for fragment in fragments:
inses = []
for samplename, sample in samples.iterrows():
if submit:
fork_self(samplename, fragment, VERBOSE=VERBOSE, qual_min=qual_min)
continue
if VERBOSE >= 1:
print fragment, samplename
sample = SamplePat(sample)
pname = sample.patient
refseq = SeqIO.read(get_initial_reference_filename(pname, fragment), 'fasta')
fn = sample.get_mapped_filtered_filename(fragment, PCR=PCR)
if not os.path.isfile(fn):
warn('No BAM file found', NoDataWarning)
continue
_, inse = gac(fn, len(refseq), qual_min=qual_min, VERBOSE=VERBOSE)
inses.append(inse)
if save_to_file:
fn_out = sample.get_insertions_filename(fragment, PCR=PCR,
qual_min=qual_min)
save_insertions(fn_out, inse)
if VERBOSE >= 2:
print 'Insertions saved:', samplename, fragment
fork_self(samplename,
fragment,
VERBOSE=VERBOSE,
qual_min=qual_min)
continue
if VERBOSE >= 1:
print fragment, samplename
sample = SamplePat(sample)
pname = sample.patient
refseq = SeqIO.read(
get_initial_reference_filename(pname, fragment), 'fasta')
fn = sample.get_mapped_filtered_filename(fragment, PCR=PCR)
if not os.path.isfile(fn):
warn('No BAM file found', NoDataWarning)
continue
_, inse = gac(fn, len(refseq), qual_min=qual_min, VERBOSE=VERBOSE)
inses.append(inse)
if save_to_file:
fn_out = sample.get_insertions_filename(fragment,
PCR=PCR,
qual_min=qual_min)
save_insertions(fn_out, inse)
if VERBOSE >= 2:
print 'Insertions saved:', samplename, fragment
end -= rf
fn = sample.get_mapped_filtered_filename(fragment,
PCR=PCR,
decontaminated=True)
if not os.path.isfile(fn):
if VERBOSE >= 2:
print 'SKIP'
continue
if VERBOSE >= 2:
print 'Get allele counts for amino acids'
cou = gac(fn,
start_fr,
end_fr,
qual_min=qual_min,
VERBOSE=VERBOSE)
# We do not care about fwd/reverse
count[:, start // 3:end // 3] = cou.sum(axis=0)
counts.append(count)
if save_to_file:
if VERBOSE >= 2:
print 'Save allele counts:', samplename, protein
count.dump(fn_out)
if use_plot:
if VERBOSE >= 2:
print 'Plot'
for fragment in fragments:
counts = []
for samplename, sample in samples.iterrows():
if submit:
fork_self(samplename, fragment, VERBOSE=VERBOSE, qual_min=qual_min)
continue
if VERBOSE >= 1:
print fragment, samplename
sample = SamplePat(sample)
pname = sample.patient
refseq = SeqIO.read(get_initial_reference_filename(pname, fragment), 'fasta')
fn = sample.get_mapped_filtered_filename(fragment, PCR=PCR)
if not os.path.isfile(fn):
warn('No BAM file found', NoDataWarning)
continue
count, _ = gac(fn, len(refseq), qual_min=qual_min, VERBOSE=VERBOSE)
counts.append(count)
if save_to_file:
fn_out = sample.get_allele_counts_filename(fragment, PCR=PCR,
qual_min=qual_min)
count.dump(fn_out)
if VERBOSE >= 2:
print 'Allele counts saved:', samplename, fragment
fork_self(samplename,
fragment,
VERBOSE=VERBOSE,
qual_min=qual_min)
continue
if VERBOSE >= 1:
print fragment, samplename
sample = SamplePat(sample)
pname = sample.patient
refseq = SeqIO.read(
get_initial_reference_filename(pname, fragment), 'fasta')
fn = sample.get_mapped_filtered_filename(fragment, PCR=PCR)
if not os.path.isfile(fn):
warn('No BAM file found', NoDataWarning)
continue
count, _ = gac(fn, len(refseq), qual_min=qual_min, VERBOSE=VERBOSE)
counts.append(count)
if save_to_file:
fn_out = sample.get_allele_counts_filename(fragment,
PCR=PCR,
qual_min=qual_min)
count.dump(fn_out)
if VERBOSE >= 2:
print 'Allele counts saved:', samplename, fragment
rf = end % 3
if rf:
end_fr -= rf
end -= rf
fn = sample.get_mapped_filtered_filename(fragment, PCR=PCR,
decontaminated=True)
if not os.path.isfile(fn):
if VERBOSE >= 2:
print 'SKIP'
continue
if VERBOSE >= 2:
print 'Get allele counts for amino acids'
cou = gac(fn, start_fr, end_fr, qual_min=qual_min,
VERBOSE=VERBOSE)
# We do not care about fwd/reverse
count[:, start // 3: end // 3] = cou.sum(axis=0)
counts.append(count)
if save_to_file:
if VERBOSE >= 2:
print 'Save allele counts:', samplename, protein
count.dump(fn_out)
if use_plot:
if VERBOSE >= 2:
print 'Plot'
cou = count.sum(axis=0)
x = np.tile(np.arange(cou.shape[1]), (cou.shape[0], 1))
