def merge_frames(insertion_frames, sample_names):
# Check sample names for duplicates.
duplicate_samples = [
s for s, count in Counter(sample_names).items() if count > 1
]
if len(duplicate_samples) > 1:
raise ValueError('Duplicate sample names given ({})'.format(
', '.join(duplicate_samples)))
# Merge frames.
frames = []
for (frame, sample_name) in zip(insertion_frames, sample_names):
# Check if frame is valid.
Insertion.check_frame(frame)
# Augment frame with sample name.
frame = frame.copy()
frame['sample'] = sample_name
frame['id'] = add_prefix(frame['id'], prefix=sample_name + '.')
frames.append(frame)
merged = pd.concat(frames, axis=0)
merged = Insertion.format_frame(merged)
return merged
def cis_insertions():
return [
# 1000 bp upstream of Trp53bp2.
Insertion(id='INS1', chromosome='1', position=182408172, strand=1,
support=2, metadata=frozendict({'cis_id': 'CIS1'})),
# Different chromosome.
Insertion(id='INS2', chromosome='4', position=77843175, strand=1,
support=2, metadata=frozendict({'cis_id': 'CIS2'}))
] # yapf: disable
def insertions():
# Trp53bp2 location: 1: 182,409,172-182,462,432.
# Myh9 location: 15: 77,760,587-77,842,175.
return [
# 1000 bp upstream of Trp53bp2.
Insertion(id='INS1', chromosome='1', position=182408172,
strand=1, support=2, metadata=frozendict()),
# 2000 bp downstream of Myh9.
Insertion(id='INS2', chromosome='15', position=77758587,
strand=1, support=2, metadata=frozendict()),
# Different chromosome.
Insertion(id='INS3', chromosome='4', position=77843175,
strand=1, support=2, metadata=frozendict())
] # yapf: disable
def main():
"""Main function for pyim-annotate."""
args = parse_args()
insertions = Insertion.from_csv(args.insertions, sep='\t')
annotator = args.caller.from_args(args)
annotated = list(annotator.annotate(insertions))
annotated_frame = Insertion.to_frame(annotated)
annotated_frame = annotated_frame.reindex(index=order_by_index(
annotated_frame.index, index_natsorted(annotated_frame.id)))
annotated_frame.to_csv(str(args.output), sep='\t', index=False)
def main():
parser = setup_parser()
args = parser.parse_args()
# Read frame.
ins_frame = Insertion.from_csv(args.insertions, sep='\t', as_frame=True)
# Create output directory if it doesn't exist.
args.output_dir.mkdir(exist_ok=True, parents=True)
if args.samples is not None:
# Subset for samples and convert to categorical.
ins_frame = ins_frame.ix[ins_frame['sample'].isin(args.samples)]
ins_frame['sample'] = pd.Categorical(ins_frame['sample'],
categories=args.samples)
# Split and write individual outputs.
for sample, sample_frame in ins_frame.groupby('sample'):
if args.remove_prefix:
sample_frame['id'] = remove_prefix(sample_frame['id'],
prefix=sample + '.')
if len(sample_frame) == 0:
print('WARNING: no insertions found for sample {}'.format(sample))
sample_path = args.output_dir / '{}.txt'.format(sample)
sample_frame.to_csv(str(sample_path), sep='\t', index=False)
def main():
"""Main function for pyim-cis."""
args = parse_args()
# Read insertions.
ins_frame = Insertion.from_csv(args.insertions, sep='\t', as_frame=True)
# Drop any columns if needed.
if args.drop is not None:
ins_frame = ins_frame.drop(args.drop, axis=1)
ins_frame = ins_frame.drop_duplicates()
# Convert to BED frame.
start = (ins_frame['position'] - (args.width // 2)).astype(int)
end = (ins_frame['position'] + (args.width // 2)).astype(int)
strand = ins_frame['strand'].map({1: '+', -1: '-', np.nan: '.'})
color = strand.map({'+': '0,0,255', '-': '255,0,0', '.': '60,60,60'})
bed_frame = pd.DataFrame(
OrderedDict([
('chrom', ins_frame['chromosome']),
('chromStart', start),
('chromEnd', end),
('name', ins_frame['id']),
('score', ins_frame['support']),
('strand', strand),
('thickStart', start),
('thickEnd', end),
('itemRgb', color)
])
) # yapf: disable
# Write output.
bed_frame.to_csv(str(args.output), sep='\t', index=False, header=False)
def _insertions_to_cimpl(self, insertions):
# Convert insertions to frame representation.
ins_frame = Insertion.to_frame(insertions)
# Extract and rename required columns.
column_map = {
'id': 'id',
'chromosome': 'chr',
'position': 'location',
'sample': 'sampleID'
}
cimpl_ins = (ins_frame[list(
column_map.keys())].rename(columns=column_map))
# Add chr prefix.
cimpl_ins['chr'] = add_prefix(cimpl_ins['chr'], prefix='chr')
# Add depth if present.
if 'support' in ins_frame:
cimpl_ins['contig_depth'] = ins_frame['support']
elif 'depth_unique' in ins_frame:
cimpl_ins['contig_depth'] = ins_frame['depth_unique']
return cimpl_ins
def _to_insertion(ref, pos, strand, ends, id_=None, **kwargs):
metadata = toolz.merge({
'depth': len(ends),
'depth_unique': len(set(ends))
}, kwargs)
return Insertion(id=id_,
chromosome=ref,
position=pos,
strand=strand,
support=metadata['depth_unique'],
metadata=frozendict(metadata))
def run(self, read_path, output_dir, read2_path=None):
if read2_path is None:
raise ValueError('This pipeline requires paired-end data')
logger = logging.getLogger()
output_dir.mkdir(exist_ok=True, parents=True)
# Extract genomic sequences.
if logger is not None:
logger.info('Extracting genomic sequences')
logger.info(' %-18s: %s', 'Transposon',
shorten_path(self._transposon_path))
logger.info(' %-18s: %s', 'Minimum length', self._min_length)
# Trim reads and align to reference.
genomic_path, genomic2_path = self._extract_genomic(
read_path, read2_path, output_dir, logger=logger)
alignment_path = self._align(
genomic_path, genomic2_path, output_dir, logger=logger)
# Extract insertions from bam file.
bam_file = pysam.AlignmentFile(str(alignment_path))
try:
insertions = extract_insertions(
iter(bam_file),
func=_process_mates,
paired=True,
merge_dist=self._merge_distance,
min_mapq=self._min_mapq,
min_support=self._min_support,
logger=logger)
finally:
bam_file.close()
# Write insertions to output file.
insertion_path = output_dir / 'insertions.txt'
ins_frame = Insertion.to_frame(insertions)
ins_frame.to_csv(str(insertion_path), sep='\t', index=False)