def break_contigs(contigs_file, sam_file, output_file):
contigs = list(SeqIO.parse(open(contigs_file, "rU"), "fasta"))
# sam = sam_parser.SamChain([sam_parser.Samfile(sam_file) for sam_file in sam_files])
sam = sam_parser.Samfile(sam_file)
# last two arguments: K, min0 stretch length to break
coverage_breaker = break_by_coverage.ContigBreaker(contigs, sam, 100, 50)
coverage_breaker.OutputBroken(output_file)
def ConstructSubreferenceFromSam(sam_files):
#todo: make online
#todo: use config
recs = []
for sam_file in sam_files:
sam = sam_parser.Samfile(sam_file)
for rec in sam:
if rec.pos != -1:
recs.append(Record(rec))
recs.sort()
filtered_recs = CollectParts(recs, 0, 2, 500)
subreferences = CollectParts(filtered_recs, 20000, 0, 7000)
return filtered_recs, subreferences
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")