Package: XAItest 1.5.0

Ghislain FIEVET

XAItest: XAItest: Enhancing Feature Discovery with eXplainable AI

XAItest is an R Package that identifies features using eXplainable AI (XAI) methods such as SHAP or LIME. This package allows users to compare these methods with traditional statistical tests like t-tests, empirical Bayes, and Fisher's test. Additionally, it includes simThresh, a system that enables the comparison of feature importance with p-values by incorporating calibrated simulated data.

Authors:Ghislain FIEVET [aut, cre], Sébastien HERGALANT [aut]

XAItest_1.5.0.tar.gz
XAItest_1.5.0.zip(r-4.7)XAItest_1.5.0.zip(r-4.6)XAItest_1.5.0.zip(r-4.5)
XAItest_1.5.0.tgz(r-4.6-any)XAItest_1.5.0.tgz(r-4.5-any)
XAItest_1.5.0.tar.gz(r-4.7-any)XAItest_1.5.0.tar.gz(r-4.6-any)
XAItest_1.5.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
card.svg |card.png
XAItest/json (API)
NEWS

# Install 'XAItest' in R:

install.packages('XAItest', repos = c('https://bioc.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/ghislainfievet/xaitest/issues

On BioConductor:XAItest-1.5.0(bioc 3.24)XAItest-1.4.0(bioc 3.23)

software statisticalmethod featureextraction classification regression

2.85 score 1 stars 5 scripts 235 downloads 10 exports 123 dependencies

Last updated from:849972d05d. Checks:8 WARNING, 1 ERROR, 1 OK. Indexed: yes.

Target	Result	Time
bioc-checks	WARNING	217
linux-devel-x86_64	WARNING	289
source / vignettes	ERROR	196
linux-release-x86_64	WARNING	301
macos-release-arm64	WARNING	147
macos-oldrel-arm64	WARNING	146
windows-devel	WARNING	168
windows-release	WARNING	127
windows-oldrel	WARNING	209
wasm-release	OK	146

Exports:addSimThresh genScenario getFeatImpThresholds getMetricsTable mapPvalImportance modelsOverview plotModel setMetricsTable show XAI.test

Dependencies:abind assertthat base64enc Biobase BiocGenerics bslib cachem caret class cli clock codetools cpp11 crosstalk data.table DelayedArray diagram digest doFuture dplyr DT e1071 evaluate farver fastmap fontawesome foreach fs future future.apply generics GenomicRanges ggplot2 glmnet globals glue gower gtable hardhat highr htmltools htmlwidgets ipred IRanges isoband iterators jquerylib jsonlite kernelshap KernSmooth knitr labeling later lattice lava lazyeval lifecycle lime limma listenv lubridate magrittr MASS Matrix MatrixGenerics matrixStats memoise mime ModelMetrics nlme nnet numDeriv otel parallelly pillar pkgconfig plyr pROC prodlim progressr promises proxy purrr R6 randomForest rappdirs RColorBrewer Rcpp RcppEigen recipes reshape2 rlang rmarkdown rpart S4Arrays S4Vectors S7 sass scales Seqinfo shape SparseArray sparsevctrs SQUAREM statmod stringi stringr SummarizedExperiment survival tibble tidyr tidyselect timechange timeDate tinytex tzdb utf8 vctrs viridisLite withr xfun XVector yaml

Vignettes and/or manual for this package failed to build, some documents may be unavailable. Please inspect thebuild logs for more information.

Help page	Topics
Add "simThresh" Simulated Threshold Feature	addSimThresh
Generate benchmark scenarios for feature discovery	genScenario
The getFeatImpThresholds function identifies the minimum level of feature importance required to exceed a specified significance threshold, which is determined by the p-value.	getFeatImpThresholds
Get the Metrics Table	getMetricsTable getMetricsTable,ObjXAI-method
The mapPvalImportance function displays a datatable with color-coded cells based on significance thresholds for feature importance and p-value columns.	mapPvalImportance
Models Overview	modelsOverview
ObjXAI class	.objXAI ObjXAI-class
Plot the model	plotModel
Set the Metrics Table	setMetricsTable setMetricsTable,ObjXAI-method
Show Method for ObjXAI	show,ObjXAI-method
The XAI.test function complements t-test and correlation analyses in feature discovery by integrating eXplainable AI techniques such as feature importance, SHAP, LIME, or custom functions. It provides the option of automatic integration of simulated data to facilitate matching significance between p-values and feature importance.	XAI.test

Package: XAItest 1.5.0

XAItest: XAItest: Enhancing Feature Discovery with eXplainable AI

Citation

Development and contributors

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)