, minaalen=minaalen, tail=tl)
for o in orfs:
starts = o.starts
if alt: starts += o.altstarts
starts.sort()
if longest and not has_tis: starts = starts[0:1]
ol = len(starts)
if ol == 0: continue
tps = [None] * ol
rps = [1] * ol
if has_tis:
allz_tis = max(
ttis.cnts[starts[0]:o.stop:3]) == 0 # all zeros
else:
allz_tis = True
allz_ribo = max(
tribo.cnts[starts[0]:o.stop:3]) == 0 # all zeros
if allz_tis and allz_ribo: continue
for i, tis in enumerate(starts):
if has_tis:
tps[i] = ttis.tis_test(tis, paras[ip][0], paras[ip][1])
if not allz_ribo:
allz_ribo = max(tribo.cnts[tis:o.stop:3]) == 0
if not allz_ribo:
if enrichtest: rps[i] = tribo.enrich_test(tis, o.stop)
else: rps[i] = tribo.frame_test(tis, o.stop)
rst = pvalStatus(rps)
for i, tis in enumerate(starts):
if tps[i] is not None and tps[i] > tpth: continue
if rps[i] > fpth: continue # or fishers[i] > fspth
minp = rps[i]
if tps[i] is not None and tps[i] < minp: minp = tps[i]
if minp > minpth: continue
if tps[i] is None or tps[i] > minpth:
if longest:
if i > 0: continue
else:
if framelocalbest and rst[i] == 'N': continue
if framebest and rst[i][0] != 'T': continue
fsp, fss = stat.fisher_method([tps[i], rps[i]]) #
if fsp > fspth: continue
e = getResult(
t, tis, o.stop, cds1, cds2, tsq,
[ip, ttis.cnts[tis], tps[i], rps[i], rst[i], fsp],
o.has_stop_codon)
#tistype = tisType(tis, o.stop, cds1, cds2)
#orfstr = '{}\t{}\t{}'.format(tsq[tis:tis+3],tis,o.stop)
#tid = "%s\t%s\t%s\t%s\t%s:%d-%d:%s\t%s\t%s" % (t.gid, t.id, t.symbol, t.genetype, t.chr, t.genome_pos(tis), t.genome_pos(o.stop), t.strand, orfstr, tistype)
#values = [ip, ttis.cnts[tis], tps[i], rps[i], rst[i]] # , fishers[i]]
#e = exp.Exp(tid, values)
#e.length = (o.stop - tis) / 3 - 1
#e.sq = tsq[tis:o.stop]
#e.chr, e.strand, e.tistype = t.chr, t.strand, tistype
#if e.tistype == 'Extended' : e.cr = interval.cds_region_trans(t, tis, tis+3)
#else : e.cr = interval.cds_region_trans(t, tis, o.stop)
es.append(e)
#if has_tis :
j[1] += ol
j[0] += 1
return es, j, tpfs, g
def run(args):
'''Main function for differential TIS
'''
global ipth, iqth, tis1bampaths, tis2bampaths, tis1offdict, tis2offdict, compatible, compatiblemis, paired
ipth, iqth = args.ipth, args.iqth
tis1bampaths = args.tis1bampaths
tis2bampaths = args.tis2bampaths
ribo.maxNH, ribo.minMapQ, ribo.secondary = args.maxNH, args.minMapQ, args.secondary
compatible = not args.nocompatible
compatiblemis = args.compatiblemis
paired = args.paired
if len(tis1bampaths) < len(args.tis1paths) or len(tis2bampaths) < len(
args.tis2paths): # == 0 :
print('Missing bam file input!')
