Combination therapy has been widely applied in the treatment of complex diseases due to its ability to improve efficacy and reduce drug resistance. In recent years, deep learning techniques have significantly enhanced the accuracy of computational models for predicting drug interactions. However, these methods either focus solely on the molecular structure of drugs and the gene expression of cell lines or consider only the interaction networks related to drugs and cell lines. To effectively explore the combined impact of the structural information of drugs and cell lines and their interaction information in networks on drug synergy prediction, we propose a novel multimodal representation fusion model using hypergraph neural networks, called MoHyperSynergy. MoHyperSynergy constructs a hypergraph based on multimodal representations using the K-nearest neighbors approach. It interacts multimodal representations at the local feature level through an outer product embedding layer and fuses multimodal representations at the global semantic level using a hypergraph neural network, effectively utilizing information from different modalities of drugs and cell lines. MoHyperSynergy simultaneously extracts initial representations from drug molecular structures, cell line gene expressions, and the embeddings of drugs and cell lines in biomedical knowledge graphs as different modalities, and pretrains the model’s representation extractors in a self-supervised manner. We conducted experiments on real-world public datasets and evaluated our model under various scenarios that may arise in practical applications. The experimental results show that MoHyperSynergy achieves excellent performance in predicting drug synergy and significantly outperforms the current state-of-the-art models.

MOTIVATION: In the field of drug discovery, accurately and effectively predicting the binding affinity between proteins and ligands is crucial for drug screening and optimization. However, current research primarily utilizes representations based on sequence or structure to predict protein-ligand binding affinity, with relatively less study on protein surface information, which is crucial for protein-ligand interactions. Moreover, when dealing with multimodal information of proteins, traditional approaches typically concatenate features from different modalities in a straightforward manner without considering the heterogeneity among them, which results in an inability to effectively exploit the complementary between modalities. RESULTS: We introduce a novel multimodal feature extraction (MFE) framework that, for the first time, incorporates information from protein surfaces, 3D structures, and sequences, and uses cross-attention mechanism for feature alignment between different modalities. Experimental results show that our method achieves state-of-the-art performance in predicting protein-ligand binding affinity. Furthermore, we conduct ablation studies that demonstrate the effectiveness and necessity of protein surface information and multimodal feature alignment within the framework. AVAILABILITY AND IMPLEMENTATION: The source code and data are available at https://github.com/Sultans0fSwing/MFE.

MOTIVATION: Molecular representation learning plays an indispensable role in crucial tasks such as property prediction and drug design. Despite the notable achievements of molecular pre-training models, current methods often fail to capture both the structural and feature semantics of molecular graphs. Moreover, while graph contrastive learning has unveiled new prospects, existing augmentation techniques often struggle to retain their core semantics. To overcome these limitations, we propose a gradient-compensated encoder parameter perturbation approach, ensuring efficient and stable feature augmentation. By merging enhancement strategies grounded in attribute masking and parameter perturbation, we introduce MoleMCL, a new MOLEcular pre-training model based on multi-level contrastive learning. RESULTS: Experimental results demonstrate that MoleMCL adeptly dissects the structure and feature semantics of molecular graphs, surpassing current state-of-the-art models in molecular prediction tasks, paving a novel avenue for molecular modeling. AVAILABILITY AND IMPLEMENTATION: The code and data underlying this work are available in GitHub at https://github.com/BioSequenceAnalysis/MoleMCL.