def check_division(data_folder, adaID, fragment, seq_run, qual_min=35,
reference='HXB2', maxreads=-1, VERBOSE=0, minor_allele=False):
'''Check division into fragments: coverage, etc.'''
ref_fn = get_reference_premap_filename(data_folder, adaID, fragment)
# FIXME: old nomenclature for F3a
if not os.path.isfile(ref_fn):
if fragment[:2] == 'F3':
ref_fn = ref_fn.replace('F3a', 'F3')
refseq = SeqIO.read(ref_fn, 'fasta')
# Scan reads
input_filename = get_divided_filename(data_folder, adaID, fragment, type='bam')
# FIXME: old nomenclature for F3a
if not os.path.isfile(input_filename):
if fragment[:2] == 'F3':
input_filename = input_filename.replace('F3a', 'F3')
counts, inserts = get_allele_counts_insertions_from_file(input_filename,
len(refseq),
maxreads=maxreads,
VERBOSE=VERBOSE)
# Plot results
title=', '.join(map(lambda x: ' '.join([x[0], str(x[1])]),
[['run', seq_run],
['adaID', adaID],
['fragment', fragment],
['maxreads', maxreads],
]))
plot_coverage(counts, suptitle=title, minor_allele=minor_allele)
def get_allele_counts(data_folder, adaID, fragment, VERBOSE=0, maxreads=1e10):
'''Extract allele and insert counts from a bamfile'''
# Read reference
reffilename = get_consensus_filename(data_folder,
adaID,
fragment,
trim_primers=True)
refseq = SeqIO.read(reffilename, 'fasta')
# Open BAM file
# Note: the reads should already be filtered of unmapped stuff at this point
bamfilename = get_mapped_filename(data_folder,
adaID,
fragment,
type='bam',
filtered=True)
if not os.path.isfile(bamfilename):
convert_sam_to_bam(bamfilename)
# Call lower-level function
return get_allele_counts_insertions_from_file(bamfilename,
len(refseq),
qual_min=qual_min,
maxreads=maxreads,
VERBOSE=VERBOSE)
def get_allele_counts(data_folder, adaID, fragment, VERBOSE=0, maxreads=1e10):
"""Extract allele and insert counts from a bamfile"""
# Read reference
reffilename = get_consensus_filename(data_folder, adaID, fragment, trim_primers=True)
refseq = SeqIO.read(reffilename, "fasta")
# Open BAM file
# Note: the reads should already be filtered of unmapped stuff at this point
bamfilename = get_mapped_filename(data_folder, adaID, fragment, type="bam", filtered=True)
if not os.path.isfile(bamfilename):
convert_sam_to_bam(bamfilename)
# Call lower-level function
return get_allele_counts_insertions_from_file(
bamfilename, len(refseq), qual_min=qual_min, maxreads=maxreads, VERBOSE=VERBOSE
)
def check_division(data_folder,
adaID,
fragment,
seq_run,
qual_min=35,
reference='HXB2',
maxreads=-1,
VERBOSE=0,
minor_allele=False):
'''Check division into fragments: coverage, etc.'''
ref_fn = get_reference_premap_filename(data_folder, adaID, fragment)
# FIXME: old nomenclature for F3a
if not os.path.isfile(ref_fn):
if fragment[:2] == 'F3':
ref_fn = ref_fn.replace('F3a', 'F3')
refseq = SeqIO.read(ref_fn, 'fasta')
# Scan reads
input_filename = get_divided_filename(data_folder,
adaID,
fragment,
type='bam')
# FIXME: old nomenclature for F3a
if not os.path.isfile(input_filename):
if fragment[:2] == 'F3':
input_filename = input_filename.replace('F3a', 'F3')
counts, inserts = get_allele_counts_insertions_from_file(input_filename,
len(refseq),
maxreads=maxreads,
VERBOSE=VERBOSE)
# Plot results
title = ', '.join(
map(lambda x: ' '.join([x[0], str(x[1])]), [
['run', seq_run],
['adaID', adaID],
['fragment', fragment],
['maxreads', maxreads],
]))
plot_coverage(counts, suptitle=title, minor_allele=minor_allele)
