def get_insert_size_distribution(data_folder, adaID, fragment, bins=None,
maxreads=-1, VERBOSE=0, density=True):
'''Get the distribution of insert sizes'''
if maxreads <= 0:
maxreads = 1e6
insert_sizes = np.zeros(maxreads, np.int16)
# Open BAM file
if fragment == 'premapped':
bamfilename = get_premapped_filename(data_folder, adaID, type='bam')
else:
bamfilename = get_mapped_filename(data_folder, adaID, fragment, type='bam',
filtered=True)
# Convert from SAM if necessary
if not os.path.isfile(bamfilename):
convert_sam_to_bam(bamfilename)
# Open file
with pysam.Samfile(bamfilename, 'rb') as bamfile:
# Iterate over single reads (no linkage info needed)
n_written = 0
for i, reads in enumerate(pair_generator(bamfile)):
if i == maxreads:
if VERBOSE >= 2:
print 'Max reads reached:', maxreads
break
# Print output
if (VERBOSE >= 3) and (not ((i +1) % 10000)):
print (i+1)
# If unmapped or unpaired, mini, or insert size mini, discard
if reads[0].is_unmapped or (not reads[0].is_proper_pair) or \
reads[1].is_unmapped or (not reads[1].is_proper_pair):
continue
# Store insert size
i_fwd = reads[0].is_reverse
insert_sizes[i] = reads[i_fwd].isize
n_written += 1
insert_sizes = insert_sizes[:n_written]
insert_sizes.sort()
# Bin it
if bins is None:
h = np.histogram(insert_sizes, density=density)
else:
h = np.histogram(insert_sizes, bins=bins, density=density)
return insert_sizes, h
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 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 remove_premapped_tempfiles(data_folder, adaID, VERBOSE=0):
'''Remove the part files of multi-threaded premapping'''
from hivwholeseq.sequencing.filenames import get_premapped_filename
dirname = os.path.dirname(get_premapped_filename(data_folder, adaID, type='bam', part=1))+'/'
fns = glob.glob(dirname+'premapped_*part*') + \
glob.glob(dirname+'premapped_*unsorted*')
fns.append(dirname+'premapped.sam')
for fn in fns:
os.remove(fn)
if VERBOSE >= 3:
print 'File removed:', fn
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 premap_stampy(data_folder,
adaID,
VERBOSE=0,
threads=1,
summary=True,
maxreads=-1,
subsrate=0.05,
gapopen=40,
gapextend=3):
'''Call stampy for actual mapping'''
if VERBOSE:
print 'Premapping: adaID ', adaID
if summary:
summary_filename = get_premap_summary_filename(data_folder, adaID)
# Stampy can handle both gzipped and uncompressed fastq inputs
input_filenames = get_read_filenames(data_folder, adaID, gzip=True)
if not os.path.isfile(input_filenames[0]):
input_filenames = get_read_filenames(data_folder, adaID, gzip=False)
if not all(map(os.path.isfile, input_filenames)):
raise OSError('Input files for mapping not found: ' +
input_filenames[0])
# parallelize if requested
if threads == 1:
call_list = [
stampy_bin,
'--overwrite',
'-g',
get_reference_premap_index_filename(data_folder, adaID, ext=False),
'-h',
get_reference_premap_hash_filename(data_folder, adaID, ext=False),
'-o',
get_premapped_filename(data_folder, adaID, type='sam'),
'--insertsize=450',
'--insertsd=100',
'--substitutionrate=' + str(subsrate),
'--gapopen=' + str(gapopen),
'--gapextend=' + str(gapextend),
]
if maxreads > 0:
call_list.append('--numrecords=' + str(maxreads))
