def trim_additional_merged_contigs(original_contig, merged_contig):
open_merged = open(merged_contig)
fasta_reader = FastaReader(open_merged)
header, sequence = fasta_reader.next()
sp_header = header.split('_')
trim = int(sp_header[-2].strip('os'))
cigar = sp_header[-1]
all_cigar = re.findall('(\d+)([MXDI])', cigar)
for count, type in all_cigar:
if type == "M" or type == "X":
trim += int(count)
open_merged.close()
if trim > 50:
logging.info("trim %s of %s" % (trim, original_contig))
open_contig = open(original_contig)
fasta_reader = FastaReader(open_contig)
header, sequence, fasta_reader.next()
header = header + "trim_%s" % trim
sequence = sequence[trim:]
open_contig.close()
open_contig = open(original_contig, 'w')
if len(sequence) > 100:
open_contig.write(">%s\n%s\n" % (header, sequence))
open_contig.close()
def trim_additional_merged_contigs(original_contig, merged_contig):
open_merged=open(merged_contig)
fasta_reader=FastaReader(open_merged)
header, sequence = fasta_reader.next()
sp_header = header.split('_')
trim=int(sp_header[-2].strip('os'))
cigar=sp_header[-1]
all_cigar = re.findall('(\d+)([MXDI])', cigar)
for count, type in all_cigar:
if type=="M" or type=="X":
trim+=int(count)
open_merged.close()
if trim>50:
logging.info("trim %s of %s"%(trim, original_contig))
open_contig=open(original_contig)
fasta_reader=FastaReader(open_contig)
header, sequence,fasta_reader.next()
header=header+"trim_%s"%trim
sequence=sequence[trim:]
open_contig.close()
open_contig=open(original_contig, 'w')
if len(sequence)>100:
open_contig.write(">%s\n%s\n"%(header,sequence))
open_contig.close()
def get_fasta_length(fasta_file):
length = 0
with open(fasta_file) as open_fasta:
reader = FastaReader(open_fasta)
header, sequence = reader.next()
length = len(sequence)
return length
def get_fasta_length(fasta_file):
length=0
with open(fasta_file) as open_fasta:
reader = FastaReader(open_fasta)
header,sequence = reader.next()
length=len(sequence)
return length
def force_merge_consensus(read1_consensus, read2_consensus, output_merge_file):
open_output = open(output_merge_file, 'w')
open_read1 = open(read1_consensus)
open_read2 = open(read2_consensus)
fasta_reader1 = FastaReader(open_read1)
read1_name, read1_sequence = fasta_reader1.next()
open_read1.close()
name = "%s_forced_merged" % read1_name
array = [read1_sequence]
fasta_reader2 = FastaReader(open_read2)
for read2_name, read2_sequence in fasta_reader2:
name = "%s_%s" % (name, read2_name)
array.append("N" * 100)
array.append(read2_sequence)
open_output.write(">%s\n%s\n" % (name, ''.join(array)))
open_read2.close()
open_output.close()
def force_merge_consensus(read1_consensus, read2_consensus, output_merge_file):
open_output = open(output_merge_file,'w')
open_read1 = open(read1_consensus)
open_read2 = open(read2_consensus)
fasta_reader1 = FastaReader(open_read1)
read1_name, read1_sequence = fasta_reader1.next()
open_read1.close()
name="%s_forced_merged"%read1_name
array=[read1_sequence]
fasta_reader2 = FastaReader(open_read2)
for read2_name, read2_sequence in fasta_reader2:
name="%s_%s"%(name,read2_name)
array.append("N"*100)
array.append(read2_sequence)
open_output.write(">%s\n%s\n"%(name, ''.join(array)))
open_read2.close()
open_output.close()
class GenomeLoader:
"""Genome Loader take a fasta file and try to find a given chromosome in it.
You can specify so it also keep the all the loaded unused chromosome into memory until they are required (keep_in_memory=True).
You can also specify so it keep the all the loaded chromosome until the object is destroyed (keep_until_done=True).
You can provide a prefix that will be added to the chromsome names if not already there.
