def prepare_genome(genome_file,color_space=False):
run_fine=True
pipeline_param=utils_param.get_pipeline_parameters()
BWA_dir=pipeline_param.get_bwa_dir()
BWA_bin=os.path.join(BWA_dir,'bwa')
genome_loader = GenomeLoader(genome_file=genome_file)
length=0
for fasta_rec in genome_loader:
header, sequence = fasta_rec
length+=len(sequence)
if length>1000000000:
break
genome_loader.close()
#Following recommendation set the indexing algorithm to is if genome is <10M
if length>1000000000:
a_option='bwtsw'
else:
a_option='is'
#Create the indexes
if color_space:
command='%s index -c -a %s %s'%(BWA_bin, a_option, genome_file)
else:
command='%s index -a %s %s'%(BWA_bin, a_option, genome_file)
command_runner.run_command(command)
return run_fine
def prepare_genome(genome_file, color_space=False):
run_fine = True
pipeline_param = utils_param.get_pipeline_parameters()
BWA_dir = pipeline_param.get_bwa_dir()
BWA_bin = os.path.join(BWA_dir, 'bwa')
genome_loader = GenomeLoader(genome_file=genome_file)
length = 0
for fasta_rec in genome_loader:
header, sequence = fasta_rec
length += len(sequence)
if length > 1000000000:
break
genome_loader.close()
#Following recommendation set the indexing algorithm to is if genome is <10M
if length > 1000000000:
a_option = 'bwtsw'
else:
a_option = 'is'
#Create the indexes
if color_space:
command = '%s index -c -a %s %s' % (BWA_bin, a_option, genome_file)
else:
command = '%s index -a %s %s' % (BWA_bin, a_option, genome_file)
command_runner.run_command(command)
return run_fine
def bin_coordinates_through_genome(input_file, output_file, genome_file, bin_size):
open_file=utils_logging.open_input_file(input_file)
open_output=utils_logging.open_output_file(output_file)
all_coordinates_per_chr={}
genome_loader=GenomeLoader(genome_file)
previous_bin=0
all_chr=[]
for line in open_file:
sp_line=line.split()
all_coordinates=all_coordinates_per_chr.get(sp_line[0])
if all_coordinates is None:
all_chr.append(sp_line[0])
all_coordinates=[]
all_coordinates_per_chr[sp_line[0]]=all_coordinates
all_coordinates.append(int(sp_line[1]))
all_chr.sort()
for chr in all_chr:
header, sequence =genome_loader.get_chr(chr)
chr=header.strip()
chr_len=len(sequence)
all_coordinates=all_coordinates_per_chr.get(chr)
all_bins=bin_value_from_array(all_coordinates, bin_size, chr_len)
for bin,value in enumerate(all_bins):
open_output.write('%s\t%s\t%s\t%s\n'%(chr, bin*bin_size, (bin*bin_size)+previous_bin, value))
previous_bin+=len(all_bins)*bin_size
open_output.close()
def extract_reads_from_all_bam_files_set_of_consensus_old(bam_files, list_consensus, output_dir, genome_loader=None,
all_read1_consensus_file=None):
if genome_loader is None:
genome_loader = GenomeLoader(all_read1_consensus_file, keep_until_done=True)
for consensus_name in list_consensus:
logging.info("Extract reads from %s " % consensus_name)
consensus_name, consensus_sequence = genome_loader.get_chr(consensus_name)
extract_reads_from_one_consensus(bam_files, output_dir, consensus_name, consensus_sequence)
def extract_reads_from_all_bam_files_set_of_consensus_old(
bam_files,
list_consensus,
output_dir,
genome_loader=None,
all_read1_consensus_file=None):
if genome_loader is None:
genome_loader = GenomeLoader(all_read1_consensus_file,
keep_until_done=True)
for consensus_name in list_consensus:
logging.info("Extract reads from %s " % consensus_name)
consensus_name, consensus_sequence = genome_loader.get_chr(
consensus_name)
extract_reads_from_one_consensus(bam_files, output_dir, consensus_name,
consensus_sequence)
def extract_reads_from_all_bam_files_set_of_consensus(
bam_files,
list_consensus,
output_dir,
genome_loader=None,
all_read1_consensus_file=None):
all_previous_dir = glob.glob(os.path.join(output_dir, '*_dir'))
if len(all_previous_dir):
logging.info("cleanup previous run in %s" % output_dir)
for dir in all_previous_dir:
shutil.rmtree(dir)
if genome_loader is None:
genome_loader = GenomeLoader(all_read1_consensus_file,
keep_until_done=True)
for bam_file in bam_files:
extract_reads_from_one_bam_file(bam_file, output_dir, list_consensus,
genome_loader)
# All the read have been extract now close the fastq files
close_fastq_files()