call_list.extend(['-M'] + input_filenames)
call_list = map(str, call_list)
if VERBOSE >= 2:
print ' '.join(call_list)
sp.call(call_list)
if summary:
with open(get_premap_summary_filename(data_folder, adaID),
'a') as f:
f.write('\nStampy premapped (single thread).\n')
# Convert to compressed BAM
convert_sam_to_bam(
get_premapped_filename(data_folder, adaID, type='bam'))
if summary:
with open(summary_filename, 'a') as f:
f.write('\nSAM file converted to compressed BAM: '+\
get_premapped_filename(data_folder, adaID, type='bam')+'\n')
else:
# Multithreading works as follows: call qsub + stampy, monitor the process
# IDs with qstat at regular intervals, and finally merge results with pysam
output_file_parts = [
get_premapped_filename(data_folder,
adaID,
type='bam',
part=(j + 1)) for j in xrange(threads)
]
# Submit map script
jobs_done = np.zeros(threads, bool)
job_IDs = np.zeros(threads, 'S30')
# Submit map call
import hivwholeseq
JOBDIR = hivwholeseq.__path__[0].rstrip('/') + '/'
JOBLOGOUT = JOBDIR + 'logout'
JOBLOGERR = JOBDIR + 'logerr'
cluster_time = ['23:59:59', '1:59:59']
vmem = '8G'
for j in xrange(threads):
call_list = [
'qsub', '-cwd', '-b', 'y', '-S', '/bin/bash', '-o', JOBLOGOUT,
'-e', JOBLOGERR, '-N', adaID + ' p' + str(j + 1), '-l',
'h_rt=' + cluster_time[threads >= 30], '-l', 'h_vmem=' + vmem,
stampy_bin, '--overwrite', '-g',
get_reference_premap_index_filename(
data_folder, adaID, ext=False), '-h',
get_reference_premap_hash_filename(
data_folder, adaID, ext=False), '-o',
get_premapped_filename(
data_folder, adaID, type='sam', part=(j + 1)),
'--processpart=' + str(j + 1) + '/' + str(threads),
'--insertsize=450', '--insertsd=100', '--substitutionrate=' +
str(subsrate), '--gapopen=' + str(gapopen),
'--gapextend=' + str(gapextend), '-M'
] + input_filenames
call_list = map(str, call_list)
if VERBOSE >= 2:
print ' '.join(call_list)
job_ID = sp.check_output(call_list)
job_ID = job_ID.split()[2]
job_IDs[j] = job_ID
# Monitor output
time_wait = 10 # secs
while not jobs_done.all():
# Sleep some time
time.sleep(time_wait)
# Get the output of qstat to check the status of jobs
qstat_output = sp.check_output(['qstat'])
qstat_output = qstat_output.split(
'\n')[:-1] # The last is an empty line
if VERBOSE >= 3:
print qstat_output
if len(qstat_output) < 3:
jobs_done[:] = True
break
else:
qstat_output = [line.split()[0] for line in qstat_output[2:]]
time_wait = 10 # secs
for j in xrange(threads):
if jobs_done[j]:
continue
if job_IDs[j] not in qstat_output:
# Convert to BAM for merging
if VERBOSE >= 1:
print 'Convert premapped reads to BAM for merging: adaID '+\
adaID+', part '+str(j+1)+ ' of '+ \
str(threads)
convert_sam_to_bam(output_file_parts[j])
# We do not need to wait if we did the conversion (it takes
# longer than some secs)
time_wait = 0
jobs_done[j] = True
if summary:
with open(summary_filename, 'a') as f:
f.write('Stampy premapped (' + str(threads) + ' threads).\n')
# Concatenate output files
if VERBOSE >= 1:
print 'Concatenate premapped reads: adaID ' + adaID + '...',
output_filename = get_premapped_filename(data_folder,
adaID,
type='bam',
unsorted=True)
pysam.cat('-o', output_filename, *output_file_parts)
if VERBOSE >= 1:
print 'done.'