exit(1)
if args.chrmap is not None:
chrmap = {}
for lst in io.splitIter(args.chrmap):
chrmap[lst[0]] = lst[1]
chrmap[lst[1]] = lst[0]
bam.chrmap = chrmap
fa.chrmap = chrmap
global tis1bampathslist, tis2bampathslist, tis1offdictlist, tis2offdictlist
tis1bampathslist = [s.split(';') for s in args.tis1bampaths]
tis2bampathslist = [s.split(';') for s in args.tis2bampaths]
if args.tis1para is None: tis1paralist = [None] * len(args.tis1paths)
else: tis1paralist = [s.split(';') for s in args.tis1para]
if args.tis2para is None: tis2paralist = [None] * len(args.tis2paths)
else: tis2paralist = [s.split(';') for s in args.tis2para]
tis1offdictlist = [
find_offset(bampaths, para)
for bampaths, para in zip(tis1bampathslist, tis1paralist)
]
tis2offdictlist = [
find_offset(bampaths, para)
for bampaths, para in zip(tis2bampathslist, tis2paralist)
]
if len(args.tis1labels) < len(args.tis1paths):
for i in range(len(args.tis1labels), len(args.tis1paths)):
args.tis1labels.append(args.tis1paths[i])
if len(args.tis2labels) < len(args.tis2paths):
for i in range(len(args.tis2labels), len(args.tis2paths)):
args.tis2labels.append(args.tis2paths[i])
title = args.tis1labels + args.tis2labels
tis_title = ['TIS_' + lab for lab in title]
rna_title = ['RNA_' + lab for lab in title]
l = len(title)
if args.rnaseq is not None:
if args.verbose: print("Loading RNASeq data...")
rna_profile = exp.Profile()
for lst in io.splitIter(args.rnaseq):
try:
values = map(int, lst[1:])
except:
try:
values = map(float, lst[1:])
print('Error: RNASeq data should be integers {}.'.format(
lst))
sys.exit(1)
except ValueError:
pass
continue
m = min(values)
if m < 0:
print('Error: RNASeq data should be non-negative integers {}.'.
format(lst))
sys.exit(1)
e = exp.Exp(lst[0], values)
rna_profile.add_exp(e)
if args.verbose: print("{} genes.".format(len(rna_profile)))
if args.verbose: print("Loading {} TIS data...".format(l))
gname, gpos, gsig = {}, {}, {}
tall = [] # {}, {}
gid = {}
anno = {} # annotated TIS
for i, fname in enumerate(args.tis1paths + args.tis2paths):
n = 0
tdata = {}
for lst in io.splitIter(fname):
try:
tis = (lst[1], int(lst[6]))
except:
continue
gid[lst[1]] = lst[0]
cnt, pval, qval = int(lst[10]), float(lst[11]), float(lst[args.qi])
tdata[tis] = cnt, pval, qval
lst[4] = get_tis(lst[4])
if lst[8] == 'Annotated': anno[lst[4]] = 1 # genome position
if sig(tdata[tis]):
n += 1
#lst[4] = get_tis(lst[4])
gname[tis] = '\t'.join(lst[:9]) # information for the TIS
gpos[tis] = lst[4]
if tis not in gsig: gsig[tis] = [0] * len(tis_title)
gsig[tis][i] = 1
if args.verbose: print("{} TISs in {}.".format(n, fname))
tall.append(tdata)
profile = exp.Profile()
profile2 = exp.Profile() # uniq TISs for TMM
trans_for_bam = {} # TIS genes need to be analyzed
es = {}
uniq_gpos = {}
for tis in gname: # t1 :
values = []
for i, tdata in enumerate(tall):
if tis not in tdata:
if tis[0] not in trans_for_bam:
trans_for_bam[tis[0]] = [{} for j in range(l)]
trans_for_bam[tis[0]][i][tis[1]] = None
values.append(None)
else:
values.append(tdata[tis][0])
if args.rnaseq is not None:
if tis[0] in rna_profile.exps:
values += rna_profile.exps[tis[0]].data # trans level
elif gid[tis[0]] in rna_profile.exps:
values += rna_profile.exps[gid[tis[0]]].data # gene level
else:
print('Warning: transcript {} {} is not found in RNA file!'.
