def _extract_mapping(self, cimpl_obj, cis_sites):
# Convert CIS sites to frame format.
cis_frame = CisSite.to_frame(cis_sites)
# Convert to R representation for cimpl.
chr_with_prefix = add_prefix(cis_frame['chromosome'], prefix='chr')
r_base = importr('base')
cis_frame_r = RDataFrame({
'id':
r_base.I(StrVector(cis_frame['id'])),
'chromosome':
r_base.I(StrVector(chr_with_prefix)),
'scale':
StrVector(cis_frame['scale']),
'start':
IntVector(cis_frame['start']),
'end':
IntVector(cis_frame['end'])
})
cis_frame_r.rownames = StrVector(cis_frame['id'])
# Retrieve cis matrix from cimpl.
cis_matrix_r = self._cimpl.getCISMatrix(cimpl_obj, cis_frame_r)
cis_matrix = dataframe_to_pandas(cis_matrix_r)
# Extract scale information from cis matrix.
scale_cols = [c for c in cis_matrix.columns if c.startswith('X')]
cis_matrix_scales = cis_matrix[['id'] + scale_cols]
# Melt matrix into long format.
mapping = pd.melt(cis_matrix_scales, id_vars=['id'])
mapping = mapping[['id', 'value']]
mapping = mapping.rename(columns={
'id': 'insertion_id',
'value': 'cis_id'
})
# Split cis_id column into individual entries (for entries
# with multiple ids). Then drop any empty rows, as these
# entries are empty cells in the matrix.
mapping = mapping.ix[mapping['cis_id'] != '']
mapping = expand_column(mapping, col='cis_id', delimiter='|')
mapping_dict = {
ins_id: set(grp['cis_id'])
for ins_id, grp in mapping.groupby('insertion_id')
}
return mapping_dict