if summary:
with open(summary_filename, 'a') as f:
f.write('BAM files concatenated (unsorted).\n')
# Sort the file by read names (to ensure the pair_generator)
# NOTE: we exclude the extension and the option -f because of a bug in samtools
if VERBOSE >= 1:
print 'Sort premapped reads: adaID ' + adaID
output_filename_sorted = get_premapped_filename(data_folder,
adaID,
type='bam',
unsorted=False)
pysam.sort('-n', output_filename, output_filename_sorted[:-4])
if summary:
with open(summary_filename, 'a') as f:
f.write('Joint BAM file sorted.\n')
# Reheader the file without BAM -> SAM -> BAM
if VERBOSE >= 1:
print 'Reheader premapped reads: adaID ' + adaID
header_filename = get_premapped_filename(data_folder,
adaID,
type='sam',
part=1)
pysam.reheader(header_filename, output_filename_sorted)
if summary:
with open(summary_filename, 'a') as f:
f.write('Joint BAM file reheaded.\n')
if VERBOSE >= 1:
print 'Remove temporary files: adaID ' + adaID
remove_premapped_tempfiles(data_folder, adaID, VERBOSE=VERBOSE)
if summary:
with open(summary_filename, 'a') as f:
f.write('Temp premapping files removed.\n')
f.write('\n')
def trim_and_divide_reads(data_folder, adaID, n_cycles, fragments,
maxreads=-1, VERBOSE=0,
minisize=100,
include_tests=False, summary=True):
'''Trim reads and divide them into fragments'''
if VERBOSE:
print 'Trim and divide into fragments: adaID '+adaID+', fragments: '+\
' '.join(fragments)
if summary:
with open(get_divide_summary_filename(data_folder, adaID), 'a') as f:
f.write('Fragments used: '+' '.join(fragments)+'\n')
ref_filename = get_reference_premap_filename(data_folder, adaID)
refseq = SeqIO.read(ref_filename, 'fasta')
smat = np.array(refseq, 'S1')
len_reference = len(refseq)
# Get the positions of fragment start/end, w/ and w/o primers
frags_pos = get_fragment_positions(smat, fragments)
store_reference_fragmented(data_folder, adaID, refseq,
dict(zip(fragments, frags_pos['trim'])))
if summary:
with open(get_divide_summary_filename(data_folder, adaID), 'a') as f:
f.write('Primer positions (for fragments):\n')
for (fragment, poss_full, poss_trim) in izip(fragments,
frags_pos['full'],
frags_pos['trim']):
f.write(fragment+': fwd '+str(poss_full[0])+' '+str(poss_trim[0])+\
', rev '+str(poss_trim[1])+' '+str(poss_full[1])+'\n')
write_fragment_positions(data_folder, adaID, fragments, frags_pos)
# Get the positions of the unwanted outer primers (in case we DO nested PCR
# for that fragment)
# NOTE: the LTRs make no problem, because the rev outer primer of F6
# is not in the reference anymore if F6 has undergone nested PCR
# FIXME: this might not work if we have mixed fragments (e.g. F5a+b) AND nesting
from re import findall
primers_out = {'fwd': [], 'rev': []}
for i, fr in enumerate(fragments):
if (i != 0) and findall(r'F[2-6][a-z]?i', fr):
primers_out['fwd'].append(fr[:-1]+'o')
if (i != len(fragments) - 1) and findall(r'F[1-5][a-z]?i', fr):
primers_out['rev'].append(fr[:-1]+'o')
# Get all possible unambiguous primers for the unwanted outer primers
from hivwholeseq.data.primers import primers_PCR
from hivwholeseq.utils.sequence import expand_ambiguous_seq as eas
primers_out_seq = {'fwd': [np.array(map(list, eas(primers_PCR[fr][0])),
'S1', ndmin=2)
for fr in primers_out['fwd']],
'rev': [np.array(map(list, eas(primers_PCR[fr][1])),
'S1', ndmin=2)
for fr in primers_out['rev']],
}
primers_out_pos = {'fwd': [], 'rev': []}
if primers_out['fwd']:
primers_out_pos['fwd'] = map(itemgetter(0),
get_primer_positions(smat,
primers_out['fwd'], 'fwd'))
if primers_out['rev']:
primers_out_pos['rev'] = map(itemgetter(1),
get_primer_positions(smat,
primers_out['rev'], 'rev'))
# Input and output files
input_filename = get_premapped_filename(data_folder, adaID, type='bam')
if not os.path.isfile(input_filename):
convert_sam_to_bam(input_filename)
output_filenames = get_divided_filenames(data_folder, adaID, fragments, type='bam')