"""
def __init__(self,
genome_file,
keep_in_memory=True,
keep_until_done=False,
prefix=''):
self.open_genome_file = open_input_file(genome_file)
self.reader = FastaReader(self.open_genome_file)
self.keep_in_memory = keep_in_memory
self.keep_until_done = keep_until_done
self.prefix = prefix
self.all_chr = {}
def load_all(self):
self.get_chr('***********************************************')
return self.all_chr.keys()
def get_chr(self, chr):
if not chr.startswith(self.prefix):
chr = self.prefix + chr
if self.keep_until_done: #return if loaded already
fasta_seq = self.all_chr.get(chr)
else: #remove if loaded already
fasta_seq = self.all_chr.pop(chr, None)
if fasta_seq:
(header, seq) = fasta_seq
logging.debug('return %s' % header)
return fasta_seq
curr_chr = ''
seq = ''
while not curr_chr == chr:
fasta_seq = self.reader.next()
if fasta_seq:
(header, seq) = fasta_seq
logging.debug('load %s' % header)
curr_chr = header.split()[0]
if not curr_chr.startswith(self.prefix):
curr_chr = self.prefix + curr_chr
if (self.keep_in_memory
and not curr_chr == chr) or self.keep_until_done:
logging.debug('keep %s' % header)
self.all_chr[curr_chr] = fasta_seq
else:
break
return fasta_seq
def next(self):
fasta_seq = None
if len(self.all_chr) > 0:
chr = self.all_chr.keys[0]
if len(self.all_chr) > 0:
chr = self.all_chr.keys()[0]
if self.keep_until_done: #return if loaded already
fasta_seq = self.all_chr.get(chr)
else: #remove if loaded already
fasta_seq = self.all_chr.pop(chr, None)
if not fasta_seq:
fasta_seq = self.reader.next()
if fasta_seq:
(header, seq) = fasta_seq
curr_chr = header.split()[0]
logging.debug('load %s' % header)
if self.keep_until_done:
logging.debug('keep %s' % header)
self.all_chr[curr_chr] = fasta_seq
if fasta_seq:
logging.debug('return %s' % header)
return fasta_seq
return None
def __iter__(self):
return iter(self.next, None)
def __del__(self):
self.open_genome_file.close()
self.all_chr = None
def close(self):
self.__del__()
class GenomeLoader:
"""Genome Loader take a fasta file and try to find a given chromosome in it.
You can specify so it also keep the all the loaded unused chromosome into memory until they are required (keep_in_memory=True).
You can also specify so it keep the all the loaded chromosome until the object is destroyed (keep_until_done=True).
You can provide a prefix that will be added to the chromsome names if not already there.
"""
def __init__(self,genome_file, keep_in_memory=True, keep_until_done=False, prefix=''):
self.open_genome_file=open_input_file(genome_file)
self.reader=FastaReader(self.open_genome_file)
self.keep_in_memory=keep_in_memory
self.keep_until_done=keep_until_done
self.prefix=prefix
self.all_chr={}
def load_all(self):
self.get_chr('***********************************************')
return self.all_chr.keys()
def get_chr(self, chr):
if not chr.startswith(self.prefix):
chr=self.prefix+chr
if self.keep_until_done: #return if loaded already
fasta_seq=self.all_chr.get(chr)
else: #remove if loaded already
fasta_seq=self.all_chr.pop(chr,None)
if fasta_seq:
(header,seq)=fasta_seq
logging.debug('return %s'%header)
return fasta_seq
curr_chr=''
seq=''
while not curr_chr==chr:
fasta_seq=self.reader.next()
if fasta_seq:
(header,seq)=fasta_seq
logging.debug('load %s'%header)
curr_chr=header.split()[0]
if not curr_chr.startswith(self.prefix):
curr_chr=self.prefix+curr_chr
if (self.keep_in_memory and not curr_chr==chr) or self.keep_until_done:
logging.debug('keep %s'%header)
self.all_chr[curr_chr]=fasta_seq
else: break
return fasta_seq
def next(self):
fasta_seq=None
if len(self.all_chr)>0:
chr=self.all_chr.keys[0]
if len(self.all_chr)>0:
chr=self.all_chr.keys()[0]
if self.keep_until_done: #return if loaded already
fasta_seq=self.all_chr.get(chr)
else: #remove if loaded already
fasta_seq=self.all_chr.pop(chr,None)
if not fasta_seq:
fasta_seq=self.reader.next()
if fasta_seq:
(header,seq)=fasta_seq
curr_chr=header.split()[0]
logging.debug('load %s'%header)
if self.keep_until_done:
logging.debug('keep %s'%header)
self.all_chr[curr_chr]=fasta_seq
if fasta_seq:
logging.debug('return %s'%header)
return fasta_seq
return None
def __iter__(self):
return iter(self.next, None)
def __del__(self):
self.open_genome_file.close()
self.all_chr=None
def close(self):
self.__del__()
