SparseSignatures: An R package using LASSO-regularized non-negative matrix factorization to identify mutational signatures from human tumor samples.

= rownames(cv_means_mse)[min_ii[1]] min_K = colnames(cv_means_mse)[min_ii[2]] cat("Minimum MSE at:", min_Lambda, "and", min_K, "\n") Problem 4 Uncertain estimation of the number of signatures The estimation of the optimal number of signatures K is uncertain, as the mean squared error does not show a clear trend and multiple solutions seem to be similarly good.

also in 19,460 other papers