def report_coverage(data_folder, adaID, VERBOSE=0, summary=True):
'''Produce a report on rough coverage on reference (ignore inserts)'''
ref_filename = get_reference_premap_filename(data_folder, adaID)
refseq = SeqIO.read(ref_filename, 'fasta')
# Prepare data structures
coverage = np.zeros(len(refseq), int)
# Parse the BAM file
unmapped = 0
mapped = 0
bamfilename = get_premapped_filename(data_folder, adaID, type='bam')
with pysam.Samfile(bamfilename, 'rb') as bamfile:
for read in bamfile:
if read.is_unmapped or (not read.is_proper_pair) or (not len(
read.cigar)):
unmapped += 1
continue
# Proceed along CIGARs
ref_pos = read.pos
for (bt, bl) in read.cigar:
if bt not in (0, 2):
continue
# Treat deletions as 'covered'
coverage[ref_pos:ref_pos + bl] += 1
ref_pos += bl
mapped += 1
# Save results
from hivwholeseq.sequencing.filenames import get_coverage_figure_filename
import matplotlib.pyplot as plt
fig, ax = plt.subplots(1, 1, figsize=(13, 6))
ax.plot(np.arange(len(refseq)), coverage + 1, lw=2, c='b')
ax.set_xlabel('Position')
ax.set_ylabel('Coverage')
ax.set_yscale('log')
ax.set_title('adaID ' + adaID + ', premapped', fontsize=18)
ax.set_xlim(-20, len(refseq) + 20)
plt.tight_layout()
from hivwholeseq.utils.generic import mkdirs
from hivwholeseq.sequencing.filenames import get_figure_folder
mkdirs(get_figure_folder(data_folder, adaID))
plt.savefig(get_coverage_figure_filename(data_folder, adaID, 'premapped'))
plt.close(fig)
if summary:
with open(get_premap_summary_filename(data_folder, adaID), 'a') as f:
f.write('\nPremapping results: '+\
str(mapped)+' read pairs mapped, '+str(unmapped)+' unmapped\n')
f.write('\nCoverage plotted: '+\
get_coverage_figure_filename(data_folder, adaID, 'premapped')+'\n')
def report_coverage(data_folder, adaID, VERBOSE=0, summary=True):
'''Produce a report on rough coverage on reference (ignore inserts)'''
ref_filename = get_reference_premap_filename(data_folder, adaID)
refseq = SeqIO.read(ref_filename, 'fasta')
# Prepare data structures
coverage = np.zeros(len(refseq), int)
# Parse the BAM file
unmapped = 0
mapped = 0
bamfilename = get_premapped_filename(data_folder, adaID, type='bam')
with pysam.Samfile(bamfilename, 'rb') as bamfile:
for read in bamfile:
if read.is_unmapped or (not read.is_proper_pair) or (not len(
read.cigar)):
unmapped += 1
continue
# Proceed along CIGARs
ref_pos = read.pos
for (bt, bl) in read.cigar:
if bt not in (0, 2):
continue
# Treat deletions as 'covered'
coverage[ref_pos:ref_pos + bl] += 1
ref_pos += bl
mapped += 1
# Save results
from hivwholeseq.sequencing.filenames import get_coverage_figure_filename
import matplotlib.pyplot as plt
fig, ax = plt.subplots(1, 1, figsize=(13, 6))
ax.plot(np.arange(len(refseq)), coverage + 1, lw=2, c='b')
ax.set_xlabel('Position')
ax.set_ylabel('Coverage')
ax.set_yscale('log')
ax.set_title('adaID ' + adaID + ', premapped', fontsize=18)
ax.set_xlim(-20, len(refseq) + 20)
plt.tight_layout()
from hivwholeseq.utils.generic import mkdirs
from hivwholeseq.sequencing.filenames import get_figure_folder
mkdirs(get_figure_folder(data_folder, adaID))
plt.savefig(get_coverage_figure_filename(data_folder, adaID, 'premapped'))
plt.close(fig)
if summary:
with open(get_premap_summary_filename(data_folder, adaID), 'a') as f:
f.write('\nPremapping results: '+\
str(mapped)+' read pairs mapped, '+str(unmapped)+' unmapped\n')
f.write('\nCoverage plotted: '+\
get_coverage_figure_filename(data_folder, adaID, 'premapped')+'\n')
def make_output_folders(data_folder, adaID, VERBOSE=0, summary=True):
'''Make output folders'''
from hivwholeseq.utils.generic import mkdirs
outfiles = [get_premapped_filename(data_folder, adaID)]
if summary:
outfiles.append(get_coverage_figure_filename(data_folder, adaID, 'premapped'))
for outfile in outfiles:
dirname = os.path.dirname(outfile)
mkdirs(dirname)
if VERBOSE:
print 'Folder created:', dirname
def make_output_folders(data_folder, adaID, VERBOSE=0, summary=True):
'''Make output folders'''
from hivwholeseq.utils.generic import mkdirs
outfiles = [get_premapped_filename(data_folder, adaID)]
if summary:
outfiles.append(
get_coverage_figure_filename(data_folder, adaID, 'premapped'))
for outfile in outfiles:
dirname = os.path.dirname(outfile)
mkdirs(dirname)
if VERBOSE:
print 'Folder created:', dirname