MARSY: A multitask deep learning framework for prediction of drug combination synergy scores

Abstract

Motivation: Combination therapies have emerged as a treatment strategy for cancers to reduce the probability of drug resistance and to improve outcome. Large databases curating the results of many drug screening studies on preclinical cancer cell lines have been developed, capturing the synergistic and antagonistic effects of combination of drugs in different cell lines. However, due to the high cost of drug screening experiments and the sheer size of possible drug combinations, these databases are quite sparse. This necessitates the development of transductive computational models to accurately impute these missing values. Results: Here, we developed MARSY, a deep learning multi-task model that incorporates information on gene expression profile of cancer cell lines, as well as the differential expression signature induced by each drug to predict drug-pair synergy scores. By utilizing two encoders to capture the interplay between the drug-pairs, as well as the drug-pairs and cell lines, and by adding auxiliary tasks in the predictor, MARSY learns latent embeddings that improve the prediction performance compared to state-of-the-art and traditional machine learning models. Using MARSY, we then predicted the synergy scores of 133,722 new drug-pair cell line combinations, which we have made available to the community as part of this study. Moreover, we validated various insights obtained from these novel predictions using independent studies, confirming the ability of MARSY in making accurate novel predictions. Availability and Implementation: An implementation of the algorithms in Python and cleaned input datasets are provided in https://github.com/Emad-COMBINE-lab/MARSY.

Building A Foundation Model for Drug Synergy Analysis Powered by Large Language Models

“…Here we considered replacing the original embeddings in CPA with the embeddings from GPT 3.5, enlarging the accessibility for drug embeddings. for model evaluation based on datasets D1 [14] and D2 [17]. For classification, we included ROC-AUC (ROCAUC) and Accuracy (ACC) for model evaluation based on datasets D1 and D3 [18].…”

“…• MARSY [17]: MARSY is a DNN-based method with multi-task learning framework for drug synergistic effect prediction. This method can only handle the regression task.…”

“…Existing drug synergy prediction methods can be broadly classified into two groups. The first group of methods, such as MARSY [17], focus on predicting specific synergy scores, whereas the second group of methods, such as DeepDDs [18], transfer the continuous synergy score into a binary one via thresholding to infer drug combination synergy. However, most existing methods do not incorporate the extensive synergy information from public databases [19] in their predictions.…”

CODEX: COunterfactual Deep learning for thein-silicoEXploration of cancer cell line perturbations

“…MARSY [El Khili et al, 2023], which uses a drug-drug representation network combined with the latent representation learner of DeepSynergy.…”

Application of perturbation gene expression profiles in drug discovery—From mechanism of action to quantitative modelling

“…However, drug induced gene expression signatures contain more context specific biological information regarding drug effect than chemical structure, thus their application for drug synergy prediction can be beneficial. Using drug signatures has been used to predict synergistic effects of anticancer drugs (Bansal et al, 2014), and a recent benchmarking study showed that machine learning models using expression based features significantly outperform standard, chemical feature based methods (El Khili et al, 2022). Interestingly, several of these studies suggest that similarity between drug signatures is a strong predictor of synergistic drug effect (Diaz et al, 2020), suggesting drugs targeting the same pathway, but at different targets are generally more synergistic.…”