Learn R Programming

ePCR

CRAN R package - ePCR: Ensemble Penalized Cox Regression for Survival Prediction

Description

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.

Citation

Methodology:

Guinney J*, Wang T*, Laajala TD*, Winner KK, Bare JC, Neto EC, Khan SA, Peddinti G, Airola A, Pahikkala T, Mirtti T, Yu T, Bot BM, Shen L, Abdallah K, Norman T, Friend S, Stolovitzky G, Soule H, Sweeney CJ, Ryan CJ, Scher HI, Sartor O, Xie Y, Aittokallio T, Zhou FL, Costello JC; Prostate Cancer Challenge DREAM Community. Prediction of overall survival for patients with metastatic castration-resistant prostate cancer: development of a prognostic model through a crowdsourced challenge with open clinical trial data. Lancet Oncol. 2017 Jan;18(1):132-142. doi: 10.1016/S1470-2045(16)30560-5. Epub 2016 Nov 16. PMID: 27864015; PMCID: PMC5217180.

ePCR R-package:

Laajala TD, Murtojärvi M, Virkki A, Aittokallio T. ePCR: an R-package for survival and time-to-event prediction in advanced prostate cancer, applied to real-world patient cohorts. Bioinformatics. 2018 Nov 15;34(22):3957-3959. doi: 10.1093/bioinformatics/bty477. PMID: 29912284; PMCID: PMC6223370.

Copy Link

Version

Install

install.packages('ePCR')

Monthly Downloads

239

Version

0.11.0

License

GPL (>= 2)

Maintainer

Teemu Daniel Laajala

Last Published

February 19th, 2024

Functions in ePCR (0.11.0)

interact.all

Compute all pairwise interactions between the columns of a data matrix
cv.alpha

Cross-validation runs for risk predition at a single value of alpha
meanrank

Compute mean of predicted risk ranks for an ePCR ensemble
score.cindex

Scoring function for evaluating survival prediction through concordance index (c-index)
score.iAUC

Scoring function for evaluating survival prediction by time-wise integrated AUC
zt

Extended function for z-transformation, filling non-finite values and changes column names at will
normriskrank

Normalize ensemble risk scores to ranks and then to uniform range
PSP-methods

PSP-methods
TYKS_reduced

ePCR model fitted to the Turku University Hospital cohorts (features derived from text mining only)
PSP-class

Penalized Single Predictor (PSP) S4-class as a member of PEP-ensembles
NelsonAalen

Cox-Oakes extension of the Nelson-Aalen estimates for a Cox model
PEP-methods

PEP-methods
TimeSurvProb

Predict cumulative survival probabilities for new data at given time points
PEP-class

Penalized Ensemble Predictor (PEP) S4-class ensemble consisting of individual PSP-members
cv

Function that creates customized cross-validation folds
interact.part

Compute a chosen set of pairwise interactions between two sets of columns in a data matrix
integrateRegCurve

Integrate the area over/under the regularization path of a penalized regression model
ePCR

Ensemble Penalized Cox Regression Modeling for Overall Survival and Time-to-Event Prediction in Advanced Prostate Cancer
conforminput

Conform the dimensions of a new input data matrix to a readily fitted PEP or PSP object
heatcv

Plot a heatmap of the prediction performance statistic as a function of lambda and alpha combinations
cv.grid

Cross-validation runs for risk predition for a grid of predetermined alpha values and their conditional lambda values
bootstrapRegCoefs

Bootstrapped testing of regression coefficients in a penalized model
TYKS

ePCR model fitted to the Turku University Hospital cohorts (all features)
DREAM

FIMM-UTU DREAM winning implementation of an ensemble of Penalized Cox Regression models for mCPRC research (ePCR)
TYKSSIMU

TYKSSIMU - simulated data matrices and survival responses from Turku University Hospital