cmd = '{} -k19 -w19 -t{} {} {} ' \
'> contigs_against_ref.paf 2> contigs_against_ref.paf.log'.format(minimap_path, t, reference_file, contigs_file)
if not os.path.isfile('contigs_against_ref.paf'):
run(cmd)
# Read in the minimap2 alignments just generated
log('Reading alignments')
alns = read_paf_alignments('contigs_against_ref.paf')
alns = clean_alignments(alns, l=1000, in_exclude_file=exclude_file)
# Process the gff file
if gff_file:
log('Getting gff features')
features = defaultdict(list)
z = GFFReader(gff_file)
for i in z.parse_gff():
features[i.seqname].append(i)
# Break chimeras if desired
if break_chimeras:
# Record how many contigs are broken
total_inter_broken = 0
total_intra_broken = 0
alns = clean_alignments(alns,
l=10000,
in_exclude_file=exclude_file,
uniq_anchor_filter=True)
# Process contigs
log('Getting contigs')
cmd = '{} -k19 -w19 -t{} ../{} ../{} ' \
'> contigs_against_ref.paf 2> contigs_against_ref.paf.log'.format(minimap_path, t, reference_file, contigs_file)
if not os.path.isfile('contigs_against_ref.paf'):
run(cmd)
# Read in the minimap2 alignments just generated
log('-- Reading alignments')
alns = read_paf_alignments('contigs_against_ref.paf')
alns = clean_alignments(alns, l=1000, in_exclude_file=exclude_file)
# Process the gff file
if gff_file:
log('-- Getting gff features')
features = defaultdict(list)
z = GFFReader('../' + gff_file)
for i in z.parse_gff():
features[i.seqname].append(i)
# Break chimeras if desired
if break_chimeras:
# Record how many contigs are broken
total_inter_broken = 0
total_intra_broken = 0
alns = clean_alignments(alns, l=10000, in_exclude_file=exclude_file, uniq_anchor_filter=True)
# Process contigs
log('-- Getting contigs')
contigs_dict = read_contigs('../' + contigs_file)
log('-- Finding interchromosomally chimeric contigs')
run(cmd)
# Read in the minimap2 alignments just generated
if not os.path.exists(os.path.join("orderings", "done.txt")):
log('Reading alignments')
alns = read_paf_alignments('contigs_against_ref.paf')
alns = clean_alignments(alns,
l=1000,
in_exclude_file=exclude_file,
quality=args.quality)
# Process the gff file
if gff_file:
log('Getting gff features')
features = defaultdict(list)
z = GFFReader(os.path.relpath(gff_file))
for i in z.parse_gff():
features[i.seqname].append(i)
# Break chimeras if desired
if break_chimeras:
# Record how many contigs are broken
total_inter_broken = 0
total_intra_broken = 0
alns = clean_alignments(alns,
l=10000,
in_exclude_file=exclude_file,
uniq_anchor_filter=True)
# Process contigs
log('Getting contigs')