def read_het_file(self):
t_het_header = du.read_file_header(self.tumor_het_file)
n_het_header = du.read_file_header(self.normal_het_file)
cols_t_type = {t_het_header[0]: str}
cols_n_type = {n_het_header[0]: str}
tumor_het_table = pd.read_csv(self.tumor_het_file,
'\t',
index_col=False,
low_memory=False,
comment='#',
dtype=cols_t_type)
normal_het_table = pd.read_csv(self.normal_het_file,
'\t',
index_col=False,
low_memory=False,
comment='#',
dtype=cols_n_type)
tumor_het_table = du.fix_het_file_header(tumor_het_table)
normal_het_table = du.fix_het_file_header(normal_het_table)
tumor_het_table['Chromosome'] = du.chr2num(
np.array(tumor_het_table['CONTIG']))
normal_het_table['Chromosome'] = du.chr2num(
np.array(normal_het_table['CONTIG']))
tumor_het_table = tumor_het_table[np.isfinite(
tumor_het_table['Chromosome'])]
tumor_het_table['genomic_coord_x'] = du.hg19_to_linear_positions(
np.array(tumor_het_table['Chromosome']),
np.array(tumor_het_table['POSITION']))
normal_het_table = normal_het_table[np.isfinite(
normal_het_table['Chromosome'])]
normal_het_table['genomic_coord_x'] = du.hg19_to_linear_positions(
np.array(normal_het_table['Chromosome']),
np.array(normal_het_table['POSITION']))
tumor_het_table['AF'] = np.true_divide(
tumor_het_table['ALT_COUNT'],
tumor_het_table['ALT_COUNT'] + tumor_het_table['REF_COUNT'])
normal_het_table['AF'] = np.true_divide(
normal_het_table['ALT_COUNT'],
normal_het_table['ALT_COUNT'] + normal_het_table['REF_COUNT'])
self.het_table = pd.merge(normal_het_table,
tumor_het_table,
on='genomic_coord_x',
suffixes=('_N', '_T'))
def read_seg_file(self):
if self.seg_file == 'NULL':
self.seg_table = pd.DataFrame(index=[0],columns=['Chromosome','Start.bp','End.bp','n_probes','length','f','tau','genomic_coord_start','genomic_coord_end'])
self.het_table = pd.DataFrame(index=[0],columns=['seg_id','tau','f','d','AF_T','AF_N','Chromosome','genomic_coord_x','ALT_COUNT_N'
'ALT_COUNT_T','REF_COUNT_N','REF_COUNT_T'])
else:
seg_header = du.read_file_header(self.seg_file)
cols_seg_type = {seg_header[0]: str}
self.seg_table = pd.read_csv(self.seg_file, '\t', index_col=False, low_memory=False, comment='#',
dtype=cols_seg_type)
self.seg_table = du.fix_seg_file_header(self.seg_table)
self.seg_table['Chromosome'] = du.chr2num(np.array(self.seg_table['Chromosome']))
self.seg_table['genomic_coord_start'] = du.hg19_to_linear_positions(np.array(self.seg_table['Chromosome']),
np.array(self.seg_table['Start.bp']))
self.seg_table['genomic_coord_end'] = du.hg19_to_linear_positions(np.array(self.seg_table['Chromosome']),
np.array(self.seg_table['End.bp']))
