MetICA_extract_model: Extracting MetICA model

In daniellyz/MetICA2: Independent component analysis for high-resolution mass-spectrometry based metabolomics

Description

This function extracts a MetICA model with user-decided component numbers.

Usage

MetICA_extract_model(M1, ics, tops = ics)

Arguments

M1	The entire list object generated from the function MetICA(X, pcs = 15...)
ics	Number of clusters (MetICA components) decided by users according to validationPlot
tops	Integer or NULL object. If integer, the tops "best" components based on each evaluation criterion will be plotted.

Value

MetICA model (a list object) whose number of components is decided by users.

• "S"Scores of MetICA components. Data matrix contains n rows (samples) and ics columns (components)

• "A"Loadings of MetICA components. Data matrix contains p rows (metabolic features) and ics columns (components)

• "A1"Normalized loadings of MetICA components. Data matrix contains p rows (metabolic features) and ics columns (components)

• "eval$kurtosis"Vector of length ics containing Kurtosis measure of each MetICA component.

• "eval$cluster_size"Number of IPCA estimates in each corresponding cluster.

• "eval$divergence_index"Divergence indexes of clusters.

• "eval$boot_prop"Proportion of bootstrap estimates in each cluster.

• "eval$boot_stability"Stability of each cluster against bootstrapping.

daniellyz/MetICA2 documentation built on May 16, 2019, 11:11 p.m.