An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design

Abstract

As a promising tool to navigate in the vast chemical space, artificial intelligence (AI) is leveraged for drug design. From the year 2017 to 2021, the number of applications of several recent AI models (i.e. graph neural network (GNN), recurrent neural network (RNN), variation autoencoder (VAE), generative adversarial network (GAN), flow and reinforcement learning (RL)) in drug design increases significantly. Many relevant literature reviews exist. However, none of them provides an in-depth summary of many applications of the recent AI models in drug design. To complement the existing literature, this survey includes the theoretical development of the previously mentioned AI models and detailed summaries of 42 recent applications of AI in drug design. Concretely, 13 of them leverage GNN for molecular property prediction and 29 of them use RL and/or deep generative models for molecule generation and optimization. In most cases, the focus of the summary is the models, their variants, and modifications for specific tasks in drug design. Moreover, 60 additional applications of AI in molecule generation and optimization are briefly summarized in a table. Finally, this survey provides a holistic discussion of the abundant applications so that the tasks, potential solutions, and challenges in AI-based drug design become evident.

arXiv comment26 pages, 6 figures, 3 tables, 253 references

References in corpus (62)

• Semi-Supervised Classification with Graph Convolutional Networks
• Neural Message Passing for Quantum Chemistry
• On the difficulty of training Recurrent Neural Networks
• Geometric deep learning: going beyond Euclidean data
• A Critical Review of Recurrent Neural Networks for Sequence Learning
• Learning to Plan Chemical Syntheses
• Modeling polypharmacy side effects with graph convolutional networks
• Tutorial on Variational Autoencoders
• NICE: Non-linear Independent Components Estimation
• Variational Inference with Normalizing Flows
• Normalizing Flows: An Introduction and Review of Current Methods
• Convolutional Networks on Graphs for Learning Molecular Fingerprints
• Deep learning for molecular design - a review of the state of the art
• Density estimation using Real NVP
• Discriminative Embeddings of Latent Variable Models for Structured Data
• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• MolGAN: An implicit generative model for small molecular graphs
• Learning Deep Generative Models of Graphs
• How Powerful are Graph Neural Networks?
• A Tutorial on Bayesian Optimization
• Normalizing Flows for Probabilistic Modeling and Inference
• Autonomous discovery in the chemical sciences part II: Outlook
• Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
• Conditional molecular design with deep generative models
• Masked Autoregressive Flow for Density Estimation
• Wasserstein Auto-Encoders
• Exploring Chemical Space using Natural Language Processing Methodologies for Drug Discovery
• Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
• Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
• Multi-Objective Molecule Generation using Interpretable Substructures
• Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Space
• Learning Graph-Level Representation for Drug Discovery
• Optimizing Molecules using Efficient Queries from Property Evaluations
• Hierarchical, rotation-equivariant neural networks to select structural models of protein complexes
• MolecularRNN: Generating realistic molecular graphs with optimized properties
• A Two-Step Graph Convolutional Decoder for Molecule Generation
• Equivariant Graph Neural Networks for 3D Macromolecular Structure
• Molecular Hypergraph Grammar with its Application to Molecular Optimization
• Monte Carlo Tree Search: A Review of Recent Modifications and Applications
• Learning to Extend Molecular Scaffolds with Structural Motifs
• Hierarchical Inter-Message Passing for Learning on Molecular Graphs
• DeepGS: Deep Representation Learning of Graphs and Sequences for Drug-Target Binding Affinity Prediction
• Graph Residual Flow for Molecular Graph Generation
• Edge-based sequential graph generation with recurrent neural networks
• Decoding Molecular Graph Embeddings with Reinforcement Learning
• GraphDF: A Discrete Flow Model for Molecular Graph Generation
• JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design
• Meta-Learning GNN Initializations for Low-Resource Molecular Property Prediction
• Drug-Target Interaction Prediction with Graph Attention networks
• Message Passing Networks for Molecules with Tetrahedral Chirality
• Reinforced Molecular Optimization with Neighborhood-Controlled Grammars
• Quantum Generative Models for Small Molecule Drug Discovery
• Learning a Continuous Representation of 3D Molecular Structures with Deep Generative Models
• Adversarial Learned Molecular Graph Inference and Generation
• Symmetry-Aware Actor-Critic for 3D Molecular Design
• Artificial Intelligence in Drug Discovery: Applications and Techniques
• Tiered Latent Representations and Latent Spaces for Molecular Graphs
• Learning Latent Space Energy-Based Prior Model for Molecule Generation
• A Systematic Assessment of Deep Learning Models for Molecule Generation
• ChemoVerse: Manifold traversal of latent spaces for novel molecule discovery
• Goal directed molecule generation using Monte Carlo Tree Search
• Graph Energy-based Model for Substructure Preserving Molecular Design