Dual Representation Learning for Predicting Drug-Side Effect Frequency Using Protein Target Information

Knowledge of unintended effects of drugs is critical in assessing the risk of treatment and in drug repurposing. Although numerous existing studies predict drug-side effect presence, only four of them predict the frequency of the side effects. Unfortunately, current prediction methods 1) do not utilize drug targets, 2) do not predict well for unseen drugs, and 3) do not use multiple heterogeneous drug features. We propose a novel deep learning-based drug-side effect frequency prediction model. Our model utilized heterogeneous features such as target protein information as well as molecular graph, fingerprints, and chemical similarity to create drug embeddings simultaneously. Furthermore, the model represents drugs and side effects into a common vector space, learning the dual representation vectors of drugs and side effects, respectively. We also extended the predictive power of our model to compensate for the drugs without clear target proteins using the Adaboost method. We achieved state-of-the-art performance over the existing methods in predicting side effect frequencies, especially for unseen drugs. Ablation studies show that our model effectively combines and utilizes heterogeneous features of drugs. Moreover, we observed that, when the target information given, drugs with explicit targets resulted in better prediction than the drugs without explicit targets.

Authors

• Sungjoon Park
• Sangseon Lee
• Minwoo Pak
• Sun Kim Interdisciplinary Program in Bioinformatics, Seoul National University AIGENDRUG Co., Ltd. Department of Computer Science and Engineering, Seoul National University Interdisciplinary Program in Artificial Intelligence, Seoul National University

Keywords

• Drugs
• Predictive models
• Proteins
• Bioinformatics
• Protein engineering
• Chemicals
• Databases
• Target Proteins
• Target Information
• Dual Representation
• Dual Learning
• Protein Target Information
• Side Effects
• Drug Targets
• Unintended Consequences
• Frequency Of Events
• Heterogeneous Characteristics
• Chemical Similarity
• Common Space
• Drug Repurposing
• Molecular Fingerprints
• Drug Features
• Deep Learning-based Models
• Molecular Graph
• Explicit Target
• Frequency Of Side Effects
• Graph Attention Network
• Number Of Side Effects
• Drug Target Proteins
• Drug Group
• Number Of Drugs
• Medical Dictionary For Regulatory Activities
• Drug Information
• Nervous System Drugs
• Weight Matrix Of Layer
• Network Propagation
• Drug-side effect frequency
• dual represen- tation learning
• adverse drug reaction
• drug target protein
• Humans
• Deep Learning
• Drug-Related Side Effects and Adverse Reactions
• Computational Biology