cocoatree.statistics.pairwise.compute_mutual_information_matrix¶
- cocoatree.statistics.pairwise.compute_mutual_information_matrix(sequences, seq_weights=None, freq_regul=0.03, normalize=True)[source]¶
Compute the mutual information matrix
\[I(X, Y) = \sum_{x,y} p(x, y) \log \frac{p(x, y)}{p(x)p(y)}\]Arguments¶
sequences : list of sequences
- seq_weightsndarray (nseq), optional, default: None
if None, will compute sequence weights
freq_regul : regularization parameter (default=__freq_regularization_ref)
- normalizeboolean, defaultTrue
Whether to normalize the mutual information by the entropy.
Returns¶
- mi_matrixnp.ndarray of shape (nseq, nseq)
the matrix of mutual information
