get_biomarkers: Gets the biomarkers for each column in a matrix of responses...

In broadinstitute/cdsr_biomarker: R toolkit for biomarker analysis

Description

Gets the biomarkers for each column in a matrix of responses using: random_forest lin_associations discrete_test

Usage

get_biomarkers(Y, p_cutoff = 0.1, out_path = NULL)

Arguments

Y	n x p numerical matrix of responses to perturbations, rownames must be Arxspan IDs (missing values are allowed).
p_cutoff	maximum p-value in output tables (to keep them smaller), defaults to 0.1
out_path	if specified, string path to folder to write results to as a .csv

Value

a list with components

rf_table

A table with the following columns:
feature: the column names of X.
RF.imp.mean: an estimate of the importance of that feature for model accuracy.
RF.imp.sd: the standard deviation of the importance estimate.
RF.imp.stability: the proportion of models that used this feature.
rank: the rank of the feature in terms of importance for the model.
MSE: the mean-squared error of the model.
MSE.se: the standard error of the MSE.
R2: the R^2 of the model.
PearsonScore: the Pearson correlation of predicted and observed responses.
pert: the column names of Y

lin_table

A table with the following columns (values calculated with adaptive shrinkage):
betahat: estimated linear coefficient controlled for W.
sebetahat: standard error for the estimate of beta.
NegativeProb: posterior probabilities that beta is negative.
PositiveProb: posterior probabilities that beta is positive
lfsr: local and global fsr values.
svalue: s-values.
lfdr: local and global fdr values.
qvalue: q-values for the effect size estimates.
PosteriorMean: moderated effect size estimates.
PosteriorSD: standard deviations of moderated effect size estimates.
dep.var: dependent variables (column names of Y).
ind.var: independent variables (column names of X).

disc_table

A table with the following columns: feature: the column names of X.
effect_size: an estimate of the difference between groups.
t.stat: the t-statistic associated with the test on group differences.
p.value: the p-value of the t-statistic.
q.value: the multiple hypothesis corrected p-value.
pert: the column names of Y

broadinstitute/cdsr_biomarker documentation built on March 1, 2021, 3:12 a.m.