Predicting clinical response to anticancer drugs using an ex vivo platform that captures tumour heterogeneity

TLDR

Predicting clinical response to anticancer drugs is challenging, as tumour microenvironment and heterogeneity limit the predictive power of current biomarker‑guided strategies. The study aims to engineer personalized tumour ecosystems that preserve heterogeneity and mimic the tumour microenvironment. These ecosystems are created by culturing tumour explants in grade‑matched matrix support with autologous patient serum to preserve heterogeneity and microenvironmental context. Using data from 109 patients, the authors trained a machine learning model on ecosystem drug responses and clinical outcomes, achieving 100 % sensitivity with high specificity in an independent cohort of 55 patients, demonstrating that the CANScript platform can enable personalized medicine.

Abstract

Predicting clinical response to anticancer drugs remains a major challenge in cancer treatment. Emerging reports indicate that the tumour microenvironment and heterogeneity can limit the predictive power of current biomarker-guided strategies for chemotherapy. Here we report the engineering of personalized tumour ecosystems that contextually conserve the tumour heterogeneity, and phenocopy the tumour microenvironment using tumour explants maintained in defined tumour grade-matched matrix support and autologous patient serum. The functional response of tumour ecosystems, engineered from 109 patients, to anticancer drugs, together with the corresponding clinical outcomes, is used to train a machine learning algorithm; the learned model is then applied to predict the clinical response in an independent validation group of 55 patients, where we achieve 100% sensitivity in predictions while keeping specificity in a desired high range. The tumour ecosystem and algorithm, together termed the CANScript technology, can emerge as a powerful platform for enabling personalized medicine.