def initialize_containers(args):
scaffold_tp_fp = {}
true_breakpoints = {}
for acc, scf in fasta_iter(open(args.scafs, 'r')):
scaffold_tp_fp[acc] = [0, 0]
true_breakpoints[acc] = set()
return true_breakpoints, scaffold_tp_fp
def initialize_containers(args):
scaffold_tp_fp = {}
true_breakpoints = {}
for acc, scf in fasta_iter(open(args.scafs, 'r')):
scaffold_tp_fp[acc] = [0,0]
true_breakpoints[acc] = set()
return true_breakpoints, scaffold_tp_fp
def main(args):
if not os.path.exists(args.folder_path):
os.mkdir(args.folder_path)
for acc, seq in fasta.fasta_iter(open(args.genome, 'r')):
accession, genome = acc, seq
break
#print seq
dist = DistanceContainer()
dist.parse_genome(seq, args.k)
dist.plot()
def main(args): if not os.path.exists(args.folder_path): os.mkdir(args.folder_path) for acc, seq in fasta.fasta_iter(open(args.genome,'r')): accession,genome = acc, seq break #print seq dist = DistanceContainer() dist.parse_genome(seq,args.k) dist.plot()
def simulate_instance(args):
#print 'Started simulating'
if not os.path.exists(args.output_path):
os.makedirs(args.output_path)
if not args.contigs:
genome_path = os.path.join(args.output_path, 'genome.fa')
contig_path = os.path.join(args.output_path, 'ctgs.fa')
else:
genome_path = args.genome
contig_path = args.contigs
read1_path = os.path.join(args.output_path, 'reads1.fa')
read2_path = os.path.join(args.output_path, 'reads2.fa')
bam_path = os.path.join(args.output_path, 'mapped')
if not args.contigs:
#genome
#print args.genomelen
g = genome.Genome([0.25]*4,args.genomelen,'genome1')
g.genome()
print >> open(genome_path,'w'), g.genome_fasta_format()
#contigs
ctgs = open(contig_path,'w')
ctg_list = [x for x in contigs.generate_contigs(g.sequence,args.min_contig, args.max_contig, 0,3000)]
random.shuffle( ctg_list )
for ctg in ctg_list:
ctgs.write(ctg)
else:
g = genome.Genome([0.25]*4,args.genomelen,'genome1')
#print genome_path, args.genomelen
longest_seq = 0
for acc,seq in fasta.fasta_iter(open(genome_path,'r')):
print acc, len(seq)
if len(seq) > longest_seq:
g.sequence = seq
g.accession = acc
longest_seq = len(seq)
print 'chosen:',g.accession
#ctgs.write('>ctg0\n{0}\n'.format(g.sequence[0:args.burnin]))
#for i,x in enumerate(range(args.burnin,args.genomelen,(args.contiglen + args.gaplen))):
# ctgs.write('>ctg{0}\n{1}\n'.format(i+1,g.sequence[x:x+args.contiglen]))
#reads
if args.distr == 'normal':
lib = reads.DNAseq(args.read_length ,args.coverage, distribution=args.distr, mean=args.mean,stddev=args.sd)
lib.simulate_pe_reads(g)
elif args.distr == 'uniform':
lib = reads.DNAseq(args.read_length ,args.coverage, distribution=args.distr, min_size=args.min_size,max_size=args.max_size)
lib.simulate_pe_reads(g)
elif args.distr == 'mix':
lib_part1 = reads.DNAseq(args.read_length ,args.coverage/2, distribution='normal', mean=args.mean,stddev=args.sd)
lib_part1.simulate_pe_reads(g)
lib_part2 = reads.DNAseq(args.read_length ,args.coverage/2, distribution='uniform', min_size=(args.mean - 4*args.sd),max_size=(args.mean + 4*args.sd))
lib_part2.simulate_pe_reads(g)
# concatenate the reads from each distribution
lib = reads.DNAseq(args.read_length ,args.coverage, distribution=args.distr, mean=args.mean,stddev=args.sd)
lib.reads = lib_part1.reads + lib_part2.reads
reads1 = open(read1_path,'w')
reads2 = open(read2_path,'w')
i=0
for read in lib.fasta_format():
if i%2==0:
reads1.write(read)
else:
reads2.write(read)
i+=1
#print 'Started mapping'
#mapping
#align.map_paired_reads(read1_path, read2_path, contig_path, bam_path, args)
align.bwa_mem(read1_path, read2_path, genome_path, bam_path, args)