format(gid[tis[0]], tis[0]))
values += [0] * l # len(title)
e = exp.Exp(gname[tis], values)
e.tis = tis
es[tis] = e
profile.add_exp(e)
if gpos[tis] not in uniq_gpos:
if args.normanno and gpos[tis] not in anno: continue
if args.normcomm:
for tdata in tall:
if tis not in tdata or not sig(tdata[tis]): break
else: profile2.add_exp(e)
#elif args.normanno :
#if gpos[tis] in anno : profile2.add_exp(e)
else:
profile2.add_exp(e)
uniq_gpos[gpos[tis]] = 1
if args.verbose: print("{} TISs in total.".format(len(profile)))
if not args.normcomm:
uns = [0] * len(tis_title)
for i in range(len(tis_title)):
uns[i] = len([i for e in profile2 if gsig[e.tis][i] == 1])
m = min(uns)
elst = list(profile2.exps.values())
profile3 = exp.Profile()
for i in range(len(tis_title)):
for e in elst:
e.value[0:2] = [gsig[e.tis][i], e.data[i]]
elst.sort(reverse=True)
for j in range(m):
if elst[j].id not in profile3.exps: profile3.add_exp(elst[j])
profile2 = profile3
if args.verbose: print("Reading bams...")
trans_iter = io.transIter(args.genepath,
fileType=args.geneformat,
verbose=args.verbose,
filt=trans_for_bam)
para_iter = transPara(trans_iter, trans_for_bam)
if args.numProc <= 1: pred_iter = itertools.imap(_get_tis, para_iter)
else:
from multiprocessing import Pool
pool = Pool(processes=args.numProc - 1)
pred_iter = pool.imap_unordered(_get_tis, para_iter, chunksize=5)
for result in pred_iter:
tid, pos_cnt = result # r1, r2 = result
for i, pc in enumerate(pos_cnt):
for pos in pc:
tis = tid, pos
es[tis].data[i] = pc[pos]
if len(args.tis1paths) > 1 or len(
args.tis2paths) > 1 or args.export is not None:
if args.export is None: args.export = 'tisdiff_export.txt'
if args.verbose:
print('Export TIS counts table to {}.'.format(args.export))
exfile = open(args.export, 'w')
if args.rnaseq is None:
exfile.write(io.tabjoin('TIS', tis_title) +
'\n') # args.tis1labels, args.tis2labels)+'\n')
else:
exfile.write(io.tabjoin('TIS', tis_title, rna_title) + '\n')
for tis in gname:
s = '{}_{}_{}\t'.format(tis[0], tis[1], gpos[tis])
s += io.tabjoin(es[tis].data)
exfile.write(s + '\n')
return
if args.scalefactor is not None: scale = args.scalefactor
else:
if args.verbose: print('Estimate scale factor...')
f = profile2.TMM(i1=0, i2=1)
if args.verbose: print('TIS TMM log2 f = {}'.format(f))
scale = 2**(-f)
if args.rnaseq is not None:
if args.rnascale is not None: scale_r = args.rnascale
else:
fr = rna_profile.TMM(i1=0, i2=1) # for only one replicate
if args.verbose: print('RNASeq TMM log2 f = {}'.format(fr))
scale_r = 2**(-fr)
if args.verbose: print('Diff test...')
exps = profile.exps.values()
for e in exps:
if args.rnaseq is None:
p = 1 / (scale + 1)
x, y = e.data[0], e.data[1] # [2]
n = x + y
if x == 0: fc, alt = 'INF', 'less'
elif y == 0: fc, alt = 0, 'greater'
else:
fc = y / (1.0 * x * scale) # / y
if scale * x <= y: alt = 'less'
else: alt = 'greater'
pv = stat.binom_test(n, x, p=p, alt=alt)
else:
x, y, r1, r2 = e.data[0:4]
if x == 0: fc, alt = 'INF', 'less'
elif y == 0 or r1 == 0: fc, alt = 0, 'greater'
elif r2 == 0: fc, alt = 'INF', 'less'
else:
fc = y / (1.0 * x * scale) / (r2 / (1.0 * r1 * scale_r))
if fc >= 1: alt = 'less' # test x
else: alt = 'greater'
if args.chi2:
pv = ribo.TIStest_chi2(x, y, r1, r2, scale, scale_r, alt=alt)
elif args.betabinom:
pv = ribo.TIStest_betaBinom(x,
y,
r1,
r2,
scale,
scale_r,
alt=alt)
else:
pv = ribo.TIStest_FisherExact(x,
y,
r1,
r2,
scale,
scale_r,
alt=alt)
pv *= 2 # two tailed
if pv > 1: pv = 1
e.data.append(fc)
e.data.append(pv)
result = profile.BHcorrection(-1, append=True) # (5)
if args.verbose: print('Output...')
