| Literature DB >> 31825821 |
Theodore Sakellaropoulos1, Konstantinos Vougas2, Sonali Narang1, Filippos Koinis3, Athanassios Kotsinas3, Alexander Polyzos4, Tyler J Moss5, Sarina Piha-Paul6, Hua Zhou7, Eleni Kardala3, Eleni Damianidou3, Leonidas G Alexopoulos8, Iannis Aifantis1, Paul A Townsend9, Mihalis I Panayiotidis10, Petros Sfikakis11, Jiri Bartek12, Rebecca C Fitzgerald13, Dimitris Thanos14, Kenna R Mills Shaw5, Russell Petty15, Aristotelis Tsirigos16, Vassilis G Gorgoulis17.
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.Entities:
Keywords: DNN; deep neural networks; drug response prediction; machine learning; precision medicine
Mesh：
Year: 2019 PMID： 31825821 DOI： 10.1016/j.celrep.2019.11.017
Source DB: PubMed Journal: Cell Rep Impact factor: 9.423