with pysam.Samfile(input_filename, 'rb') as bamfile:
try:
file_handles = [pysam.Samfile(ofn, 'wb', template=bamfile)
for ofn in output_filenames[:len(fragments)]]
fo_am = pysam.Samfile(output_filenames[-4], 'wb', template=bamfile)
fo_cm = pysam.Samfile(output_filenames[-3], 'wb', template=bamfile)
fo_um = pysam.Samfile(output_filenames[-2], 'wb', template=bamfile)
fo_lq = pysam.Samfile(output_filenames[-1], 'wb', template=bamfile)
# Iterate over the mapped reads and assign fragments
n_mapped = [0 for fragment in fragments]
n_unmapped = 0
n_crossfrag = 0
n_ambiguous = 0
n_outer = 0
n_lowq = 0
for irp, reads in enumerate(pair_generator(bamfile)):
if irp == maxreads:
if VERBOSE:
print 'Maximal number of read pairs reached:', maxreads
break
if VERBOSE >= 2:
if not ((irp+1) % 10000):
print irp+1
i_fwd = reads[0].is_reverse
# If unmapped or unpaired, mini, or insert size mini, or
# divergent read pair (fully cross-overlapping), discard
if reads[0].is_unmapped or (not reads[0].is_proper_pair) or \
reads[1].is_unmapped or (not reads[1].is_proper_pair) or \
(reads[0].rlen < 50) or (reads[1].rlen < 50) or \
(reads[i_fwd].isize < minisize):
if VERBOSE >= 3:
print 'Read pair unmapped/unpaired/tiny/divergent:', reads[0].qname
n_unmapped += 1
fo_um.write(reads[0])
fo_um.write(reads[1])
continue
# If the insert is a misamplification from the outer primers
# in fragments that underwent nested PCR,
# trash it (it will have skewed amplification anyway). We cannot
# find all of those, rather only the ones still carrying the
# primer itself (some others have lost it while shearing). For
# those, no matter what happens at the end (reading into adapters,
# etc.), ONE of the reads in the pair will start exactly with one
# outer primer: if the rev read with a rev primer, if the fwd
# with a fwd one. Test all six.
if (len(primers_out_pos['fwd']) or len(primers_out_pos['rev'])) and \
test_outer_primer(reads,
primers_out_pos, primers_out_seq,
len_reference):
if VERBOSE >= 3:
print 'Read pair from outer primer:', reads[0].qname
n_outer += 1
fo_um.write(reads[0])
fo_um.write(reads[1])
continue
# FIXME: the following becomes a bit harder when we mix parallel
# PCRs, e.g. F5a+b, to get more product
# Assign to a fragment now, so that primer trimming is faster
pair_identity = assign_to_fragment(reads, frags_pos['full'],
VERBOSE=VERBOSE)
# 1. If no fragments are possible (e.g. one read crosses the
# fragment boundary, they map to different fragments), dump it
# into a special bucket
if pair_identity == 'cross':
n_crossfrag += 1
fo_cm.write(reads[0])
fo_cm.write(reads[1])
continue
# 2. If 2+ fragments are possible (tie), put into a special bucket
# (essentially excluded, because we want two independent measurements
# in the overlapping region, but we might want to recover them)
elif pair_identity == 'ambiguous':
n_ambiguous += 1
fo_am.write(reads[0])
fo_am.write(reads[1])
continue
# 3. If the intersection is a single fragment, good: trim the primers
# NB: n_frag is the index IN THE POOL. If we sequence only F2-F5, F2 is n_frag = 0
n_frag = int(pair_identity)
frag_pos = frags_pos['trim'][n_frag]
if not np.isscalar(frag_pos[0]):
frag_pos = [frag_pos[0]['inner'], frag_pos[1]['inner']]
trashed_primers = trim_primers(reads, frag_pos,
include_tests=include_tests)
if trashed_primers or (reads[i_fwd].isize < 100):
n_unmapped += 1
if VERBOSE >= 3:
print 'Read pair is mismapped:', reads[0].qname
fo_um.write(reads[0])
fo_um.write(reads[1])
continue
# Quality trimming: if no decently long pair survives, trash
#trashed_quality = main_block_low_quality(reads, phred_min=20,
# include_tests=include_tests)
trashed_quality = trim_low_quality(reads, phred_min=20,
include_tests=include_tests)
if trashed_quality or (reads[i_fwd].isize < 100):
n_lowq += 1
if VERBOSE >= 3:
print 'Read pair has low phred quality:', reads[0].qname
fo_lq.write(reads[0])
fo_lq.write(reads[1])
