Package: ePCR 0.11.0

ePCR: Ensemble Penalized Cox Regression for Survival Prediction

The top-performing ensemble-based Penalized Cox Regression (ePCR) framework developed during the DREAM 9.5 mCRPC Prostate Cancer Challenge <https://www.synapse.org/ProstateCancerChallenge> presented in Guinney J, Wang T, Laajala TD, et al. (2017) <doi:10.1016/S1470-2045(16)30560-5> is provided here-in, together with the corresponding follow-up work. While initially aimed at modeling the most advanced stage of prostate cancer, metastatic Castration-Resistant Prostate Cancer (mCRPC), the modeling framework has subsequently been extended to cover also the non-metastatic form of advanced prostate cancer (CRPC). Readily fitted ensemble-based model S4-objects are provided, and a simulated example dataset based on a real-life cohort is provided from the Turku University Hospital, to illustrate the use of the package. Functionality of the ePCR methodology relies on constructing ensembles of strata in patient cohorts and averaging over them, with each ensemble member consisting of a highly optimized penalized/regularized Cox regression model. Various cross-validation and other modeling schema are provided for constructing novel model objects.

Authors:Teemu Daniel Laajala <[email protected]> [aut, cre], Mika Murtojarvi <[email protected]> [ctb]

ePCR_0.11.0.tar.gz
ePCR_0.11.0.zip(r-4.7)ePCR_0.11.0.zip(r-4.6)ePCR_0.11.0.zip(r-4.5)
ePCR_0.11.0.tgz(r-4.6-any)ePCR_0.11.0.tgz(r-4.5-any)
ePCR_0.11.0.tar.gz(r-4.7-any)ePCR_0.11.0.tar.gz(r-4.6-any)
ePCR_0.11.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
ePCR/json (API)

# Install 'ePCR' in R:

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

Bug tracker:https://github.com/syksy/epcr/issues

Datasets:

DREAM - FIMM-UTU DREAM winning implementation of an ensemble of Penalized Cox Regression models for mCPRC research
TYKS - EPCR model fitted to the Turku University Hospital cohorts
TYKS_reduced - EPCR model fitted to the Turku University Hospital cohorts
xMEDISIMU - TYKSSIMU - simulated data matrices and survival responses from Turku University Hospital
xTEXTSIMU - TYKSSIMU - simulated data matrices and survival responses from Turku University Hospital
yMEDISIMU - TYKSSIMU - simulated data matrices and survival responses from Turku University Hospital
yTEXTSIMU - TYKSSIMU - simulated data matrices and survival responses from Turku University Hospital

On CRAN:

5.04 score 22 scripts 339 downloads 12 mentions 25 exports 104 dependencies

Last updated from:629d3b96e0. Checks:9 OK. Indexed: yes.

Target	Result	Time
linux-devel-x86_64	OK	211
source / vignettes	OK	308
linux-release-x86_64	OK	183
macos-release-arm64	OK	116
macos-oldrel-arm64	OK	101
windows-devel	OK	119
windows-release	OK	143
windows-oldrel	OK	144
wasm-release	OK	181

Exports:bootstrapRegCoefs coef conforminput cv cv.alpha cv.grid heatcv integrateRegCurve interact.all interact.part meanrank NelsonAalen normriskrank plot predict print PSP.BOX PSP.CSP PSP.KM PSP.NA PSP.PCA score.cindex score.iAUC TimeSurvProb zt

Dependencies:backports base64enc Bolstad2 bslib cachem checkmate cli cluster cmprsk codetools colorspace cpp11 data.table diagram digest doParallel evaluate farver fastmap fontawesome foreach foreign Formula fs future future.apply ggplot2 glmnet globals glue gridExtra gtable hamlet highr Hmisc htmlTable htmltools htmlwidgets impute isoband iterators jquerylib jsonlite KernSmooth knitr labeling lattice lava lifecycle listenv magrittr MASS Matrix MatrixModels memoise mets mime multcomp mvtnorm nlme nnet numDeriv parallelly pec plotrix polspline pracma prodlim progressr Publish quantreg R6 ranger rappdirs RColorBrewer Rcpp RcppArmadillo RcppEigen riskRegression rlang rmarkdown rms rpart rstudioapi S7 sandwich sass scales shape SparseM SQUAREM stringi stringr survival TH.data timereg timeROC tinytex vctrs viridisLite withr xfun yaml zoo

User guide to the ePCR R-package

Rendered fromePCR_guide.Rmdusingknitr::rmarkdown

Last update: 2024-02-19
Started: 2023-07-29

Help page	Topics
Bootstrapped testing of regression coefficients in a penalized model	bootstrapRegCoefs
Conform the dimensions of a new input data matrix to a readily fitted PEP or PSP object	conforminput
Function that creates customized cross-validation folds	cv
Cross-validation runs for risk predition at a single value of alpha	cv.alpha
Cross-validation runs for risk predition for a grid of predetermined alpha values and their conditional lambda values	cv.grid
FIMM-UTU DREAM winning implementation of an ensemble of Penalized Cox Regression models for mCPRC research (ePCR)	DREAM
Ensemble Penalized Cox Regression Modeling for Overall Survival and Time-to-Event Prediction in Advanced Prostate Cancer	ePCR
Plot a heatmap of the prediction performance statistic as a function of lambda and alpha combinations	heatcv
Integrate the area over/under the regularization path of a penalized regression model	integrateRegCurve
Compute all pairwise interactions between the columns of a data matrix	interact.all
Compute a chosen set of pairwise interactions between two sets of columns in a data matrix	interact.part
Compute mean of predicted risk ranks for an ePCR ensemble	meanrank
Cox-Oakes extension of the Nelson-Aalen estimates for a Cox model	NelsonAalen
Normalize ensemble risk scores to ranks and then to uniform range	normriskrank
Penalized Ensemble Predictor (PEP) S4-class ensemble consisting of individual PSP-members	PEP-class
PEP-methods	PEP-methods predict,PEP-method print,PEP-method
Penalized Single Predictor (PSP) S4-class as a member of PEP-ensembles	PSP-class
PSP-methods	coef,PSP-method plot plot,PSP,ANY-method plot,PSP-method predict,PSP-method print,PSP-method PSP-methods PSP.BOX PSP.BOX,PSP,ANY-method PSP.BOX,PSP-method PSP.CSP PSP.CSP,PSP,ANY-method PSP.CSP,PSP-method PSP.KM PSP.KM,PSP,ANY-method PSP.KM,PSP-method PSP.NA PSP.NA,PSP,ANY-method PSP.NA,PSP-method PSP.PCA PSP.PCA,PSP,ANY-method PSP.PCA,PSP-method
Scoring function for evaluating survival prediction through concordance index (c-index)	score.cindex
Scoring function for evaluating survival prediction by time-wise integrated AUC	score.iAUC
Predict cumulative survival probabilities for new data at given time points	TimeSurvProb
ePCR model fitted to the Turku University Hospital cohorts (all features)	TYKS
ePCR model fitted to the Turku University Hospital cohorts (features derived from text mining only)	TYKS_reduced
TYKSSIMU - simulated data matrices and survival responses from Turku University Hospital	TYKSSIMU xMEDISIMU xTEXTSIMU yMEDISIMU yTEXTSIMU
Extended function for z-transformation, filling non-finite values and changes column names at will	zt

Package: ePCR 0.11.0

ePCR: Ensemble Penalized Cox Regression for Survival Prediction

Citation

Development and contributors

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)