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 print_distribution_holder(holder, output_file=None, textgraph=None, sort_by_weight=False, reverse=False, nb_bin=None):
if not sort_by_weight:
if nb_bin is None:
values,weights=holder.get_sorted_value_and_weight(reverse=reverse)
else:
values,weights=holder.get_binned_value(nb_bin=nb_bin)
else:
values,weights=holder.get_sorted_weight_and_value(reverse=reverse)
out=[]
if output_file:
open_output=utils_logging.open_output_file(output_file, pipe=False)
function=open_output.write
else:
function=out.append
if textgraph:
multiplier=200
sum=0
mark='|'
maximum=max(weights)
if maximum<multiplier:
maximum=multiplier
for i in range(len(values)):
function('%s\t%s %s\n'%(values[i],(mark * int(float(weights[i])/maximum*multiplier)), weights[i] ))
else:
for i in range(len(values)):
function('%s\t%s\n'%(values[i],weights[i]))
if output_file:
open_output.close()
to_return = output_file
else:
to_return = ''.join(out)
return to_return
def shift_reads(bam_file, fasta_file, output_sam_file):
all_sequences = load_new_fasta(fasta_file)
stream, process = utils.get_sam_stream(bam_file, options='-h')
open_output = utils_logging.open_output_file(output_sam_file, pipe=True)
open_output.write("@HD\tVN:1.0\tSO:unsorted\n")
all_values = all_sequences.values()
all_values.sort(key=lambda x: x[0])
for header, sequence in all_values:
open_output.write("@SQ\tSN:%s\tLN:%s\n" % (header, len(sequence)))
# read the header to get the read groups
for line in stream:
if line.startswith('@'):
if line.startswith('@RG'):
open_output.write("%s\n" % (line.strip()))
else:
break
sam_record = Sam_record(line)
sam_record = process_one_record(sam_record, all_sequences)
if sam_record:
open_output.write(str(sam_record))
for line in stream:
sam_record = Sam_record(line)
sam_record = process_one_record(sam_record, all_sequences)
if sam_record:
open_output.write(str(sam_record))
open_output.close()
def output_all_sites(all_sites, output_sites):
open_file = utils_logging.open_output_file(output_sites)
open_file.write("sites\t%s\n" % ("\t".join(all_sites_headers)))
for site_name in all_sites.keys():
open_file.write("%s\t%s\n" % (site_name, "\t".join([
str(all_sites.get(site_name).get(key)) for key in all_sites_headers
])))
open_file.close()
def bin_coordinates(input_file, output_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={}
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_coordinates=[]
all_coordinates_per_chr[sp_line[0]]=all_coordinates
all_coordinates.append(int(sp_line[1]))
for chr in all_coordinates_per_chr.keys():
all_coordinates=all_coordinates_per_chr.get(chr)
all_bins=bin_value_from_array(all_coordinates, bin_size)
for bin,value in enumerate(all_bins):
open_output.write('%s\t%s\t%s\n'%(chr,bin*bin_size,value))
open_output.close()
def RAD_median_coverage(bam_files,output_file):
try:
pipeline_param=utils_param.get_pipeline_parameters()
samtools_dir=pipeline_param.get_samtools_dir()
except Config_file_error, e:
#logging.exception('Config_file_error:')
logging.warning("You'll need to have samtools in your path")
samtools_dir=''
samtools_bin=os.path.join(samtools_dir,"samtools")
bam_file_str=' '.join(bam_files)
all_dists=[]
pileup_stream = get_mpileup_from_bam(bam_file_str, genome_file=None, samtools_bin=samtools_bin, options="-d 100000 -A")
if output_file:
open_output=utils_logging.open_output_file(output_file)
else:
open_output=sys.stdout
bam_file_names=[]
for file in bam_files:
bam_file_names.append(os.path.basename(file))
open_output.write("Consensus\t%s\n"%("\t".join(bam_file_names)))
line = pileup_stream.readline()
sp_line=line.strip().split()
curr_contig=sp_line[0]
for i in range(len(sp_line)/3-1):
all_dists.append(Distribution_holder());
all_dists[i].add_value(sp_line[(i+1)*3])
for line in pileup_stream:
sp_line=line.strip().split()
def output_all_sites(all_sites, output_sites):
open_file = utils_logging.open_output_file(output_sites)
open_file.write("sites\t%s\n"%("\t".join(all_sites_headers)))
for site_name in all_sites.keys():
open_file.write("%s\t%s\n"%(site_name,"\t".join([str(all_sites.get(site_name).get(key)) for key in all_sites_headers])))
open_file.close()