continue
# Check for cross-overhangs or COH (reading into the adapters)
# --------------->
# <-----------
# In that case, trim to perfect overlap.
if test_coh(reads, VERBOSE=False):
trim_coh(reads, trim=0, include_tests=include_tests)
# Change coordinates into the fragmented reference (primer-trimmed)
for read in reads:
read.pos -= frag_pos[0]
read.mpos -= frag_pos[0]
# Here the tests
if include_tests:
lfr = frags_pos['trim'][n_frag][1] - frags_pos['trim'][n_frag][0]
if test_sanity(reads, n_frag, lfr):
print 'Tests failed:', reads[0].qname
import ipdb; ipdb.set_trace()
# There we go!
n_mapped[n_frag] += 1
file_handles[n_frag].write(reads[0])
file_handles[n_frag].write(reads[1])
finally:
for f in file_handles:
f.close()
fo_am.close()
fo_cm.close()
fo_um.close()
fo_lq.close()
if VERBOSE:
print 'Trim and divide results: adaID '+adaID
print 'Total:\t\t', irp
print 'Mapped:\t\t', sum(n_mapped), n_mapped
print 'Unmapped/unpaired/tiny:\t', n_unmapped
print 'Outer primer\t', n_outer
print 'Crossfrag:\t', n_crossfrag
print 'Ambiguous:\t', n_ambiguous
print 'Low-quality:\t', n_lowq
# Write summary to file
if summary:
with open(get_divide_summary_filename(data_folder, adaID), 'a') as f:
f.write('\n')
f.write('Trim and divide results: adaID '+adaID+'\n')
f.write('Total:\t\t'+str(irp + 1)+'\n')
f.write('Mapped:\t\t'+str(sum(n_mapped))+' '+str(n_mapped)+'\n')
f.write('Unmapped/unpaired/tiny insert:\t'+str(n_unmapped)+'\n')
f.write('Outer primer\t'+str(n_outer)+'\n')
f.write('Crossfrag:\t'+str(n_crossfrag)+'\n')
f.write('Ambiguous:\t'+str(n_ambiguous)+'\n')
f.write('Low-quality:\t'+str(n_lowq)+'\n')
' --adaIDs '+adaID+\
' --fragments '+fragment+\
' --block-length '+str(block_len_initial)+\
' --reads-per-alignment '+str(n_reads_per_ali)+\
' --verbose '+str(VERBOSE))
if store_allele_counts:
f.write(' --allele-counts')
f.write('\n')
if VERBOSE:
print seq_run, adaID, fragment
if fragment == 'genomewide':
refseq = SeqIO.read(
get_reference_premap_filename(data_folder, adaID), 'fasta')
bamfilename = get_premapped_filename(data_folder,
adaID,
type='bam')
frag_out = fragment
else:
fn = get_reference_premap_filename(data_folder, adaID,
fragment)
bamfilename = get_divided_filename(data_folder,
adaID,
fragment,
type='bam')
#FIXME: old nomenclature for F3a is F3
if not os.path.isfile(fn) and fragment[:3] == 'F3a':
fn = get_reference_premap_filename(data_folder, adaID,
'F3' + fragment[-1])
if not os.path.isfile(bamfilename) and fragment[:3] == 'F3a':
f.write('Call: python build_consensus.py'+\
' --run '+seq_run+\
' --adaIDs '+adaID+\
' --fragments '+fragment+\
' --block-length '+str(block_len_initial)+\
' --reads-per-alignment '+str(n_reads_per_ali)+\
' --verbose '+str(VERBOSE))
if store_allele_counts:
f.write(' --allele-counts')
f.write('\n')
if VERBOSE:
print seq_run, adaID, fragment
if fragment == 'genomewide':
refseq = SeqIO.read(get_reference_premap_filename(data_folder, adaID), 'fasta')
bamfilename = get_premapped_filename(data_folder, adaID, type='bam')
frag_out = fragment
else:
fn = get_reference_premap_filename(data_folder, adaID, fragment)
bamfilename = get_divided_filename(data_folder, adaID, fragment, type='bam')
