crested.tl.modisco.create_pattern_matrix

crested.tl.modisco.create_pattern_matrix(classes, all_patterns, normalize=False, pattern_parameter='seqlet_count')

Create a pattern matrix from classes and patterns, with optional normalization.

Parameters:

• classes (list[str]) – list of class labels.

• all_patterns (dict[str, dict[str, str | list[float]]]) – dictionary containing pattern data.

• normalize (bool (default: False)) – Flag to indicate whether to normalize the rows of the matrix.

• pattern_parameter (str (default: 'seqlet_count')) – Parameter which is used to indicate the pattern’s importance. Either average contribution score (‘contrib’), or number of pattern instances (‘seqlet_count’, default) and its log (‘seqlet_count_log’).

See also

crested.tl.modisco.process_patterns, crested.pl.patterns.clustermap

Return type:

ndarray

Returns:

The resulting pattern matrix, optionally normalized.