outfile = open(args.output, 'w')
s = "Gid\tTid\tSymbol\tGeneType\tGenomePos\tStartCodon\tStart\tStop\tTisType\t"
s += '\t'.join(tis_title)
if args.rnaseq is not None: s += '\t' + '\t'.join(rna_title)
s += '\tFoldChange\tDiffPvalue\tDiffQvalue\n'
outfile.write(s)
for e in profile:
fc = e.data[-3]
e.is_q = e.is_fc = True
if fc != 'INF' and fc != 0 and max(fc, 1 / fc) < args.foldchange:
e.is_fc = False
if e.data[-2] > args.opth or e.data[-1] > args.oqth:
e.is_q = False
if e.is_q and e.is_fc:
outfile.write(str(e) + '\n')
# Plot
if args.plotout is not None:
if args.verbose: print("Ploting...")
from zbio import plot
plot.figure(figsize=args.figsize)
if args.rnaseq is not None:
qd1 = [
math.log(e.data[0] + 1, 2) - math.log(e.data[2] + 1, 2)
for e in exps if e.is_q and e.is_fc
]
qd2 = [
math.log(e.data[1] + 1, 2) - math.log(e.data[3] + 1, 2)
for e in exps if e.is_q and e.is_fc
]
pd1 = [
math.log(e.data[0] + 1, 2) - math.log(e.data[2] + 1, 2)
for e in exps if e.is_q and not e.is_fc
]
pd2 = [
math.log(e.data[1] + 1, 2) - math.log(e.data[3] + 1, 2)
for e in exps if e.is_q and not e.is_fc
]
nd1 = [
math.log(e.data[0] + 1, 2) - math.log(e.data[2] + 1, 2)
for e in exps if not e.is_q
]
nd2 = [
math.log(e.data[1] + 1, 2) - math.log(e.data[3] + 1, 2)
for e in exps if not e.is_q
]
else:
qd1 = [
math.log(e.data[0] + 1, 2) for e in exps if e.is_q and e.is_fc
]
qd2 = [
math.log(e.data[1] + 1, 2) for e in exps if e.is_q and e.is_fc
]
pd1 = [
math.log(e.data[0] + 1, 2) for e in exps
if e.is_q and not e.is_fc
]
pd2 = [
math.log(e.data[1] + 1, 2) for e in exps
if e.is_q and not e.is_fc
]
nd1 = [math.log(e.data[0] + 1, 2) for e in exps if not e.is_q]
nd2 = [math.log(e.data[1] + 1, 2) for e in exps if not e.is_q]
plot.scatter(qd1,
qd2,
alpha=0.1,
edgecolors='none',
color='r',
label='q < {} & FC > {}'.format(args.oqth,
args.foldchange))
plot.scatter(pd1,
pd2,
alpha=0.1,
edgecolors='none',
color='y',
label='q < {} & FC <= {}'.format(args.oqth,
args.foldchange))
plot.scatter(nd1,
nd2,
alpha=0.1,
edgecolors='none',
color='g',
label='q >= {}'.format(args.oqth))
plot.legend(loc='upper left', frameon=False)
plot.xlabel(title[0])
plot.ylabel(title[1])
if args.rnaseq is not None: d = (fr - f) / 2
else: d = -f / 2
m1 = max(min(qd1 + pd1 + nd1), min(qd2 + pd2 + nd2))
m2 = min(max(qd1 + pd1 + nd1), max(qd2 + pd2 + nd2))
plot.plot([m1 - d, m2 - d], [m1 + d, m2 + d], color='k', linestyle=':')
d2 = d - math.log(args.foldchange, 2) / 2
plot.plot([m1 - d2, m2 - d2], [m1 + d2, m2 + d2],
color='r',
linestyle=':')
d2 = d + math.log(args.foldchange, 2) / 2
plot.plot([m1 - d2, m2 - d2], [m1 + d2, m2 + d2],
color='r',
