get_panels_from_fit: Extract Panel Details from Group Lasso Fit

In ICBioMark: Data-Driven Design of Targeted Gene Panels for Estimating Immunotherapy Biomarkers

Description

An internal function for analysing a group Lasso fit as part of the predictive model learning procedure, which returns the sets of genes identified by different iterations of the group Lasso algorithm.

Usage

get_panels_from_fit(gene_lengths, fit, gene_list, mut_types_list)

Arguments

gene_lengths	(dataframe) A table with two columns: Hugo_Symbol and max_cds, providing the lengths of the genes to be modelled.
fit	(list) A fit from the group lasso algorithm, produced by the function gglasso (package: gglasso).
gene_list	(character) A character vector of genes listing the genes (in order) included in the model pred_fit.
mut_types_list	(character) A character vector listing the mutation type groupings (in order) included in the model pred_fit.

Value

A list of two elements:

• panel_genes: A matrix where each row corresponds to a gene, each column to an iteration of the group lasso with a different penalty factor, and the elements booleans specifying whether that gene was selected to be included in that iteration.

• panel_lengths:

Examples

panels <- get_panels_from_fit(example_maf_data$gene_lengths, example_first_pred_tmb$fit,
example_gen_model$names$gene_list, mut_types_list = example_gen_model$names$mut_types_list)

print(panels$fit)

ICBioMark documentation built on Nov. 15, 2021, 5:09 p.m.