def fix_insert_size(in_bam, config):
"""
Tophat sets PI in the RG to be the inner distance size, but the SAM spec
states should be the insert size. This fixes the RG in the alignment
file generated by Tophat header to match the spec
"""
fixed_file = os.path.splitext(in_bam)[0] + ".pi_fixed.bam"
if file_exists(fixed_file):
return fixed_file
header_file = os.path.splitext(in_bam)[0] + ".header.sam"
read_length = bam.estimate_read_length(in_bam)
bam_handle = bam.open_samfile(in_bam)
header = bam_handle.header.copy()
rg_dict = header['RG'][0]
if 'PI' not in rg_dict:
return in_bam
PI = int(rg_dict.get('PI'))
PI = PI + 2 * read_length
rg_dict['PI'] = PI
header['RG'][0] = rg_dict
with pysam.Samfile(header_file, "wb", header=header) as out_handle:
with bam.open_samfile(in_bam) as in_handle:
for record in in_handle:
out_handle.write(record)
shutil.move(header_file, fixed_file)
return fixed_file
def fix_insert_size(in_bam, config):
"""
Tophat sets PI in the RG to be the inner distance size, but the SAM spec
states should be the insert size. This fixes the RG in the alignment
file generated by Tophat header to match the spec
"""
fixed_file = os.path.splitext(in_bam)[0] + ".pi_fixed.bam"
if file_exists(fixed_file):
return fixed_file
header_file = os.path.splitext(in_bam)[0] + ".header.sam"
read_length = bam.estimate_read_length(in_bam)
bam_handle= bam.open_samfile(in_bam)
header = bam_handle.header.copy()
rg_dict = header['RG'][0]
if 'PI' not in rg_dict:
return in_bam
PI = int(rg_dict.get('PI'))
PI = PI + 2*read_length
rg_dict['PI'] = PI
header['RG'][0] = rg_dict
with pysam.Samfile(header_file, "wb", header=header) as out_handle:
with bam.open_samfile(in_bam) as in_handle:
for record in in_handle:
out_handle.write(record)
shutil.move(header_file, fixed_file)
return fixed_file
def pick_kmersize(fq):
"""
pick an appropriate kmer size based off of https://www.biostars.org/p/201474/
tl;dr version: pick 31 unless the reads are very small, if not then guess
that readlength / 2 is about right.
"""
if bam.is_bam(fq):
readlength = bam.estimate_read_length(fq)
else:
readlength = fastq.estimate_read_length(fq)
halfread = int(round(readlength / 2))
if halfread >= 31:
kmersize = 31
else:
kmersize = halfread
if kmersize % 2 == 0:
kmersize += 1
return kmersize
def pick_kmersize(fq):
"""
pick an appropriate kmer size based off of https://www.biostars.org/p/201474/
tl;dr version: pick 31 unless the reads are very small, if not then guess
that readlength / 2 is about right.
"""
if bam.is_bam(fq):
readlength = bam.estimate_read_length(fq)
else:
readlength = fastq.estimate_read_length(fq)
halfread = int(round(readlength / 2))
if halfread >= 31:
kmersize = 31
else:
kmersize = halfread
if kmersize % 2 == 0:
kmersize += 1
return kmersize
