Danh-Tai Hoang, Gal Dinstag, Eldad D. Shulman, Leandro C. Hermida, Doreen S. Ben-Zvi, Efrat Elis, Katherine Caley, Stephen-John Sammut, Sanju Sinha, Neelam Sinha, Christopher H. Dampier, Chani Stossel, Tejas Patil, Arun Rajan, Wiem Lassoued, Julius Strauss, Shania Bailey, Clint Allen, Jason Redman, Tuvik Beker, Peng Jiang, Talia Golan, Scott Wilkinson, Adam G. Sowalsky, Sharon R. Pine, Carlos Caldas, James L. Gulley, Kenneth Aldape, Ranit Aharonov, Eric A. Stone & Eytan Ruppin
July, 2024
Advances in artificial intelligence have paved the way for leveraging hematoxylin and eosin-stained tumor slides for precision oncology. We present ENLIGHT–DeepPT, an indirect two-step approach consisting of DeepPT, a deep-learning framework that predicts genome-wide tumor mRNA expression from slides, and ENLIGHT, which predicts response to targeted and immune therapies from the inferred expression values. We show that DeepPT successfully predicts transcriptomics in all 16 The Cancer Genome Atlas cohorts tested and generalizes well to two independent datasets. ENLIGHT–DeepPT successfully predicts true responders in five independent patient cohorts involving four different treatments spanning six cancer types, with an overall odds ratio of 2.28 and a 39.5% increased response rate among predicted responders versus the baseline rate. Notably, its prediction accuracy, obtained without any training on the treatment data, is comparable to that achieved by directly predicting the response from the images, which requires specific training on the treatment evaluation cohorts.