def get_max_reads_length(reads_file, log, num_checked):
file_type = SeqIO.get_read_file_type(reads_file)
if not file_type:
error('Incorrect extension of reads file: ' + reads_file, log)
max_reads_length = max([len(rec) for rec in itertools.islice(SeqIO.parse(SeqIO.Open(reads_file, "r"), file_type), num_checked)])
log.info(reads_file + ': max reads length: ' + str(max_reads_length))
return max_reads_length
def collect_contigs(dataset, barcodes_dir, output_base, format):
output = open(output_base + "." + format, "w")
for barcode in dataset:
file = os.path.join(barcodes_dir, barcode.id, "truseq_long_reads." + format)
if os.path.exists(file):
contigs = SeqIO.parse(open(file), format)
for contig in contigs:
contig.id = barcode.id + "-" + contig.id
SeqIO.write(contig, output, format)
output.close()
def check_file_not_empty(input_filename, message="", log=None):
filename = abspath(expanduser(input_filename))
file_type = get_read_file_type(input_filename, log)
if (file_type == 'bam'):
return
try:
reads_iterator = SeqIO.parse(SeqIO.Open(filename, "r"), file_type)
if next(reads_iterator, None) is None:
error("file is empty: %s (%s)" % (filename, message), log=log)
except Exception as inst:
error(inst.args[0].format(FILE=filename) + "\n\n" +
traceback.format_exc().format(FILE=filename),
log=log)
def get_max_reads_length(reads_file, log, num_checked):
if reads_file in options_storage.dict_of_prefixes:
ext = options_storage.dict_of_prefixes[reads_file]
file_type = SeqIO.get_read_file_type(ext)
else:
file_type = SeqIO.get_read_file_type(reads_file)
if not file_type:
error("incorrect extension of reads file: %s" % reads_file, log)
max_reads_length = max([
len(rec) for rec in itertools.islice(
SeqIO.parse(SeqIO.Open(reads_file, "r"), file_type), num_checked)
])
log.info("%s: max reads length: %s" % (reads_file, str(max_reads_length)))
return max_reads_length
def moleculo_postprocessing(contigs_file, output_file, sam_files, log):
log.info("===== Starting postprocessing based on read alignment")
log.info("Processing scaffolds from " + contigs_file)
log.info("Using read alignments to break and filter scaffolds")
contigs = list(SeqIO.parse(open(contigs_file, "rU"), "fasta"))
sam = sam_parser.SamChain([sam_parser.Samfile(sam_file) for sam_file in sam_files])
generate_quality.GenerateQuality(contigs, sam)
pattern_filter = moleculo_filter_contigs.PatternContigFilter(contigs, sam, pattern, rc_pattern)
length_filter = moleculo_filter_contigs.ContigLengthFilter(1500)
coverage_breaker = break_by_coverage.ContigBreaker(contigs, sam, 100, 50)
pattern_breaker = break_by_coverage.PatternBreaker(pattern, rc_pattern, 150)
n_breaker = break_by_coverage.NBreaker(3)
result = SplitAndFilter(contigs, coverage_breaker, length_filter, n_breaker, pattern_breaker, pattern_filter)
OutputResults(output_file, "fasta", result)
OutputResults(output_file, "fastq", result)
log.info("===== Postprocessing finished. Results can be found in " + output_file + ".fastq")
def get_max_reads_length(reads_file, log, num_checked):
file_type = get_read_file_type(reads_file, log)
max_reads_length = 0
try:
max_reads_length = max([
len(rec) for rec in itertools.islice(
SeqIO.parse(SeqIO.Open(reads_file, "r"), file_type),
num_checked)
])
except Exception as inst:
error(inst.args[0].format(FILE=reads_file) + "\n\n" +
traceback.format_exc().format(FILE=reads_file),
log=log)
else:
log.info("%s: max reads length: %s" %
(reads_file, str(max_reads_length)))
return max_reads_length