No abstract

Precision oncology is gradually advancing into mainstream clinical practice, demonstrating significant survival benefits. However, eligibility and response rates remain limited in many cases, calling for better predictive biomarkers. Here we present ENLIGHT, a transcriptomics-based computational approach that identifies clinically relevant genomic interactions and uses them to predict patients' response to a variety of therapies in multiple cancer types without training on previous response data. We study ENLIGHT in two translationally oriented scenarios, Personalized Medicine (PM), aimed at prioritizing treatments for a single patient, and Clinical Trial Design (CTD), selecting the most likely responders in a patient cohort. Evaluating ENLIGHT's PM performance on 21 blinded clinical trial datasets, we show that it can effectively predict treatment response across multiple therapies and cancer types (obtaining an odds ratio of 2.59), substantially improving upon SELECT, a previously published transcriptomics-based approach, and performing as well as supervised predictors developed for specific indications and drugs, but on a much broader array of therapies and indications. In the CTD scenario, ENLIGHT can markedly enhance the success of clinical trials by excluding non-responders while achieving more than 90% of the response rate attainable under an optimal exclusion strategy. In sum, ENLIGHT is one of the first approaches to demonstrably predict therapeutic response across multiple cancer types by leveraging the transcriptome.

Advances in artificial intelligence have paved the way for predicting cancer patients' survival and response to treatment from hematoxylin and eosin (H&E)-stained tumor slides. Extant approaches do so either directly from the H&E images or via prediction of actionable mutations and gene fusions. Here we present the first genetic interactions (GI)-based approach for predicting patient response to treatment, founded on two conceptual steps: (1) First, we build DeepPT, a deep-learning framework that predicts tumor gene expression from H&E slides, and subsequently, (2) we apply ENLIGHT - a previously published GI based approach - to predict patient treatment response from the inferred tumor expression. DeepPT was trained on images and corresponding transcriptomics data of TCGA breast, kidney, lung, and brain tumor samples. Testing DeepPT transcriptomics prediction ability, we find that it generalizes well to predicting the expression of two breast and brain cancer unseen independent datasets. Studying samples from a recently published large multi-omics breast cancer clinical trial, we applied ENLIGHT to the expression predicted by DeepPT from the tumor slides. We find that it successfully predicts true responders with a clinically meaningful hazard ratio of about six. These results put forward a general framework for predicting patient response to a broad array of targeted and checkpoint therapies from the histological images. If corroborated further, the new approach could augment the feasibility of precision oncology in developing countries and in other situations where comprehensive molecular profiling is not available.