TY - JOUR
T1 - A Deep Learning Framework for Predicting Response to Therapy in Cancer
AU - Sakellaropoulos, Theodore
AU - Vougas, Konstantinos
AU - Narang, Sonali
AU - Koinis, Filippos
AU - Kotsinas, Athanassios
AU - Polyzos, Alexander
AU - Moss, Tyler J.
AU - Piha-Paul, Sarina
AU - Zhou, Hua
AU - Kardala, Eleni
AU - Damianidou, Eleni
AU - Alexopoulos, Leonidas G.
AU - Aifantis, Iannis
AU - Townsend, Paul A.
AU - Panayiotidis, Mihalis I.
AU - Sfikakis, Petros
AU - Bartek, Jiri
AU - Fitzgerald, Rebecca C.
AU - Thanos, Dimitris
AU - Mills Shaw, Kenna R.
AU - Petty, Russell
AU - Tsirigos, Aristotelis
AU - Gorgoulis, Vassilis G.
N1 - Financial support to V.G.G. and his team is from the European Union’s Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant 722729 (SYNTRAIN); the Welfare Foundation for Social & Cultural Sciences (KIKPE), Greece; Pentagon Biotechnology, UK; DeepMed IO, UK; and NKUA-SARG grants 70/3/9816 and 70/3/12128. J.B. is financially supported by the Novo Nordisk Foundation grant 16584, the Danish Cancer Society (R204-A12617), and the Swedish Cancerfonden (170176). Financial support to P.A.T. is from the Medical Research Council – MRC (Confidence in Concept to support Dr. Tom Jackson for early pilot data and a subsequent DTP studentship to P.A.T. and V.G.G.) and the infrastructure of Manchester Cancer Research Centre and CRUK Manchester Institute. Support to D.T. is from the KMW offsets program. A.T. and the NYU Applied Bioinformatics Laboratories (ABL) are partially supported by the Cancer Center Support Grant P30CA016087 at the Laura and Isaac Perlmutter Cancer Center. On behalf of the OCCAMS Consortium, we acknowledge that infrastructure was supported by Cancer Research UK (CRUK).
PY - 2019/12/10
Y1 - 2019/12/10
N2 - 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.
AB - 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.
KW - deep neural networks
KW - DNN
KW - drug response prediction
KW - machine learning
KW - precision medicine
UR - http://www.scopus.com/inward/record.url?scp=85076028003&partnerID=8YFLogxK
U2 - 10.1016/j.celrep.2019.11.017
DO - 10.1016/j.celrep.2019.11.017
M3 - Article
C2 - 31825821
AN - SCOPUS:85076028003
SN - 2211-1247
VL - 29
SP - 3367-3373.e4
JO - Cell Reports
JF - Cell Reports
IS - 11
ER -