#FIXME: old nomenclature for F3a is F3
if not os.path.isfile(fn) and fragment[:3] == 'F3a':
fn = get_reference_premap_filename(data_folder, adaID, 'F3'+fragment[-1])
if not os.path.isfile(bamfilename) and fragment[:3] == 'F3a':
bamfilename = get_divided_filename(data_folder, adaID, 'F3'+fragment[-1], type='bam')
refseq = SeqIO.read(fn, 'fasta')
frag_out = fragment[:2]
consensus = build_consensus(bamfilename, len(refseq), VERBOSE=VERBOSE,
def premap_stampy(data_folder,
adaID,
VERBOSE=0,
threads=1,
summary=True,
maxreads=-1,
subsrate=0.05,
gapopen=40,
gapextend=3):
'''Call stampy for actual mapping'''
if VERBOSE:
print 'Premapping: adaID ', adaID
if summary:
summary_filename = get_premap_summary_filename(data_folder, adaID)
# Stampy can handle both gzipped and uncompressed fastq inputs
input_filenames = get_read_filenames(data_folder, adaID, gzip=True)
if not os.path.isfile(input_filenames[0]):
input_filenames = get_read_filenames(data_folder, adaID, gzip=False)
if not all(map(os.path.isfile, input_filenames)):
raise OSError('Input files for mapping not found: ' +
input_filenames[0])
# parallelize if requested
if threads == 1:
call_list = [
stampy_bin,
'--overwrite',
'-g',
get_reference_premap_index_filename(data_folder, adaID, ext=False),
'-h',
get_reference_premap_hash_filename(data_folder, adaID, ext=False),
'-o',
get_premapped_filename(data_folder, adaID, type='sam'),
'--insertsize=450',
'--insertsd=100',
'--substitutionrate=' + str(subsrate),
'--gapopen=' + str(gapopen),
'--gapextend=' + str(gapextend),
]
if maxreads > 0:
call_list.append('--numrecords=' + str(maxreads))
call_list.extend(['-M'] + input_filenames)
call_list = map(str, call_list)
if VERBOSE >= 2:
print ' '.join(call_list)
sp.call(call_list)
if summary:
with open(get_premap_summary_filename(data_folder, adaID),
'a') as f:
f.write('\nStampy premapped (single thread).\n')
# Convert to compressed BAM
convert_sam_to_bam(
get_premapped_filename(data_folder, adaID, type='bam'))
if summary:
with open(summary_filename, 'a') as f:
f.write('\nSAM file converted to compressed BAM: '+\
get_premapped_filename(data_folder, adaID, type='bam')+'\n')
else:
# Multithreading works as follows: call qsub + stampy, monitor the process
# IDs with qstat at regular intervals, and finally merge results with pysam
output_file_parts = [
get_premapped_filename(
data_folder, adaID, type='bam', part=(j + 1))
for j in xrange(threads)
]
# Submit map script
jobs_done = np.zeros(threads, bool)
job_IDs = np.zeros(threads, 'S30')
# Submit map call
import hivwholeseq
JOBDIR = hivwholeseq.__path__[0].rstrip('/') + '/'
JOBLOGOUT = JOBDIR + 'logout'
JOBLOGERR = JOBDIR + 'logerr'
cluster_time = ['23:59:59', '1:59:59']
vmem = '8G'
for j in xrange(threads):
call_list = [
'qsub', '-cwd', '-b', 'y', '-S', '/bin/bash', '-o', JOBLOGOUT,
'-e', JOBLOGERR, '-N', adaID + ' p' + str(j + 1), '-l',
'h_rt=' + cluster_time[threads >= 30], '-l', 'h_vmem=' + vmem,
stampy_bin, '--overwrite', '-g',
get_reference_premap_index_filename(
data_folder, adaID, ext=False), '-h',
get_reference_premap_hash_filename(
