def extend_UTRs(old_fn, new_fn, UTR_fn, genome_dir):
UTR_boundaries = call_UTRs.read_UTR_file(UTR_fn)
all_features = get_all_features(old_fn)
genes = transcript.get_gff_transcripts(all_features, '/dev/null')
genes = {g.name: g for g in genes}
smallest_start = lambda e: e.start
largest_end = lambda e: e.end
for name in UTR_boundaries:
gene = genes[name]
if len(gene.mRNAs) != 1:
raise ValueError('not exactly one mRNA')
_, _, five_pos, three_pos = UTR_boundaries[name]
if gene.strand == '+':
leftmost_exon = min(gene.exons, key=smallest_start)
leftmost_exon.start = five_pos
gene.mRNAs[0].start = five_pos
gene.top_level_feature.start = five_pos
rightmost_exon = max(gene.exons, key=largest_end)
rightmost_exon.end = three_pos
gene.mRNAs[0].end = three_pos
gene.top_level_feature.end = three_pos
elif gene.strand == '-':
leftmost_exon = max(gene.exons, key=largest_end)
leftmost_exon.end = five_pos
gene.mRNAs[0].end = five_pos
gene.top_level_feature.end = five_pos
rightmost_exon = min(gene.exons, key=smallest_start)
rightmost_exon.start = three_pos
gene.mRNAs[0].start = three_pos
gene.top_level_feature.start = three_pos
with open(new_fn, 'w') as new_fh:
original_lines = open(old_fn)
for line in original_lines:
if line.startswith('#'):
new_fh.write(line)
else:
break
new_fh.write('''\
# UTRs have been extended.
# Top-level features have had distances to the closest other top-level features annotated.
''')
mark_nearby(all_features, genome_dir)
for feature in all_features:
new_fh.write(str(feature) + '\n')
def get_CDSs(gff_fn, genome_dir, annotate_nearby=False):
all_features = get_all_features(gff_fn)
if annotate_nearby:
mark_nearby(all_features, genome_dir)
genes = transcript.get_gff_transcripts(all_features, genome_dir)
translated_genes = [g for g in genes if g.CDSs]
return translated_genes
def get_noncoding_RNA_transcripts(gff_fn):
all_features = get_all_features(gff_fn)
genes = transcript.get_gff_transcripts(all_features, '/dev/null')
rRNA_transcripts = []
tRNA_transcripts = []
other_ncRNA_transcripts = []
for gene in genes:
if gene.top_level_feature.feature == 'rRNA':
rRNA_transcripts.append(gene)
elif gene.top_level_feature.feature == 'tRNA':
tRNA_transcripts.append(gene)
elif 'RNA' in gene.top_level_feature.feature:
other_ncRNA_transcripts.append(gene)
return rRNA_transcripts, tRNA_transcripts, other_ncRNA_transcripts
