Prediction of Acquired Taxane Resistance Using a Personalized Pathway-Based Machine Learning Method

Abstract

Purpose: This study was conducted to develop and validate an individualized prediction model for automated detection of acquired taxane resistance (ATR).

Materials and methods: Penalized regression, combinedwith an individualized pathway score algorithm,was applied to construct a predictive model using publically available genomic cohorts of ATR and intrinsic taxane resistance (ITR). To develop a model with enhanced generalizability, we merged multiple ATR studies then updated the learning parameter via robust cross-study validation.

Results: For internal cross-study validation, the ATR model produced a perfect performance with an overall area under the receiver operating curve (AUROC) of 1.000 with an area under the precision-recall curve (AUPRC) of 1.000, a Brier score of 0.007, a sensitivity and a specificity of 100%. The model showed an excellent performance on two independent blind ATR cohorts (overall AUROC of 0.940, AUPRC of 0.940, a Brier score of 0.127). When we applied our algorithm to two large-scale pharmacogenomic resources for ITR, the Cancer Genome Project (CGP) and the Cancer Cell Line Encyclopedia (CCLE), an overall ITR cross-study AUROC was 0.70, which is a far better accuracy than an almost random level reported by previous studies. Furthermore, this model had a high transferability on blind ATR cohorts with an AUROC of 0.69, suggesting that general predictive features may be at work across both ITR and ATR.

Conclusion: We successfully constructed a multi-study-derived personalized prediction model for ATR with excellent accuracy, generalizability, and transferability.

Keywords: Docetaxel; Drug resistance; Machine learning; Molecular diagnosis; Paclitaxel; Taxoids.

Fig. 1.

Flow diagram describing the selection process of genomic studies for acquired taxane resistance. GEO, Gene Expression Omnibus; AE, ArrayExpress; PM, PubMed.

Fig. 2.

Workflow for the development and validation of machine learning model for predicting acquired taxane resistance (ATR). The pipeline consists of three main parts: cross-study normalization, transformation into pathway information and model construction. The study cohort was preprocessed and splited into an internal development and validation cohort and an external blind validation cohort. An empirical Bayes approach (Combat) method was used for cross-study normalization. Transforming gene expression level information into pathway-level score for each individual sample was conducted using three curated pathway databases (Kyoto Encyclopedia of Genes and Genomes [KEGG], Pathway Interaction Database [PID], and BioCarta). Using these pathway-level score matrix, penalized regression model was constructed. Parameter optimization of the prediction model was conducted using leave-one-out cross validation (LOOCV) with Efficient Parameter Selection via Global Optimization (EPSGO) algorithm. QC, quality control; CGP, Cancer Genome Project; PTX, paclitaxel; DTX, docetaxel; CCLE, Cancer Cell Line Encyclopedia; EM, Empirical Bayes Method; PDS, pathway dysregulation scores; PC, principal component; AUROC, area under the receiver operating curve; AUPRC, area under the precision-recall curve; ACC, accuracy.

Fig. 3.

Multi-study–derived, individualized pathway learning model for predicting acquired taxane resistance (ATR). (A) Pathway deregulation score (PDS) matrix for the three development cohorts (GSE36135, GSE28784, GSE23779). Each row (744 pathway features from 11,520 input gene features) represents the z‐score-normalized PDS for each individual sample in each cohort. The color bars in the bottom indicate drug sunsitivity status, type of taxane and study cohort. (B) An example of principal curve of the pathway. The principal curve is individually learned with each pathways of the development cohorts. The data points and the principal curve are projected onto the three principal components (PCs). The principal curve goes through the cloud of samples and is directed so that control samples (sensitive to taxane) are near the beginning of the curve. (C) Hyperparameter optimization for elastic-net with Efficient Parameter Selection via Global Optimization (EPSGO). Cross-study validation deviance as a function of both tuning hyperparameters α and λ is shown. α controls the tradeoff between the ridge and lasso penalties, whereas λ controls the overall amount of penalization. The red arrow highlights the final EPSGO solution where the deviance is within 1SE of the minimum (α=0.682 and λ=0.004). (D) Heatmap of the pathways with non-zero coefficient. From 744 input pathways, 39 pathways with non-zero coefficients were selected. The names of the final pathways are labelled on the right side of PDS matrix shown in panel A. S, sensitive; DTX, docetaxel; PTX, paclitaxel.

Fig. 4.

Acquired taxane resistance (ATR)–trained model performances on internal and external validation ATR cohorts. Receiver operating characteristic (ROC) and precision-recall curve are used to show ability to predict. (A) Model performances on internal cross-validation ATR cohorts. (B) Model performances on external blind ATR cohorts. DTX, docetaxel; PTX, paclitaxel; AUC, area under the curve.

Fig. 5.

Intrinsic taxane resistance (ITR)‒trained model performances on internal (ITR) and external validation (acquired taxane resistance [ATR]) cohorts. Receiver operating characteristic (ROC) and precision-recall curve are used to show ability to predict. (A) Model performances on internal validation of ITR cohorts (CCLE-PTX, CGP-DTX, and CGP-PTX). (B) Model performances on external ATR cohorts. AUC, area under the curve; CCLE, Cancer Cell Line Encyclopedia; PTX, paclitaxel; CGP, Cancer Genome Project; DTX, docetaxel.