A Deep Learning Framework for Predicting Response to Therapy in Cancer

Theodore Sakellaropoulos(NYU Langone’s Laura and Isaac Perlmutter Cancer Center), Konstantinos Vougas(National and Kapodistrian University of Athens), Sonali Narang(NYU Langone’s Laura and Isaac Perlmutter Cancer Center), Filippos Koinis(National and Kapodistrian University of Athens), Athanassios Kotsinas(National and Kapodistrian University of Athens), Alexander Polyzos(Cornell University), Tyler J. Moss(The University of Texas MD Anderson Cancer Center), Sarina A. Piha‐Paul(The University of Texas MD Anderson Cancer Center), Hua Zhou, Eleni Kardala(National and Kapodistrian University of Athens), Eleni Damianidou(National and Kapodistrian University of Athens), Leonidas G. Alexopoulos(National Technical University of Athens), Iannis Aifantis(NYU Langone’s Laura and Isaac Perlmutter Cancer Center), Paul A. Townsend(Manchester Academic Health Science Centre), Mihalis I. Panayiotidis(Northumbria University), Petros P. Sfikakis(National and Kapodistrian University of Athens), Jiří Bártek(Science for Life Laboratory), Rebecca C. Fitzgerald(University of Cambridge), Dimitris Thanos(Academy of Athens), Kenna Shaw(The University of Texas MD Anderson Cancer Center), Russell Petty(University of Dundee), Aristotelis Tsirigos(NYU Langone’s Laura and Isaac Perlmutter Cancer Center), Vassilis G. Gorgoulis(National and Kapodistrian University of Athens)
Cell Reports
December 1, 2019
Cited by 213Open Access
Full Text

Abstract

A major challenge in cancer treatment is predicting clinical response to anti-cancer drugs on a personalized basis. Using a pharmacogenomics database of 1,001 cancer cell lines, we trained deep neural networks for prediction of drug response and assessed their performance on multiple clinical cohorts. We demonstrate that deep neural networks outperform the current state in machine learning frameworks. We provide a proof of concept for the use of deep neural network-based frameworks to aid precision oncology strategies.


Related Papers

No related papers found

Powered by citation graph analysis