linestyle=':')
plot.save(args.plotout)
if args.plotma is not None:
exps = profile2.exps.values()
plot.figure(figsize=args.figsize)
plot.axhline(f)
ms = [e.M for e in exps if hasattr(e, 'select') and e.select]
aa = [e.A for e in exps if hasattr(e, 'select') and e.select]
plot.scatter(aa, ms, alpha=0.1, edgecolors='none', color='r')
ms = [e.M for e in exps if hasattr(e, 'select') and not e.select]
aa = [e.A for e in exps if hasattr(e, 'select') and not e.select]
plot.scatter(aa, ms, alpha=0.1, edgecolors='none', color='b')
plot.save(args.plotma)
def run(args):
'''Main function for ORF finding
'''
# prepare
global tisbampaths, tisoffdict, ribobampaths, riboffdict, genomefapath, compatible, compatiblemis
global minaalen, enrichtest, slp, paras, verbose, alt, title, tis2ribo, gfilter
global tpth, fpth, minpth, fspth, framebest, framelocalbest, longest, transprofile, TIS_types #fspth
global paired, seq, aaseq, blocks # showtime
paired, seq, aaseq, blocks = args.paired, args.seq, args.aaseq, args.blocks
ribo.maxNH, ribo.minMapQ, ribo.secondary = args.maxNH, args.minMapQ, args.secondary
tisbampaths = args.tisbampaths
ribobampaths = args.ribobampaths
if len(tisbampaths) == 0 and len(ribobampaths) == 0:
print('No bam file input!')
exit(1)
genomefapath = args.genomefapath
compatible = not args.nocompatible
compatiblemis = args.compatiblemis
minaalen = args.minaalen
enrichtest = args.enrichtest
transprofile = args.transprofile
harrwidth = None
TIS_types = [
'Annotated', 'Truncated', 'Extended', "5'UTR", "3'UTR", 'Internal',
'Novel'
]
if args.chrmap is not None:
chrmap = {}
for lst in io.splitIter(args.chrmap):
chrmap[lst[0]] = lst[1]
chrmap[lst[1]] = lst[0]
bam.chrmap = chrmap
fa.chrmap = chrmap
if args.harrwidth is not None: harrwidth = args.harrwidth
elif args.harr: harrwidth = 15
verbose = args.verbose
alt = args.alt
if args.altcodons is not None:
alt = True
if args.altcodons[0].upper() == 'ALL': orf.cstartlike = orf.allcodons
else: orf.cstartlike = [c.upper() for c in args.altcodons]
tpth, fpth, minpth, framebest, framelocalbest = args.tpth, args.fpth, args.minpth, args.framebest, args.framelocalbest # fspth
fspth = args.fspth
longest = args.longest
tis2ribo = args.tis2ribo
parts = [0.1 * (i + 1) for i in range(args.nparts)]
gfilter = None
if args.genefilter is not None:
gfilter = {}
for gid in args.genefilter:
gfilter[gid] = 1
flank = 3 ##
tisoffdict = find_offset(args.tisbampaths, args.tispara)
riboffdict = find_offset(args.ribobampaths, args.ribopara)
if len(args.ribobampaths) == 0:
print(
'No regular RiboSeq data input. TIS data will also be used as regular RiboSeq data.'
