def run(self, mult3=False):
for aln_id, aln, t, a in self.alignment_transcript_annotation_iterator(
):
# do not include noncoding transcripts or lift-overs that contain less than short_cds_size
if comp_ann_lib.short_cds(t) or comp_ann_lib.short_cds(a):
self.classify_dict[aln_id] = 0
continue
for start, stop, size in comp_ann_lib.deletion_iterator(
t, aln, mult3):
if start >= t.thick_start and stop < t.thick_stop:
bed_rec = seq_lib.chromosome_region_to_bed(
t, start, stop, self.rgb, self.column)
self.details_dict[aln_id].append(bed_rec)
self.classify_dict[aln_id] = len(self.details_dict[aln_id])
self.dump_results_to_disk()
def run(self, equality_test=lambda target, query: target != query):
self.get_fasta()
for aln_id, aln, t, a in self.alignment_transcript_annotation_iterator(
):
# do not include noncoding transcripts or lift-overs that contain less than short_cds_size
if comp_ann_lib.short_cds(t) or comp_ann_lib.short_cds(a):
self.classify_dict[aln_id] = 0
continue
for i, target_codon, query_codon in comp_ann_lib.codon_pair_iterator(
a, t, aln, self.seq_dict, self.ref_seq_dict):
target_aa = seq_lib.codon_to_amino_acid(target_codon)
query_aa = seq_lib.codon_to_amino_acid(query_codon)
if target_codon != query_codon and equality_test(
target_aa, query_aa) is True:
bed_rec = seq_lib.cds_coordinate_to_bed(
t, i, i + 3, self.rgb, self.column)
self.details_dict[aln_id].append(bed_rec)
self.classify_dict[aln_id] = len(self.details_dict[aln_id])
self.dump_results_to_disk()
def run(self):
for aln_id, aln, t, a in self.alignment_transcript_annotation_iterator(
):
# do not include noncoding transcripts or lift-overs that contain less than short_cds_size
if comp_ann_lib.short_cds(t) or comp_ann_lib.short_cds(a):
self.classify_dict[aln_id] = 0
continue
frame_shifts = list(comp_ann_lib.frame_shift_iterator(a, t, aln))
if len(frame_shifts) == 0:
self.classify_dict[aln_id] = 0
continue
windowed_stops, windowed_starts = self.window_starts_stops(
t, frame_shifts)
for start, stop in itertools.izip(windowed_starts, windowed_stops):
bed_rec = seq_lib.chromosome_coordinate_to_bed(
t, start, stop, self.rgb, self.column)
self.details_dict[aln_id].append(bed_rec)
self.classify_dict[aln_id] = len(self.details_dict[aln_id])
self.dump_results_to_disk()
def run(self):
for ens_id, a in self.annotation_iterator():
if comp_ann_lib.short_cds(a) is True and a.cds_size != 0:
bed_rec = seq_lib.cds_coordinate_to_bed(
a, 0, a.cds_size, self.rgb, self.column)
self.details_dict[ens_id].append(bed_rec)
self.classify_dict[ens_id] = 1
else:
self.classify_dict[ens_id] = 0
self.dump_results_to_disk()
def run(self):
for aln_id, aln, t, a in self.alignment_transcript_annotation_iterator(
):
# do not include noncoding transcripts or lift-overs that contain less than short_cds_size
if comp_ann_lib.short_cds(t) or comp_ann_lib.short_cds(a):
self.classify_dict[aln_id] = 0
continue
cds_positions = [
t.chromosome_coordinate_to_cds(
aln.query_coordinate_to_target(
a.cds_coordinate_to_transcript(i))) for i in xrange(3)
]
if None in cds_positions:
self.details_dict[aln_id].append(
seq_lib.cds_coordinate_to_bed(t, 0, 3, self.rgb,
self.column))
self.classify_dict[aln_id] = 1
else:
self.classify_dict[aln_id] = 0
self.dump_results_to_disk()
def run(self):
self.get_fasta()
for ens_id, a in self.annotation_iterator():
# do not include noncoding transcripts or lift-overs that contain less than short_cds_size
if comp_ann_lib.short_cds(a):
self.classify_dict[ens_id] = 0
elif a.get_cds(self.ref_seq_dict)[:3] != "ATG":
bed_rec = seq_lib.cds_coordinate_to_bed(
a, 0, 3, self.rgb, self.column)
self.details_dict[ens_id].append(bed_rec)
self.classify_dict[ens_id] = 1
else:
self.classify_dict[ens_id] = 0
self.dump_results_to_disk()
def run(self):
for ens_id, a in self.annotation_iterator():
# do not include noncoding transcripts or lift-overs that contain less than short_cds_size
if comp_ann_lib.short_cds(a):
self.classify_dict[ens_id] = 0
continue
if a.cds_size % 3 != 0:
bed_rec = seq_lib.chromosome_coordinate_to_bed(
a, a.thick_start, a.thick_stop, self.rgb, self.column)
self.details_dict[ens_id].append(bed_rec)
self.classify_dict[ens_id] = 1
else:
self.classify_dict[ens_id] = 0
self.dump_results_to_disk()
def run(self):
for ens_id, a in self.annotation_iterator():
# do not include noncoding transcripts or lift-overs that contain less than short_cds_size
if comp_ann_lib.short_cds(a):
self.classify_dict[ens_id] = 0
continue
# remove all -1 frames because those are UTR exons
a_frames = [x for x in a.exon_frames if x != -1]
if a.strand is True and a_frames[
0] != 0 or a.strand is False and a_frames[-1] != 0:
self.classify_dict[ens_id] = 1
self.details_dict[ens_id].append(
seq_lib.cds_coordinate_to_bed(a, 0, 3, self.rgb,
self.column))
else:
self.classify_dict[ens_id] = 0
self.dump_results_to_disk()