DeepSynergy: predicting anti-cancer drug synergy with Deep Learning

Abstract

MotivationWhile drug combination therapies are a well-established concept in cancer treatment, identifying novel synergistic combinations is challenging due to the size of combinatorial space. However, computational approaches have emerged as a time- and cost-efficient way to prioritize combinations to test, based on recently available large-scale combination screening data. Recently, Deep Learning has had an impact in many research areas by achieving new state-of-the-art model performance. However, Deep Learning has not yet been applied to drug synergy prediction, which is the approach we present here, termed DeepSynergy. DeepSynergy uses chemical and genomic information as input information, a normalization strategy to account for input data heterogeneity, and conical layers to model drug synergies.ResultsDeepSynergy was compared to other machine learning methods such as Gradient Boosting Machines, Random Forests, Support Vector Machines and Elastic Nets on the largest publicly available synergy dataset with respect to mean squared error. DeepSynergy significantly outperformed the other methods with an improvement of 7.2% over the second best method at the prediction of novel drug combinations within the space of explored drugs and cell lines. At this task, the mean Pearson correlation coefficient between the measured and the predicted values of DeepSynergy was 0.73. Applying DeepSynergy for classification of these novel drug combinations resulted in a high predictive performance of an AUC of 0.90. Furthermore, we found that all compared methods exhibit low predictive performance when extrapolating to unexplored drugs or cell lines, which we suggest is due to limitations in the size and diversity of the dataset. We envision that DeepSynergy could be a valuable tool for selecting novel synergistic drug combinations.Availability and implementationDeepSynergy is available via www.bioinf.jku.at/software/DeepSynergy.Supplementary information Supplementary data are available at Bioinformatics online.

Deciphering the combinatorial interaction landscape

“…We obtained global insight into the principles and functions of interactions from analysis of the landscape, and validated new hypotheses about combinatorial cytokine effects. Developing learning models to predict synergistic combinations of treatments based on the individual effects is an active area of research [18][19][20][21] . Despite an apparent methodological similarity, the motivation and goals of our framework are fundamentally different from these studies.…”

Machine Learning for Cancer Drug Combination

“…DL utilizes multiple, or “deep” nonlinear layers to progressively extract high‐level features from the input. DeepSynergy is an example of how DL can be used for predicting drug combination synergy ( Figure b ). DeepSynergy accepts both cell line‐specific genomic profiles and compound‐specific chemo‐informatic features as inputs—the latter input was not provided in the previous DREAM challenge.…”

“…Hidden prior knowledge is often crucial for developing a powerful prediction model and a better understanding of the mechanism underlying drug synergism. For instance, Li et al 2 leveraged prior information of the gene-gene interaction network and drug target genes to improve prediction accuracy, and, in DeepSynergy, 3 both genomic profiles and chemical compounds were considered. However, it remains unknown to what extent the hidden biological information is needed to perfectly predict drug synergy.…”

A reference model for the combination of an arbitrary number of drugs: A generalization of the Bliss independence model

“…Although an arbitrary number of drugs is involved, the description of the reference model is still similar to the dose-response curve of a single drug, cf. (14), although, of course, the parameters are different.…”