介紹

R 語言包 BioPred 提供了一系列用于精準醫療中的亞組分析和生物標志物分析的工具。它借助極端梯度提升（XGBoost）算法，并結合傾向得分加權和 A 學習方法，幫助優化個體化治療規則，從而簡化亞組識別過程。BioPred 還能夠識別預測性生物標志物，并獲取其重要性排名。此外，該包還提供了針對生物標志物分析定制的圖形圖表。這一工具使臨床研究人員能夠加深對藥物開發中生物標志物和患者群體的理解。

The R package BioPred offers a suite of tools for subgroup and biomarker analysis in precision medicine. Leveraging Extreme Gradient Boosting (XGBoost) along with propensity score weighting and A-learning methods, BioPred facilitates the optimization of individualized treatment rules to streamline subgroup identification. BioPred also enables the identification of predictive biomarkers and obtaining their importance rankings. Moreover, the package provides graphical plots tailored for biomarker analysis. This tool enables clinical researchers seeking to enhance their understanding of biomarkers and patient population in drug development.

代碼

https://github.com/deeplearner0731/BioPred

案例

安裝

install.packages("BioPred")devtools::install_github("deeplearner0731/BioPred")

運行代碼: https://cran.r-project.org/web/packages/BioPred/vignettes/Tutorial.html

model = XGBoostSub_bin(X, y, trt, pi,Loss_type = “A_learning”, params = list(learning_rate = 0.01, max_depth = 1, lambda = 5, tree_method = ‘hist’), nrounds = 300, disable_default_eval_metric = 0, verbose = FALSE)get_subgroup_results(model, X)eval_metric_bin(model, X, y, pi, trt, Loss_type = “A_learning”)predictive_biomarker_imp(model)fixcut_bin(yvar=“y”, xvar=“x1”, dir=“>“, cutoffs=c(0.1,0.3,0.5), data=tutorial_data, method=“Fisher”, yvar.display=“y”, xvar.display=“Biomarker x1”, vert.x=F)res=cut_perf(yvar=“y”, censorvar=NULL, xvar=“x1”, cutoff=c(0.5), dir=“>”, xvars.adj=NULL, data=tutorial_data, type=“c”, yvar.display=“y”, xvar.display=“Biomarker x1”)res = subgrp_perf_pred(yvar=“y.time”, censorvar=“y.event”, grpvar=“biogroup”, grpname=c(“biomarker_positive”,‘biomarker_negative’),trtvar=“treatment_categorical”, trtname=c(“Placebo”, “Treatment”), xvars.adj=NULL,data=tutorial_data, type=“s”)gam_ctr_plot(yvar=“y.time”, censorvar=“y.event”, xvar= “x1”, xvars.adj=NULL,sxvars.adj=NULL,trtvar=“trt”,type=“s”,data=tutorial_data, k=5, title=“Group Contrast”, ybreaks=NULL, xbreaks=NULL, rugcol.var=NULL,link.scale=T, prt.sum=T, prt.chk=F, outlier.rm=F)roc_bin_plot(yvar=“y”, xvars=“x1”, dirs=“auto”, data=tutorial_data, yvar.display=“y.bin”, xvars.display=“Biomarker x1”)

參考

• BioPred: an R package for biomarkers analysis in precision medicine
• https://github.com/deeplearner0731/BioPred