New Collaborative Study Uses Pangea’s Platform to Create World’s First Sequencing-Free, Transcriptomics-Based Drug Response Predicting System
Pangea Biomed, the company that created ENLIGHT - the world’s most advanced multi-cancer response predictor, announced the publication of research demonstrating the first-ever combined digital pathology and expression-based approach for predicting patient response to cancer treatment. This novel research, dubbed ENLIGHT-DeepPT, applies Pangea’s original ENLIGHT platform to the gene expressions predicted by the new DeepPT framework, demonstrating for the first time a genetic interactions (GI) based approach for predicting patient response to treatment. Specifically, they first built a novel deep-learning framework, DeepPT (Deep Pathology for Treatment), that predicts tumor gene expression from histopathology slide images. They then applied their previously developed approach, ENLIGHT, to predict patient treatment response from the inferred gene expression. Remarkably, their model performance with images was on par with that achieved using the actual gene expression.
Published in bioRxiv, and with Dr Danh-Tai Hoang and Professor Eric Stone (BDSI/ANU) forming part of the collaboration team.
