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')
all_chimeras = dict()
for i in alns.keys():
ref_parts = get_ref_parts(alns[i], min_len, min_break_pct, min_range)
if len(ref_parts) > 1:
all_chimeras[i] = ref_parts
log('-- Finding break points and breaking interchromosomally chimeric contigs')
break_intervals = dict()
for i in all_chimeras.keys():
break_intervals[i] = cluster_contig_alns(i, alns, all_chimeras[i], min_len)
# If its just going to break it into the same thing, skip it.
if len(break_intervals[i]) <= 1:
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')
all_chimeras = dict()
for i in alns.keys():
ref_parts = get_ref_parts(alns[i], min_len, min_break_pct,
min_range)
if len(ref_parts) > 1:
all_chimeras[i] = ref_parts
log('Finding break points and breaking interchromosomally chimeric contigs'
)
break_intervals = dict()
for i in all_chimeras.keys():
break_intervals[i] = cluster_contig_alns(i, alns, all_chimeras[i],
min_len)