Search

The powerful combination of large-scale drug-related interaction networks and deep learning provides new opportunities for accelerating the process of drug discovery. However, chemical structures that play an important role in drug properties and high-order relations that involve a greater number of nodes are not tackled in current biomedical networks. In this study, we present a general hypergraph learning framework, which introduces Drug-Substructures relationship into Molecular interaction Networks to construct the micro-to-macro drug centric heterogeneous network (DSMN), and develop a multi-branches HyperGraph learning model, called HGDrug, for Drug multi-task predictions. HGDrug achieves highly accurate and robust predictions on 4 benchmark tasks (drug-drug, drug-target, drug-disease, and drug-side-effect interactions), outperforming 8 state-of-the-art task specific models and 6 general-purpose conventional models. Experiments analysis verifies the effectiveness and rationality of the HGDrug model architecture as well as the multi-branches setup, and demonstrates that HGDrug is able to capture the relations between drugs associated with the same functional groups. In addition, our proposed drug-substructure interaction networks can help improve the performance of existing network models for drug-related prediction tasks. Author summary: Drugs containing the same functional groups may have similar pharmacochemical properties. However, how to effectively combine chemical information of drugs from molecular fragments containing functional groups into the biomolecular network is challenging and rarely explored. we decompose drugs' SMILES string and construct a drug-centric heterogeneous network that integrates drug substructure and molecular interactions information. Based on the heterogeneous network, we proposed an end-to-end hypergraph attention network framework for the drug multi-task predictions, termed as HGDrug. The efficiency and generalization of the proposed HGDrug have been demonstrated by the state-of-the-art performance in four drug-related interaction predictions tasks with huge improvement compared to previous general-purpose classical models and task-specific models. In addition, HGDrug can effectively identify potential drug-related interactions and the drug-sub-structure networks are able to help to improve the performance of other GNN models. These conclusions present important insights on how to introduce the drug' substructure information for multiple drug-related interactions tasks on biomedical networks. In summary, HGDrug offers a general and powerful tool for the identification of drug-related interactions by constructing the micro-to-macro drug-centric heterogeneous network. [ABSTRACT FROM AUTHOR]

Current methods of molecular image-based drug discovery face two major challenges: (1) work effectively in absence of labels, and (2) capture chemical structure from implicitly encoded images. Given that chemical structures are explicitly encoded by molecular graphs (such as nitrogen, benzene rings and double bonds), we leverage self-supervised contrastive learning to transfer chemical knowledge from graphs to images. Specifically, we propose a novel Contrastive Graph-Image Pre-training (CGIP) framework for molecular representation learning, which learns explicit information in graphs and implicit information in images from large-scale unlabeled molecules via carefully designed intra- and inter-modal contrastive learning. We evaluate the performance of CGIP on multiple experimental settings (molecular property prediction, cross-modal retrieval and distribution similarity), and the results show that CGIP can achieve state-of-the-art performance on all 12 benchmark datasets and demonstrate that CGIP transfers chemical knowledge in graphs to molecular images, enabling image encoder to perceive chemical structures in images. We hope this simple and effective framework will inspire people to think about the value of image for molecular representation learning. [ABSTRACT FROM AUTHOR]

Informative representation of molecules is a crucial prerequisite in AI-driven drug design and discovery. Pharmacophore information including functional groups and chemical reactions can indicate molecular properties, which have not been fully exploited by prior atom-based molecular graph representation. To obtain a more informative representation of molecules for better molecule property prediction, we propose the Pharmacophoric-constrained Heterogeneous Graph Transformer (PharmHGT). We design a pharmacophoric-constrained multi-views molecular representation graph, enabling PharmHGT to extract vital chemical information from functional substructures and chemical reactions. With a carefully designed pharmacophoric-constrained multi-view molecular representation graph, PharmHGT can learn more chemical information from molecular functional substructures and chemical reaction information. Extensive downstream experiments prove that PharmHGT achieves remarkably superior performance over the state-of-the-art models the performance of our model is up to 1.55% in ROC-AUC and 0.272 in RMSE higher than the best baseline model) on molecular properties prediction. The ablation study and case study show that our proposed molecular graph representation method and heterogeneous graph transformer model can better capture the pharmacophoric structure and chemical information features. Further visualization studies also indicated a better representation capacity achieved by our model. Informative molecular representation is a vital prerequisite in artificial intelligence-driven de novo drug discovery, however, mapping the pharmacophoric information is underexploited by the atom-level based molecular graph representation. Here, the authors design a multi-level based Pharmacophoric-constrained heterogeneous graph transformer (PharmHGT) to better capture the pharmacophore structure and chemical information. [ABSTRACT FROM AUTHOR]