)
tis2ribo = True
if len(args.tisbampaths) == 1:
if args.inestpath is None:
path = args.tisbampaths[0] + '.bgest.txt'
if isfile(path): args.inestpath = path
else: args.estpath = path
if args.agenepath is None: args.agenepath = args.genepath
# load genome, fasta file indexing
if args.verbose: print("{} Loading genome...".format(time.ctime()))
genome = fa.Fa(args.genomefapath, verbose=args.verbose)
# TIS background estimation
if len(args.tisbampaths) == 0:
print('No input TIS data!')
paras, slp = [(1, 0.5)], [1] # No TIS input
elif args.inestpath is None: #== '' :
print("{} Estimating TIS background parameters...".format(
time.ctime()))
if args.verbose:
print(
"TIS background estimation result will be saved to {}".format(
args.estpath))
if args.numProc > 1:
from multiprocessing import Process
import multiprocessing.pool
class NoDaemonProcess(Process):
# make 'daemon' attribute always return False
def _get_daemon(self):
return False
def _set_daemon(self, value):
pass
daemon = property(_get_daemon, _set_daemon)
class MyPool(multiprocessing.pool.Pool):
Process = NoDaemonProcess
pool = MyPool(1) # This is for memory efficiency
paras, slp, data = pool.apply(ribo.estimateTISbg,
args=(args.agenepath,
args.tisbampaths,
args.genomefapath),
kwds={
'parts': parts,
'offdict': tisoffdict,
'numProc': args.numProc,
'verbose': args.verbose,
'geneformat': args.geneformat,
'harrwidth': harrwidth,
'paired': paired
})
pool.close()
else:
paras, slp, data = ribo.estimateTISbg(args.genepath,
args.tisbampaths,
args.genomefapath,
parts=parts,
offdict=tisoffdict,
numProc=1,
verbose=verbose,
geneformat=args.geneformat,
harrwidth=harrwidth,
paired=paired)
estfile = open(args.estpath, 'w')
for i in range(len(parts)):
estfile.write("{}\t{}\t{}\t{}\t{}\n".format(
paras[i][0], paras[i][1], parts[i], slp[i], data[i]))
estfile.close()
else:
inestfile = open(args.inestpath, 'r')
paras, slp = [], []
for l in inestfile:
lst = l.strip().split('\t')
paras.append((float(lst[0]), float(lst[1])))
slp.append(eval(lst[3]))
if args.inprofile is not None and not isfile(args.inprofile):
print('inprofile {} not found!'.format(args.inprofile))
if args.transprofile is None:
transprofile = args.inprofile
if args.numProc > 1:
from multiprocessing import Pool
pool = Pool(processes=args.numProc - 1)
cds_regions = {}
known_tis = {}
if args.agenepath != args.genepath:
if verbose: print('Loading CDS annotation...')
for g in io.geneIter(args.agenepath,
fileType=args.geneformat,
chrs=genome.idx,
verbose=args.verbose):
if g.chr not in cds_regions:
cds_regions[g.chr] = {
'+': [interval.Interval() for i in range(3)],
'-': [interval.Interval() for i in range(3)]
}
known_tis[g.chr] = {'+': {}, '-': {}}
for t in g.trans:
cr = interval.cds_region_trans(t)
for i in range(3):
cds_regions[t.chr][t.strand][i].lst += cr[i].lst
#for t in g.trans :
tis = t.cds_start(cdna=False)
if tis is not None: known_tis[t.chr][t.strand][tis] = 1
inorf = None
if args.input is not None:
if verbose: print('Loading candidates...')
inorf = {}
infile = open(args.input, 'r')
for l in infile:
lst = l.strip().split()
tid, tis, stop = lst[0], int(lst[1]), int(lst[2])
#if gfilter is not None and tid not in gfilter : continue
if tid not in inorf: inorf[tid] = []
inorf[tid].append([tis, stop])
inprofile = None
if args.inprofile is not None:
if isfile(args.inprofile):
if verbose: print('Loading transcript profile...')
