def __init__(self,
chromosome,
build="mm9",
resolution=1000000,
downweighting="none"):
"""Constructs an instance of the Contacts class.
Args:
chromosome (str): The chromosome to visualize, or "genome" for an
interchromosomal heatmap.
build (str): The genome assembly.
resolution (int): The resolution of the heatmap, in bp.
downweighting (str): The downweighting scheme.
"""
self._chromosome = chromosome
self._resolution = resolution
self._assembly = assembly.build(build, resolution)
if downweighting == "none":
self._downweighting = Downweighting.NONE
elif downweighting == "n_minus_one":
self._downweighting = Downweighting.N_MINUS_ONE
elif downweighting == "n_over_two":
self._downweighting = Downweighting.N_OVER_TWO
else:
self._downweighting = Downweighting.UNKNOWN
if self._chromosome == "genome":
self.init_genome_matrix()
else:
self.init_chromosome_matrix()
def main():
args = parse_arguments()
contacts = np.loadtxt(args.heatmap)
resolution = args.resolution
assem = assembly.build(args.assembly, resolution)
hubfile = args.hub
compute_hub_avgs_and_print(contacts, hubfile, assem)
def filter_reads(args):
'''Filter bam
Params:
args: argparse arguments
Notes:
Will filter reads without a full barcode, will remove alt chromosome and MT
and if aligned with ensembl (1, 2, ..., X, Y) will change chromosomes to ucsc
scheme (chr1, chr2, ..., chrX, chrY)
'''
if args.assembly != 'none':
#filter out reads that do not map to main assembly
chroms = list(assembly.build(args.assembly, 1)._chromsizes.keys())
#add chr to bam header
bam_header = add_chr_to_bam_header(args.input, chroms)
# with pysam.AlignmentFile("/mnt/data/2p5-4.RNA.Aligned.sortedByCoord.out.bam.featureCounts.bam", "rb") as input_file,\
# pysam.AlignmentFile("/mnt/data/2p5-4.RNA.test.bam", "wb", header = bam_header) as output_file:
filtered_count = 0
out_count = 0
with pysam.AlignmentFile(args.input, "rb") as input_file:
if args.assembly == 'none':
output_file = pysam.AlignmentFile(args.output,
"wb",
template=input_file)
for read in input_file.fetch(until_eof=True):
if not "NOT_FOUND" in read.query_name:
output_file.write(read)
out_count += 1
else:
filtered_count += 1
else:
output_file = pysam.AlignmentFile(args.output,
"wb",
header=bam_header)
for read in input_file.fetch(until_eof=True):
ref_name = read.reference_name if 'chr' in read.reference_name else 'chr' + read.reference_name
if not "NOT_FOUND" in read.query_name and ref_name in chroms:
output_file.write(read)
out_count += 1
else:
filtered_count += 1
output_file.close()
print('Filtered reads:', filtered_count)
print('Written out reads:', out_count)
def __init__(self,
chromosome,
build="mm9",
resolution=1000000,
downweighting="none"):
self._chromosome = chromosome
self._resolution = resolution
self._assembly = assembly.build(build)
self._assembly.init_offsets(self._resolution)
if downweighting == "none":
self._downweighting = Downweighting.NONE
elif downweighting == "n_minus_one":
self._downweighting = Downweighting.N_MINUS_ONE
elif downweighting == "n_over_two":
self._downweighting = Downweighting.N_OVER_TWO
else:
self._downweighting = Downweighting.UNKNOWN
if self._chromosome == "genome":
self.init_genome_matrix()
else:
self.init_chromosome_matrix()
