def fetch_intervals(self, gr: GenomeRange):
"""
Parameters
----------
gr : {str, GenomeRange}
Returns
-------
intervals : pandas.core.frame.DataFrame
Annotation interval table.
"""
rows = [
row
for row in tabix_query(self.bgz_file, gr.chrom, gr.start, gr.end)
]
if not rows:
gr.change_chrom_names()
for row in tabix_query(self.bgz_file, gr.chrom, gr.start, gr.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 fetch_intervals(self, gr: GenomeRange):
"""
Parameters
----------
gr : {str, GenomeRange}
Returns
-------
intervals : pandas.core.frame.DataFrame
Annotation interval table.
"""
rows = [
row
for row in tabix_query(self.bgz_file, gr.chrom, gr.start, gr.end)
]
if not rows:
gr.change_chrom_names()
for row in tabix_query(self.bgz_file, gr.chrom, gr.start, gr.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)
name_attr = self.properties.get("name_attr", "auto")
if name_attr == "auto":
gene_name = df['attribute'].str.extract(
".*gene_name (.*?) ").iloc[:, 0].str.strip('\";')
if gene_name.hasnans:
gene_id = df['attribute'].str.extract(
".*gene_id (.*?) ").iloc[:, 0].str.strip('\";')
gene_name.fillna(gene_id, inplace=True)
if gene_name.hasnans:
pos_str = df['seqname'].astype(str) + ":" +\
df['start'].astype(str) + "-" +\
df['end'].astype(str)
gene_name.fillna(pos_str, inplace=True)
df['feature_name'] = gene_name
else:
df['feature_name'] = df['attribute'].str.extract(
f".*{name_attr} (.*?) ").iloc[:, 0].str.strip('\";')
return df
def __load(self, gr):
rows = []
ix_pos = self.properties['col_pos']
ix_pval = self.properties['col_pval']
for items in tabix_query(self.bgz_file, gr.chrom, gr.start, gr.end):
items[ix_pos] = int(items[ix_pos])
items[ix_pval] = float(items[ix_pval])
rows.append(items)
return rows
def __load(self, genome_range):
rows = []
gr = genome_range
for it in tabix_query(self.bgz_file,
gr.chrom,
gr.start,
gr.end,
split=True):
rows.append([it[0], int(it[1]), int(it[2]), float(it[3])])
return rows
def load(self, genome_range):
gr = genome_range
return [[it[0], int(it[1]),
int(it[2]), float(it[3])] for it in tabix_query(
self.bgz_file, gr.chrom, gr.start, gr.end, split=True)]