data_folder, adaID, ext=False), '-o',
get_premapped_filename(
data_folder, adaID, type='sam', part=(j + 1)),
'--processpart=' + str(j + 1) + '/' + str(threads),
'--insertsize=450', '--insertsd=100', '--substitutionrate=' +
str(subsrate), '--gapopen=' + str(gapopen),
'--gapextend=' + str(gapextend), '-M'
] + input_filenames
call_list = map(str, call_list)
if VERBOSE >= 2:
print ' '.join(call_list)
job_ID = sp.check_output(call_list)
job_ID = job_ID.split()[2]
job_IDs[j] = job_ID
# Monitor output
time_wait = 10 # secs
while not jobs_done.all():
# Sleep some time
time.sleep(time_wait)
# Get the output of qstat to check the status of jobs
qstat_output = sp.check_output(['qstat'])
qstat_output = qstat_output.split(
'\n')[:-1] # The last is an empty line
if VERBOSE >= 3:
print qstat_output
if len(qstat_output) < 3:
jobs_done[:] = True
break
else:
qstat_output = [line.split()[0] for line in qstat_output[2:]]
time_wait = 10 # secs
for j in xrange(threads):
if jobs_done[j]:
continue
if job_IDs[j] not in qstat_output:
# Convert to BAM for merging
if VERBOSE >= 1:
print 'Convert premapped reads to BAM for merging: adaID '+\
adaID+', part '+str(j+1)+ ' of '+ \
str(threads)
convert_sam_to_bam(output_file_parts[j])
# We do not need to wait if we did the conversion (it takes
# longer than some secs)
time_wait = 0
jobs_done[j] = True
if summary:
with open(summary_filename, 'a') as f:
f.write('Stampy premapped (' + str(threads) + ' threads).\n')
# Concatenate output files
if VERBOSE >= 1:
print 'Concatenate premapped reads: adaID ' + adaID + '...',
output_filename = get_premapped_filename(
data_folder, adaID, type='bam', unsorted=True)
pysam.cat('-o', output_filename, *output_file_parts)
if VERBOSE >= 1:
print 'done.'
if summary:
with open(summary_filename, 'a') as f:
f.write('BAM files concatenated (unsorted).\n')
# Sort the file by read names (to ensure the pair_generator)
# NOTE: we exclude the extension and the option -f because of a bug in samtools
if VERBOSE >= 1:
print 'Sort premapped reads: adaID ' + adaID
output_filename_sorted = get_premapped_filename(
data_folder, adaID, type='bam', unsorted=False)
pysam.sort('-n', output_filename, output_filename_sorted[:-4])
if summary:
with open(summary_filename, 'a') as f:
f.write('Joint BAM file sorted.\n')
# Reheader the file without BAM -> SAM -> BAM
if VERBOSE >= 1:
print 'Reheader premapped reads: adaID ' + adaID
header_filename = get_premapped_filename(
data_folder, adaID, type='sam', part=1)
pysam.reheader(header_filename, output_filename_sorted)
if summary:
with open(summary_filename, 'a') as f:
f.write('Joint BAM file reheaded.\n')
if VERBOSE >= 1:
print 'Remove temporary files: adaID ' + adaID
remove_premapped_tempfiles(data_folder, adaID, VERBOSE=VERBOSE)
if summary:
with open(summary_filename, 'a') as f:
f.write('Temp premapping files removed.\n')
f.write('\n')
def check_premap(data_folder, adaID, fragments, seq_run, samplename,
qual_min=30, match_len_min=10,
maxreads=-1, VERBOSE=0,
savefig=True,
title=None):
'''Check premap to reference: coverage, etc.'''
refseq = SeqIO.read(get_reference_premap_filename(data_folder, adaID), 'fasta')
