A systematic evaluation of deep learning methods for the prediction of drug synergy in cancer

Abstract

One of the main obstacles to the successful treatment of cancer is the phenomenon of drug resistance. A common strategy to overcome resistance is the use of combination therapies. However, the space of possibilities is huge and efficient search strategies are required. Machine Learning (ML) can be a useful tool for the discovery of novel, clinically relevant anti-cancer drug combinations. In particular, deep learning (DL) has become a popular choice for modeling drug combination effects. Here, we set out to examine the impact of different methodological choices on the performance of multimodal DL-based drug synergy prediction methods, including the use of different input data types, preprocessing steps and model architectures. Focusing on the NCI ALMANAC dataset, we found that feature selection based on prior biological knowledge has a positive impact—limiting gene expression data to cancer or drug response-specific genes improved performance. Drug features appeared to be more predictive of drug response, with a 41% increase in coefficient of determination (R2) and 26% increase in Spearman correlation relative to a baseline model that used only cell line and drug identifiers. Molecular fingerprint-based drug representations performed slightly better than learned representations—ECFP4 fingerprints increased R2 by 5.3% and Spearman correlation by 2.8% w.r.t the best learned representations. In general, fully connected feature-encoding subnetworks outperformed other architectures. DL outperformed other ML methods by more than 35% (R2) and 14% (Spearman). Additionally, an ensemble combining the top DL and ML models improved performance by about 6.5% (R2) and 4% (Spearman). Using a state-of-the-art interpretability method, we showed that DL models can learn to associate drug and cell line features with drug response in a biologically meaningful way. The strategies explored in this study will help to improve the development of computational methods for the rational design of effective drug combinations for cancer therapy.

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

“…For classification, we included ROC-AUC (ROCAUC) and Accuracy (ACC) for model evaluation based on datasets D1 and D3 [18]. These metrics and datasets were widely used in the related work [14,17,18,37,38]. We selected seven other methods (DeepSynergy, MARSY, TreeComb, SVM [39,40], TabNet [41], BERT [42] and Lasso [40,43]) for benchmarking the regression task and seven methods (DeepSynergy, DeepDDs, TreeComb, SVC, TabNet, BERT and Lasso) for benchmarking the classification task.…”

Optimized models and deep learning methods for drug response prediction in cancer treatments: a review

“…However, these drug response datasets are complex and have many dimensions ( Zampieri et al, 2019 ). The intricate nature of (DRP) problems necessitates the utilization of progressively intricate (DL) architectures, leading to a substantial augmentation in the number of learnable parameters, as observed by Baptista, Ferreira & Rocha (2023) . Learning continuous representations of compounds of the drug is limited since most methods need to pay more attention to the Graph convolutions ( Sun, 2020 ).…”

“…The intricate nature of (DRP) problems necessitates the utilization of progressively intricate (DL) architectures, leading to a substantial augmentation in the number of learnable parameters, as observed by Baptista, Ferreira & Rocha (2023) .…”

MMSyn: A New Multimodal Deep Learning Framework for Enhanced Prediction of Synergistic Drug Combinations

“…In regression methods, the model is trained by minimizing the distance between the predicted and true synergistic scores to predict the quantitative synergistic score of a drug combination. Generally, DL-based methods for synergistic drug combination prediction first derive feature representations of drugs and cell lines, and then these features are input into the prediction network . The performance of the prediction model depends on the quality of the feature extraction .…”

“…Generally, DL-based methods for synergistic drug combination prediction first derive feature representations of drugs and cell lines, and then these features are input into the prediction network. 28 The performance of the prediction model depends on the quality of the feature extraction. 29 Handcrafted features, such as rule-based molecular fingerprints and descriptors, are commonly used as drug representations during early research.…”