def fetch_intervals(bgz_file,
gr: GenomeRange,
gr2: GenomeRange = None) -> pd.DataFrame:
rows = list(pairix_query(bgz_file, gr, second=gr2, split=True))
if len(rows) == 0:
gr.change_chrom_names()
if gr2:
gr2.change_chrom_names()
rows = list(pairix_query(bgz_file, gr, second=gr2, split=True))
return pd.DataFrame(rows)
def fetch(self, genome_range1, genome_range2=None):
"""
Return
------
matrix : numpy.ndarray
"""
from coolbox.utilities.genome import GenomeRange
if genome_range2 is None:
genome_range2 = genome_range1
genome_range1 = to_gr(genome_range1)
genome_range2 = to_gr(genome_range2)
if isinstance(genome_range1, str):
genome_range1 = GenomeRange(genome_range1)
if isinstance(genome_range2, str):
genome_range2 = GenomeRange(genome_range2)
if genome_range1.chrom.startswith("chr"):
genome_range1.change_chrom_names()
if genome_range2.chrom.startswith("chr"):
genome_range2.change_chrom_names()
binsize = self.infer_binsize(genome_range1)
self.fetched_binsize = binsize # expose fetched binsize
straw_list = self.__fetch_straw_list(genome_range1, genome_range2, binsize)
matrix = self.__list_to_matrix(straw_list, genome_range1, genome_range2, binsize)
return matrix
def fetch_intervals(self, bgz_file, gr: GenomeRange) -> pd.DataFrame:
"""
Fetch intervals within input chromosome range.
"""
intervals, bed_type = self.load_range(bgz_file, gr)
if len(intervals) == 0:
gr.change_chrom_names()
intervals, bed_type = self.load_range(bgz_file, gr)
if len(intervals) == 0:
log.debug(f"No valid intervals were found in file {bgz_file} within range {gr}")
intval_table = self.intervals2dataframe(intervals, bed_type)
# attach bed_type info onto the dataframe
intval_table.bed_type = bed_type
return intval_table
def goto(self, genome_range: str = None, genome_range2: str = None):
"""Goto a genome range.
:param genome_range: Genome range string, like "chr9:4000000-6000000".
:param genome_range2: Genome range string, like "chr9:4000000-6000000. Only required in JointView mode".
"""
if genome_range2 is None:
genome_range2 = genome_range
# validate genome range
if genome_range:
gr = GenomeRange(genome_range)
if genome_range2:
gr = GenomeRange(genome_range2)
log.info(f"Goto genome range '{genome_range}' '{genome_range2}'")
self.current_range = [genome_range, genome_range2]
return self
def fetch_intervals(self,
bgz_file,
gr: GenomeRange,
gr2: GenomeRange = None) -> pd.DataFrame:
open_region = self.properties.get("open_region") == "yes"
rows = list(
pairix_query(bgz_file,
gr,
second=gr2,
open_region=open_region,
split=True))
if not rows:
gr.change_chrom_names()
if gr2:
gr2.change_chrom_names()
rows = list(
pairix_query(bgz_file,
gr,
second=gr2,
open_region=open_region,
split=True))
return pd.DataFrame(rows)
def plot(self, ax, gr: GenomeRange, **kwargs):
gr = GenomeRange(gr)
ymin, ymax = ax.get_ylim()
if self.properties['percent_mode'] != 'no':
hlines_list = [
ymin + val * ymax for val in self.properties['values']
]
else:
hlines_list = self.properties['values']
ax.hlines(hlines_list,
gr.start,
gr.end,
linestyle=self.properties['line_style'],
linewidth=self.properties['line_width'],
color=self.properties['color'],
alpha=self.properties['alpha'])
def fetch(self, gr1, gr2=None):
"""
Return
------
matrix : numpy.ndarray
"""
from coolbox.utilities.genome import GenomeRange
flip = False
if gr2 is None:
gr2 = gr1
gr1 = to_gr(gr1)
gr2 = to_gr(gr2)
if gr2.start < gr1.start:
flip = True
gr1, gr2 = gr2, gr1
if isinstance(gr1, str):
gr1 = GenomeRange(gr1)
if isinstance(gr2, str):
gr2 = GenomeRange(gr2)
if gr1.chrom.startswith("chr"):
gr1.change_chrom_names()
if gr2.chrom.startswith("chr"):
gr2.change_chrom_names()
binsize = self.infer_binsize(gr1)
self.fetched_binsize = binsize # expose fetched binsize
straw_iter = self.__fetch_straw_iter(gr1, gr2, binsize)
mat = self.__straw_to_matrix(straw_iter, gr1, gr2, binsize)
if flip:
mat = mat.T
return mat