# FIXME: do this possibly better than parsing the description!
try:
fields = refseq.description.split()
refseq_start = int(fields[fields.index('(indices') - 3])
except ValueError:
refseq_start = 550
fragpos_filename = get_fragment_positions_filename(data_folder, adaID)
if os.path.isfile(fragpos_filename):
# Load the fragment positions, considering mixed fragments (e.g. F5a+b)
fragtmp = []
postmp = []
with open(fragpos_filename, 'r') as f:
f.readline() #HEADER
for line in f:
fields = line[:-1].split('\t')
fragtmp.append(fields[0])
if 'inner' not in fields[1]:
postmp.append([fields[1], fields[4]])
else:
start = int(fields[1].split(',')[1].split(': ')[1].rstrip('}'))
end = int(fields[4].split(',')[1].split(': ')[1].rstrip('}'))
postmp.append([start, end])
postmp = np.array(postmp, int)
# NOTE: In a lot of old files, it says F3o instead of F3ao
if 'F3o' in fragtmp:
fragtmp[fragtmp.index('F3o')] = 'F3ao'
elif 'F3i' in fragtmp:
fragtmp[fragtmp.index('F3i')] = 'F3ai'
frags_pos = np.array([postmp[fragtmp.index(fr)] for fr in fragments], int).T
else:
frags_pos = None
frags_pos_out = None
# Open BAM and scan reads
input_filename = get_premapped_filename(data_folder, adaID, type='bam')
if not os.path.isfile(input_filename):
if VERBOSE:
print 'Premapped BAM file not found'
return (None, None)
# Count reads if requested
n_reads = get_number_reads(input_filename)
if VERBOSE:
print 'N. of reads:', n_reads
# Get counts
counts, inserts = get_allele_counts_insertions_from_file_unfiltered(input_filename,
len(refseq),
qual_min=qual_min,
match_len_min=match_len_min,
maxreads=maxreads,
VERBOSE=VERBOSE)
# Plot results
if title is None:
title=', '.join(['run '+seq_run+' '+adaID,
'sample '+samplename,
'reads '+str(min(maxreads, n_reads))+'/'+str(n_reads),
])
plot_coverage(counts,
offset_x=refseq_start,
frags_pos=frags_pos,
frags_pos_out=frags_pos_out,
title=title)
if savefig:
from hivwholeseq.sequencing.adapter_info import foldername_adapter
plt.savefig(data_folder+foldername_adapter(adaID)+'figures/coverage_premapped_'+samplename+'.png')
return (counts, inserts)
def check_premap(data_folder,
adaID,
fragments,
seq_run,
samplename,
qual_min=30,
match_len_min=10,
maxreads=-1,
VERBOSE=0,
savefig=True,
title=None):
'''Check premap to reference: coverage, etc.'''
refseq = SeqIO.read(get_reference_premap_filename(data_folder, adaID),
'fasta')
# FIXME: do this possibly better than parsing the description!
try:
fields = refseq.description.split()
refseq_start = int(fields[fields.index('(indices') - 3])
except ValueError:
refseq_start = 550
fragpos_filename = get_fragment_positions_filename(data_folder, adaID)
if os.path.isfile(fragpos_filename):
# Load the fragment positions, considering mixed fragments (e.g. F5a+b)
fragtmp = []
postmp = []
with open(fragpos_filename, 'r') as f:
f.readline() #HEADER
for line in f:
fields = line[:-1].split('\t')
fragtmp.append(fields[0])
if 'inner' not in fields[1]:
postmp.append([fields[1], fields[4]])
else:
start = int(
fields[1].split(',')[1].split(': ')[1].rstrip('}'))
end = int(
fields[4].split(',')[1].split(': ')[1].rstrip('}'))
postmp.append([start, end])
postmp = np.array(postmp, int)
# NOTE: In a lot of old files, it says F3o instead of F3ao
if 'F3o' in fragtmp:
fragtmp[fragtmp.index('F3o')] = 'F3ao'
elif 'F3i' in fragtmp:
fragtmp[fragtmp.index('F3i')] = 'F3ai'
frags_pos = np.array([postmp[fragtmp.index(fr)] for fr in fragments],
int).T
else:
frags_pos = None
frags_pos_out = None
# Open BAM and scan reads
input_filename = get_premapped_filename(data_folder, adaID, type='bam')
if not os.path.isfile(input_filename):
if VERBOSE:
print 'Premapped BAM file not found'
return (None, None)
# Count reads if requested
n_reads = get_number_reads(input_filename)
if VERBOSE:
print 'N. of reads:', n_reads
# Get counts
counts, inserts = get_allele_counts_insertions_from_file_unfiltered(
input_filename,
len(refseq),
qual_min=qual_min,
match_len_min=match_len_min,
maxreads=maxreads,
VERBOSE=VERBOSE)
# Plot results
if title is None:
title = ', '.join([
'run ' + seq_run + ' ' + adaID,
'sample ' + samplename,
'reads ' + str(min(maxreads, n_reads)) + '/' + str(n_reads),
])
plot_coverage(counts,
offset_x=refseq_start,
frags_pos=frags_pos,
frags_pos_out=frags_pos_out,
title=title)
if savefig:
from hivwholeseq.sequencing.adapter_info import foldername_adapter
plt.savefig(data_folder + foldername_adapter(adaID) +
'figures/coverage_premapped_' + samplename + '.png')
return (counts, inserts)
