Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction

Abstract

Recent advances and achievements of artificial intelligence (AI) as well as deep and graph learning models have established their usefulness in biomedical applications, especially in drug-drug interactions (DDIs). DDIs refer to a change in the effect of one drug to the presence of another drug in the human body, which plays an essential role in drug discovery and clinical research. DDIs prediction through traditional clinical trials and experiments is an expensive and time-consuming process. To correctly apply the advanced AI and deep learning, the developer and user meet various challenges such as the availability and encoding of data resources, and the design of computational methods. This review summarizes chemical structure based, network based, NLP based and hybrid methods, providing an updated and accessible guide to the broad researchers and development community with different domain knowledge. We introduce widely-used molecular representation and describe the theoretical frameworks of graph neural network models for representing molecular structures. We present the advantages and disadvantages of deep and graph learning methods by performing comparative experiments. We discuss the potential technical challenges and highlight future directions of deep and graph learning models for accelerating DDIs prediction.

arXiv commentAccepted by Briefings in Bioinformatics

References in corpus (19)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Sequence to Sequence Learning with Neural Networks
• DeepWalk: Online Learning of Social Representations
• BioBERT: a pre-trained biomedical language representation model for biomedical text mining
• LINE: Large-scale Information Network Embedding
• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Modeling polypharmacy side effects with graph convolutional networks
• struc2vec: Learning Node Representations from Structural Identity
• Knowledge Graph Convolutional Networks for Recommender Systems
• Molecular Contrastive Learning of Representations via Graph Neural Networks
• MolTrans: Molecular Interaction Transformer for Drug Target Interaction Prediction
• ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction
• Graph Transformer Networks
• Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations
• SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization
• A Review of Biomedical Datasets Relating to Drug Discovery: A Knowledge Graph Perspective
• Drug-Drug Adverse Effect Prediction with Graph Co-Attention
• GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles
• Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks

Cited by in corpus (3)

• Learning to Denoise Biomedical Knowledge Graph for Robust Molecular Interaction Prediction
• LLMs for Drug-Drug Interaction Prediction: A Comprehensive Comparison
• A Multi-Scale Graph Neural Process with Cross-Drug Co-Attention for Drug-Drug Interactions Prediction