Deep learning for molecular design - a review of the state of the art

Abstract

In the space of only a few years, deep generative modeling has revolutionized how we think of artificial creativity, yielding autonomous systems which produce original images, music, and text. Inspired by these successes, researchers are now applying deep generative modeling techniques to the generation and optimization of molecules - in our review we found 45 papers on the subject published in the past two years. These works point to a future where such systems will be used to generate lead molecules, greatly reducing resources spent downstream synthesizing and characterizing bad leads in the lab. In this review we survey the increasingly complex landscape of models and representation schemes that have been proposed. The four classes of techniques we describe are recursive neural networks, autoencoders, generative adversarial networks, and reinforcement learning. After first discussing some of the mathematical fundamentals of each technique, we draw high level connections and comparisons with other techniques and expose the pros and cons of each. Several important high level themes emerge as a result of this work, including the shift away from the SMILES string representation of molecules towards more sophisticated representations such as graph grammars and 3D representations, the importance of reward function design, the need for better standards for benchmarking and testing, and the benefits of adversarial training and reinforcement learning over maximum likelihood based training.

24 pages, new title, published in RSC MSDE

References in corpus (14)

• Improving neural networks by preventing co-adaptation of feature detectors
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
• Multi-task Neural Networks for QSAR Predictions
• Grammar Variational Autoencoder
• A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules
• ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity?
• On the State of the Art of Evaluation in Neural Language Models
• Molecular Generation with Recurrent Neural Networks (RNNs)
• In silico generation of novel, drug-like chemical matter using the LSTM neural network
• Towards GAN Benchmarks Which Require Generalization
• Decoding Molecular Graph Embeddings with Reinforcement Learning
• The Chemical Space of B, N-substituted Polycyclic Aromatic Hydrocarbons: Combinatorial Enumeration and High-Throughput First-Principles Modeling
• Actively Learning what makes a Discrete Sequence Valid

Cited by in corpus (7)

• Exploring Chemical Space using Natural Language Processing Methodologies for Drug Discovery
• Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
• Physics-Informed Neural Networks for Nonhomogeneous Material Identification in Elasticity Imaging
• Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
• Graph Neural Networks for the Prediction of Substrate-Specific Organic Reaction Conditions
• Augmenting Molecular Images with Vector Representations as a Featurization Technique for Drug Classification
• Continuous Representation of Molecules Using Graph Variational Autoencoder