def tmp_chrom_file(self, tmp_dir=None, genome=True, chrom=None):
make_dir(tmp_dir)
tmp_genome = tmp_dir + '{}.genome'.format(self.id)
tmpfh = open(tmp_genome, 'w')
if genome == True:
if chrom == None:
for ref in self.refs:
tmpfh.write('{}\t{}\n'.format(format_chrom(ref),
self.refs[ref]))
else:
tmpfh.write('{}\t{}\n'.format(format_chrom(chrom),
self.refs[chrom]))
if genome == False:
for ref in self.refs:
tmpfh.write('{}\t0\t{}\n'.format(format_chrom(ref),
self.refs[ref]))
tmpfh.close()
return tmp_genome
def main():
init_time = int(time())
parser = argparse.ArgumentParser(formatter_class=RawTextHelpFormatter,usage=splash.replace(" ","",1)+__useage___,add_help=False)
inArgs,genoArgs,optArgs = parser.add_argument_group('input arguments'),parser.add_argument_group('genotype arguments'),parser.add_argument_group('optional arguments')
inArgs.add_argument('-i','-bam',type=str,default=None,nargs='*')
inArgs.add_argument('-b','-bed',type=str,default=None,nargs='*')
inArgs.add_argument('-v','-vcf',type=str,default=None,nargs='*')
inArgs.add_argument('-snv',type=str,default=None,nargs='*')
inArgs.add_argument('-p','-ped',type=str,default=None,nargs='*')
genoArgs.add_argument('-g','-genome',required=False,default='hg19',type=str)
genoArgs.add_argument('-pcrfree',required=False,default=False,action="store_true")
genoArgs.add_argument('-M',default=False,required=False,action="store_true")
genoArgs.add_argument('-pre',required=False,default=None)
genoArgs.add_argument('-feats',required=False,default=None)
optArgs.add_argument('-L','-log',default=None,required=False)
optArgs.add_argument('-T','-tmp-dir',default=os.getcwd()+'/sv2_tmp_'+rand_id(),required=False)
optArgs.add_argument('-s','-seed',required=False,default=42,type=int)
optArgs.add_argument('-o','-out',required=False,default="sv2_training_features",type=str)
optArgs.add_argument('-O','-odir',required=False,default=os.getcwd(),type=str)
optArgs.add_argument('-h','-help',required=False,action="store_true",default=False)
args = parser.parse_args()
bams,bed,vcf,snv,ped = args.i,args.b,args.v,args.snv,args.p
gen,pcrfree,legacy_m,predir,featsdir= args.g,args.pcrfree,args.M,args.pre,args.feats
logfh, tmp_dir, seed, ofh, odir = args.L,args.T,args.s,args.o,args.O
_help = args.h
if (_help==True or len(sys.argv)==1):
print splash+__useage___
sys.exit(0)
if logfh!=None:
lfh = open(logfh,'w')
sys.stderr=lfh
preprocess_files,feats_files={},{}
gens = ['hg19','hg38','mm10']
olog = logfh
if olog == None: olog = 'STDOUT'
print 'sv2 version:{} report bugs to <dantaki at ucsd dot edu> error messages located in {}'.format(__version__,olog)
Confs=Config()
if bams==None and predir==None and featsdir==None:
print 'FATAL ERROR: No BAM file specified <-i, -bam FILE ...>'
sys.stderr.write('FATAL ERROR: No BAM file specified <-i, -bam FILE ...>\n')
sys.exit(1)
if snv==None and predir==None and featsdir==None:
print 'FATAL ERROR: No SNV VCF file specified <-snv FILE ...>'
sys.stderr.write('FATAL ERROR: No SNV VCF file specified <-snv FILE ...>\n')
sys.exit(1)
if ped==None:
print 'FATAL ERROR: No PED file specified <-p, -ped FILE ...>'
sys.stderr.write('FATAL ERROR: No PED file specified <-p, -ped FILE ...>\n')
sys.exit(1)
if bed==None and vcf==None:
print 'FATAL ERROR: No SVs provided <-b, -bed BED ...> <-v,-vcf VCF ...>'
sys.stderr.write('FATAL ERROR: No SVs provided <-b, -bed BED ...> <-v,-vcf VCF ...>\n')
sys.exit(1)
if gen not in gens:
print 'FATAL ERROR -g must be hg19 or hg38. NOT {}'.format(gen)
sys.stderr.write('FATAL ERROR -g must be hg19 or hg38. NOT {}\n'.format(gen))
sys.exit(1)
Peds=ped_init(ped)
if bams!=None: Bams=bam_init(bams,Peds,snv_init(snv),gen)
SV = sv_init(bed,vcf,gen)
ofh = ofh.replace('.vcf','').replace('.out','').replace('.txt','')
make_dir(tmp_dir)
tmp_dir=slash_check(tmp_dir)
if not odir.endswith('/'): odir = odir+'/'
make_dir(odir)
"""
PREPROCESSING
"""
if predir == None:
outdir = odir+'sv2_preprocessing/'
make_dir(outdir)
for bam in Bams:
preofh = outdir+bam.id+'_sv2_preprocessing.txt'
preprocess_files[bam.id]=preofh
preprocess(bam,preofh,seed,gen,tmp_dir)
else:
predir=slash_check(predir)
for fh in glob(predir+'*sv2_preprocessing.txt'):
f = open(fh)
if sum(1 for l in open(fh)) <= 1: continue
else:
preids=[]
for l in f:
if l.startswith('#'):continue
preids.append(l.rstrip('\n').split('\t').pop(0))
f.close()
for iid in set(preids):
if iid in Peds.ids : preprocess_files[iid]=fh
report_time(init_time,'PREPROCESSING COMPLETE')
""""
FEATURE EXTRACTION
"""
if featsdir == None:
outdir = odir+'sv2_features/'
make_dir(outdir)
for bam in Bams:
if preprocess_files.get(bam.id) == None:
sys.stderr.write('WARNING: BAM sample id {} not found in preprocessing files. Skipping ...\n'.format(bam.id))
continue
prefh = preprocess_files[bam.id]
featfh = outdir+bam.id+'_sv2_features.txt'
feats_files[bam.id]=featfh
extract_feats(bam,SV.raw,prefh,featfh,gen,pcrfree,legacy_m,Confs,tmp_dir)
else:
featsdir=slash_check(featsdir)
for fh in glob(featsdir+'*sv2_features.txt'):
f = open(fh)
if sum(1 for l in open(fh)) <= 1: continue
else:
featsid=[]
for l in f:
if l.startswith('#'):continue
featsid.append(l.rstrip('\n').split('\t').pop(5))
f.close()
for iid in set(featsid):
if iid in Peds.ids : feats_files[iid]=fh
feats=[]
train_dir = odir+'sv2_training_features/'
make_dir(train_dir)
for iid in feats_files:
with open(feats_files[iid]) as f:
for l in f: feats.append(tuple(l.rstrip('\n').split('\t')))
sv2_train_output(feats,Peds,gen,train_dir+ofh)
shutil.rmtree(tmp_dir)
lfh.close()
report_time(init_time,'FEATURE EXTRACTION COMPLETE')