inprofile = {}
for lst in io.splitIter(args.inprofile):
try:
gid, tid, tispf, ribopf = lst[0], lst[1], eval(
lst[3]), eval(lst[4])
except:
continue
if gid not in inprofile: inprofile[gid] = {}
inprofile[gid][tid] = tispf, ribopf
print("{} Predicting...".format(time.ctime()))
profile = exp.Profile()
title = ['TISGroup', 'TISCounts', 'TISPvalue', 'RiboPvalue', 'RiboPStatus']
j = [0, 0] # total number of ORF/TIS for BH correction
gene_iter = io.geneIter(args.genepath,
fileType=args.geneformat,
chrs=genome.idx,
verbose=args.verbose)
para_iter = genePara(gene_iter, inorf, inprofile)
if args.numProc <= 1: pred_iter = itertools.imap(_pred_gene, para_iter)
else:
#from multiprocessing import Pool
#pool = Pool(processes = args.numProc - 1)
pred_iter = pool.imap_unordered(_pred_gene, para_iter, chunksize=5)
if transprofile is not None:
tpfile = open(transprofile, 'w')
tpfile.write('Gid\tTid\tSymbol\tTISProf\tRiboProf\n')
for result in pred_iter:
es, ji, tpfs, g = result
j[0] += ji[0]
j[1] += ji[1]
for e in es:
profile.add_exp(e)
if verbose >= 2: print('{} {}'.format(time.ctime(), str(e)))
if transprofile is not None:
for tid in tpfs:
tpfile.write(io.tabjoin(tid, tpfs[tid]) + '\n')
if g.chr not in cds_regions:
cds_regions[g.chr] = {
'+': [interval.Interval() for i in range(3)],
'-': [interval.Interval() for i in range(3)]
}
known_tis[g.chr] = {'+': {}, '-': {}}
for t in g.trans:
cr = interval.cds_region_trans(t)
for i in range(3):
cds_regions[t.chr][t.strand][i].lst += cr[i].lst
#for t in g.trans :
tis = t.cds_start(cdna=False)
if tis is not None: known_tis[t.chr][t.strand][tis] = 1
for chr in cds_regions:
for strand in cds_regions[chr]:
for i in range(3):
cds_regions[chr][strand][i].check()
print("{} Checking overlap with known CDS..".format(time.ctime()))
for e in profile:
if e.tistype == 0: continue
elif e.gtis in known_tis[e.chr][e.strand]: e.id += ':Known'
elif e.tistype > 1: # ["5'UTR", "3'UTR", "Inside", "Novel", 'Extended'] :
#coding_overlap = False
for i in range(3):
its = cds_regions[e.chr][e.strand][i].intersect(
e.cr[i]
) # e.cr[i].intersect(cds_regions[e.chr][e.strand][i])
if its.rlen() > 0:
#coding_overlap = True
e.id += ':CDSFrameOverlap'
break
print("{} BH correcting...".format(time.ctime()))
profile.BHcorrection(2, total=j[1],
append=True) # Calculate BH FDR of TIS p value
profile.BHcorrection(3, total=j[0], append=True) # Frame p value
i = 1
if len(tisbampaths) == 0: i = 0
profile.BHcorrection(5, total=j[i],
append=True) # Calculate BH FDR for Fisher's p value
outfile = open(args.output, 'w')
s = "Gid\tTid\tSymbol\tGeneType\tGenomePos\tStartCodon\tStart\tStop\tTisType\t"
s += '\t'.join(title)
s += '\tFisherPvalue\tTISQvalue\tFrameQvalue\tFisherQvalue\tAALen'
if seq: s += '\tSeq'
if aaseq: s += '\tAASeq'
if blocks: s += '\tBlocks'
s += '\n'
outfile.write(s)
if args.allresult is not None and args.allresult.upper() == 'OFF':
allout = None
elif args.fsqth == 1:
allout = None
else:
if args.allresult is None:
lst = args.output.split('.')
if lst[-1] == 'txt': args.allresult = args.output[:-4] + '_all.txt'
else: args.allresult = args.output + '_all.txt'
allout = open(args.allresult, 'w')
allout.write(s)
for e in profile:
#if e.q > args.fsqth : continue
if len(tisbampaths) == 0:
e.data[5], e.data[8] = None, None # No Fisher's
s = "%s\t%d" % (e, e.length)
if seq: s += '\t' + e.sq
if aaseq: s += '\t' + e.aa
if blocks: s += '\t' + e.blocks
s += '\n'
if allout is not None: allout.write(s)
if e.q <= args.fsqth:
outfile.write(s) # "%s\t%d\n" % (e, e.length)) #, e.sq))