run_motif_embedding: Run motif embedding

In motifcluster: Motif-Based Spectral Clustering of Weighted Directed Networks

Run motif embedding

Description

Calculate a motif adjacency matrix for a given motif and motif type, restrict it to its largest connected component, and then run Laplace embedding with specified Laplacian type and number of eigenvalues and eigenvectors.

Usage

run_motif_embedding(
  adj_mat,
  motif_name,
  motif_type = c("struc", "func"),
  mam_weight_type = c("unweighted", "mean", "product"),
  mam_method = c("sparse", "dense"),
  num_eigs = 2,
  type_lap = c("comb", "rw"),
  restrict = TRUE
)

Arguments

adj_mat	Adjacency matrix to be embedded.
motif_name	Motif used for the motif adjacency matrix.
motif_type	Type of motif adjacency matrix to use. One of "func" or "struc".
mam_weight_type	Weighting scheme for the motif adjacency matrix. One of "unweighted", "mean" or "product".
mam_method	The method to use for building the motif adjacency matrix. One of "sparse" or "dense".
num_eigs	Number of eigenvalues and eigenvectors for the embedding.
type_lap	Type of Laplacian for the embedding. One of "comb" or "rw".
restrict	Whether or not to restrict the motif adjacency matrix to its largest connected component before embedding.

Value

A list with 7 entries:

• adj_mat: the original adjacency matrix.

• motif_adj_mat: the motif adjacency matrix.

• comps: the indices of the largest connected component of the motif adjacency matrix (if restrict = TRUE).

• adj_mat_comps: the original adjacency matrix restricted to the largest connected component of the motif adjacency matrix (if restrict = TRUE).

• motif_adj_mat_comps: the motif adjacency matrix restricted to its largest connected component (if restrict = TRUE).

• vals: a length-num_eigs vector containing the eigenvalues associated with the Laplace embedding of the (restricted) motif adjacency matrix.

• vects: a matrix containing the eigenvectors associated with the Laplace embedding of the (restricted) motif adjacency matrix.

Examples

adj_mat <- matrix(c(1:9), nrow = 3)
run_motif_embedding(adj_mat, "M1", "func")

motifcluster documentation built on Nov. 18, 2022, 9:06 a.m.