best_cn = [a.split(',') for a in best_cn.split(':')]
best_cn = np.array(best_cn).astype(int).T
chrom_idx_filename = self.get_analysis_filename('chrom_idx.tsv')
chrom_idx = pd.read_csv(chrom_idx_filename, sep='\t')
count_data_filename = self.get_analysis_filename('counts.tsv')
cn_data = pd.read_csv(count_data_filename,
sep='\t',
header=None,
names=count_cols)
cn_data = cn_data.merge(chrom_idx)
cn_data['total_1'] = best_cn[0]
cn_data['total_2'] = best_cn[1]
cn_data = cn_data[[
'chromosome',
'start',
'end',
'total_1',
'total_2',
]]
cn_data.to_csv(output_cn_filename, sep='\t', index=False, header=True)
if __name__ == '__main__':
cmdline.interface(ThetaTool)
self.get_analysis_filename('h_table.tsv'),
)
cn_data = pd.read_csv(self.get_analysis_filename('cn.tsv'),
sep='\t',
converters={'chromosome': str})
cn_data['total_1'] = cn_data['major_1'] + cn_data['minor_1']
cn_data['total_2'] = cn_data['major_2'] + cn_data['minor_2']
cn_columns = [
'chromosome',
'start',
'end',
'major_1',
'minor_1',
'total_1',
'major_2',
'minor_2',
'total_2',
]
cn_data = cn_data[cn_columns]
cn_data.to_csv(output_cn_filename, sep='\t', index=False)
if __name__ == '__main__':
cmdline.interface(ReMixTTool)
'major': 'major_{0}'.format(clone_id),
})
if cn_table is None:
cn_table = data
else:
cn_table_prev = cn_table
cn_table = remixt.segalg.reindex_segments(cn_table_prev, data)
cn_table_prev.drop(['chromosome', 'start', 'end'],
axis=1,
inplace=True)
data.drop(['chromosome', 'start', 'end'], axis=1, inplace=True)
cn_table = cn_table.merge(cn_table_prev,
left_on='idx_1',
right_index=True)
cn_table = cn_table.merge(data,
left_on='idx_2',
right_index=True)
cn_table.drop(['idx_1', 'idx_2'], axis=1, inplace=True)
cn_table.to_csv(output_cn_filename, sep='\t', index=False)
if __name__ == '__main__':
cmdline.interface(CloneHDTool)
cn_columns = {
'Chromosome': 'chromosome',
'Start_Position(bp)': 'start',
'End_Position(bp)': 'end',
'Copy_Number': 'total_1',
'MajorCN': 'major_1',
'MinorCN': 'minor_1',
'Clonal_Cluster': 'clone',
}
cn_data = cn_data.rename(columns=cn_columns)[cn_columns.values()]
cn_data['clone'] = cn_data['clone'].fillna(1).astype(int)
cn_data['total_2'] = np.where(cn_data['clone'] == 1,
cn_data['total_1'], 2)
cn_data['major_2'] = np.where(cn_data['clone'] == 1,
cn_data['major_1'], 1)
cn_data['minor_2'] = np.where(cn_data['clone'] == 1,
cn_data['minor_1'], 1)
cn_data = cn_data.drop(['clone'], axis=1)
cn_data.to_csv(output_cn_filename, sep='\t', index=False)
if __name__ == '__main__':
cmdline.interface(TitanTool)