def test_draw_template(self):
# def draw_template(self, canvas, template, target_width, height, labels=None, colors=None):
d = DiagramSettings()
canvas = Drawing(size=(1000, 50))
t = genomic.Template(
'1',
1,
100000,
bands=[
BioInterval(None, 1, 8000, 'p1'),
BioInterval(None, 10000, 15000, 'p2')
],
)
g = draw_template(d, canvas, t, 1000)
canvas.add(g)
canvas.attribs['height'] = g.height
canvas = Drawing(size=(1000, 50))
g = draw_template(d, canvas, TEMPLATE_METADATA['1'], 1000)
self.assertEqual(
d.breakpoint_top_margin + d.breakpoint_bottom_margin +
d.template_track_height, g.height)
canvas.add(g)
canvas.attribs['height'] = g.height
self.assertEqual(2, len(canvas.elements))
def test_draw_overlay(self):
gene = genomic.Gene('12',
25357723,
25403870,
strand=STRAND.NEG,
name='KRAS')
marker = BioInterval('12', 25403865, name='splice site mutation')
t = build_transcript(cds_start=193,
cds_end=759,
exons=[(25403685, 25403865), (25398208, 25398329),
(25380168, 25380346), (25378548, 25378707),
(25357723, 25362845)],
gene=gene,
domains=[])
build_transcript(cds_start=198,
cds_end=425,
exons=[(25403685, 25403870), (25398208, 25398329),
(25362102, 25362845)],
gene=gene,
domains=[])
build_transcript(cds_start=65,
cds_end=634,
exons=[(25403685, 25403737), (25398208, 25398329),
(25380168, 25380346), (25378548, 25378707),
(25368371, 25368494), (25362365, 25362845)],
gene=gene,
domains=[
protein.Domain('domain1', [(1, 10)]),
protein.Domain('domain1', [(4, 10)])
],
is_best_transcript=True)
build_transcript(cds_start=65,
cds_end=634,
exons=[(25403698, 25403863), (25398208, 25398329),
(25386753, 25388160)],
gene=gene,
domains=[])
d = DiagramSettings()
for i, t in enumerate(gene.transcripts):
t.name = 'transcript {}'.format(i + 1)
scatterx = [x + 100 for x in range(gene.start, gene.end + 1, 400)]
scattery = [random.uniform(-0.2, 0.2) for x in scatterx]
s = ScatterPlot(list(zip(scatterx, scattery)),
'cna',
ymin=-1,
ymax=1,
yticks=[-1, 0, 1])
d.gene_min_buffer = 0
canvas = draw_multi_transcript_overlay(d,
gene,
vmarkers=[marker],
plots=[s, s])
self.assertEqual(2, len(canvas.elements)) # defs counts as element
if OUTPUT_SVG:
canvas.saveas('test_draw_overlay.svg')
def main():
args = parse_arguments()
repeat_sequences = sorted(list(set([s.lower() for s in args.repeat_seq])))
log('loading:', args.input)
reference_genome = load_reference_genome(args.input)
comments = [
os.path.basename(__file__),
'input: {}'.format(args.input),
'min_length: {}'.format(args.min_length),
'repeat_seq: {}'.format(', '.join(args.repeat_seq)),
]
log('writing:', args.output)
with open(args.output, 'w') as fh:
for comment in comments:
fh.write('## {}\n'.format(comment))
fh.write('chr\tstart\tend\tname\n')
visited = set()
for chrom, seq in sorted(reference_genome.items()):
if chrom.startswith('chr'):
chrom = chrom[3:]
seq = str(seq.seq).lower()
if seq in visited:
continue
else:
visited.add(seq)
spans = []
for repseq in repeat_sequences:
log(
'finding {}_repeat (min_length: {}), for chr{} (length: {})'.format(
repseq, args.min_length, chrom, len(seq)
)
)
index = 0
while index < len(seq):
next_n = seq.find(repseq, index)
if next_n < 0:
break
index = next_n
while (
index + len(repseq) <= len(seq)
and seq[index : index + len(repseq)] == repseq
):
index += len(repseq)
span = BioInterval(chrom, next_n + 1, index, name='repeat_{}'.format(repseq))
if len(span) >= args.min_length and len(span) >= 2 * len(repseq):
spans.append(span)
log('found', len(spans), 'spans', time_stamp=False)
for span in spans:
fh.write(
'{}\t{}\t{}\t{}\n'.format(
span.reference_object, span.start, span.end, span.name
)
)