def fetch_intervals(self, genome_range):
"""
Fetch BigWig intervals within input chromosome range.
"""
chrom, start, end = split_genome_range(genome_range)
if chrom not in self.bw.chroms():
chrom_ = change_chrom_names(chrom)
else:
chrom_ = chrom
intervals = self.bw.intervals(chrom_, start, end)
col_chrom = [chrom] * len(intervals)
col_start = []
col_end = []
col_score = []
for s, e, v in intervals:
col_start.append(s)
col_end.append(e)
col_score.append(v)
intval_table = pd.DataFrame(
{
"chromsome": col_chrom,
"start": col_start,
"end": col_end,
"score": col_score,
},
columns=['chromsome', 'start', 'end', 'score'])
return intval_table
def fetch_intervals(self, genome_range):
"""
Parameters
----------
genome_range : {str, GenomeRange}
Return
------
intervals : pandas.core.frame.DataFrame
Annotation interval table.
"""
chrom, start, end = split_genome_range(genome_range)
rows = []
for row in tabix_query(self.bgz_file, chrom, start, end):
rows.append(row)
columns = [
'seqname', 'source', 'feature', 'start', 'end', 'score', 'strand',
'frame', 'attribute'
]
df = pd.DataFrame(rows, columns=columns)
df['start'] = df['start'].astype(int)
df['end'] = df['end'].astype(int)
df['gene_name'] = df['attribute'].str.extract(
".*gene_name (.*?) ").iloc[:, 0].str.strip('\";')
df['gene_name'].fillna("", inplace=True)
return df
def __load(self, genome_range):
valid_intervals = 0
interval_tree = self.interval_tree
max_score = float('-inf')
min_score = float('inf')
chrom, start, end = split_genome_range(genome_range)
try:
bed_file_h = ReadBed(query_bed(self.bgz_file, chrom, start, end))
except StopIteration:
log.info(f"No records in the range {str(genome_range)}")
return valid_intervals, min_score, max_score
self.bed_type = bed_file_h.file_type
for bed in bed_file_h:
if bed.score < min_score:
min_score = bed.score
if bed.score > max_score:
max_score = bed.score
if bed.chromosome not in interval_tree:
interval_tree[bed.chromosome] = IntervalTree()
itv = Interval(bed.start, bed.end, bed)
if itv not in interval_tree:
interval_tree[bed.chromosome].add(itv)
valid_intervals += 1
return valid_intervals, min_score, max_score
def fetch_data(self, gr, **kwargs):
chrom, start, end = split_genome_range(gr)
sdata = self.data
if self.properties['style'] == 'heatmap':
return sdata.todense()
data = np.asarray(sdata.mean(0)).flatten()
return data
def plot_genome_range(self, ax, genome_range):
"""
Plot the track within a genome range.
Parameters
----------
ax: matplotlib.axes.Axes
Axis to use to plot the scale.
genome_range : {str, GenomeRange}
Genome range to plot.
"""
chrom, start, end = split_genome_range(genome_range)
self.plot(ax, chrom, start, end)
def fetch_intervals(self, genome_range):
"""
Fetch intervals within input chromosome range.
"""
self.load_range(genome_range)
chrom, start, end = split_genome_range(genome_range)
if chrom not in self.interval_tree:
chrom = change_chrom_names(chrom)
if chrom not in self.interval_tree:
intervals = []
else:
intervals = sorted(self.interval_tree[chrom][start:end])
intval_table = self.intervals2dataframe(intervals)
return intval_table
def fetch_intervals(self, genome_range: Union[str, GenomeRange]):
"""
Fetch intervals within input chromosome range.
"""
chrom, start, end = split_genome_range(genome_range)
gr = GenomeRange(chrom, start, end)
rows = self.__load(gr)
if len(rows) == 0:
chrom = change_chrom_names(chrom)
rows = self.__load(GenomeRange(chrom, start, end))
intval_table = pd.DataFrame(
rows, columns=['chromsome', 'start', 'end', 'score'])
return intval_table
def fetch_intervals(self, genome_range: GenomeRange):
chrom, start, end = split_genome_range(genome_range)
rows = [
row_items for row_items in query_bam(
self.indexed_bam, chrom, start, end, split=True)
]
# https://samtools.github.io/hts-specs/SAMv1.pdf
fields = [
"qname", "flag", "rname", "pos", "mapq", "cigar", "rnext", "pnext",
"tlen", "seq", "qual", "options"
]
df = pd.DataFrame(rows, columns=fields)
if df.shape[0] > 0:
df['flag'] = df['flag'].astype(int)
df['pos'] = df['pos'].astype(int)
df['mapq'] = df['mapq'].astype(int)
return df
def fetch_data(self, gr: GenomeRange, **kwargs):
"""
Parameters
----------
gr : GenomeRange
Return
------
intervals : pandas.core.frame.DataFrame
BigWig interval table.
"""
chrom, start, end = split_genome_range(gr)
if chrom not in self.bw.chromsizes:
chrom = change_chrom_names(chrom)
intervals = self.bw.fetch_intervals(chrom, start, end)
columns = list(intervals.columns)
if 'value' in columns:
columns[columns.index('value')] = 'score'
intervals.columns = columns
return intervals
def fetch_data(self, gr: GenomeRange, **kwargs):
"""
Parameters
----------
gr : GenomeRange
Return
------
intervals : pandas.core.frame.DataFrame
BigWig interval table.
"""
chrom, start, end = split_genome_range(gr)
if chrom not in self.bw.chroms():
chrom = change_chrom_names(chrom)
intervals = self.bw.intervals(chrom, start, end)
col_chrom = [chrom] * len(intervals)
col_start = []
col_end = []
col_score = []
for s, e, v in intervals:
col_start.append(s)
col_end.append(e)
col_score.append(v)
intval_table = pd.DataFrame(
{
"chromsome": col_chrom,
"start": col_start,
"end": col_end,
"score": col_score,
},
columns=['chromsome', 'start', 'end', 'score'])
return intval_table