Generative Models for Automatic Chemical Design

Abstract

Materials discovery is decisive for tackling urgent challenges related to energy, the environment, health care and many others. In chemistry, conventional methodologies for innovation usually rely on expensive and incremental strategies to optimize properties from molecular structures. On the other hand, inverse approaches map properties to structures, thus expediting the design of novel useful compounds. In this chapter, we examine the way in which current deep generative models are addressing the inverse chemical discovery paradigm. We begin by revisiting early inverse design algorithms. Then, we introduce generative models for molecular systems and categorize them according to their architecture and molecular representation. Using this classification, we review the evolution and performance of important molecular generation schemes reported in the literature. Finally, we conclude highlighting the prospects and challenges of generative models as cutting edge tools in materials discovery.

References in corpus (68)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Neural Message Passing for Quantum Chemistry
• WaveNet: A Generative Model for Raw Audio
• Categorical Reparameterization with Gumbel-Softmax
• Automatic chemical design using a data-driven continuous representation of molecules
• Spectral Networks and Locally Connected Networks on Graphs
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Conditional Image Generation with PixelCNN Decoders
• Two-dimensional materials from high-throughput computational exfoliation of experimentally known compounds
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Pixel Recurrent Neural Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Improved Training of Wasserstein GANs
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• Deep Reinforcement Learning for De-Novo Drug Design
• Energy-based Generative Adversarial Network
• Variational Graph Auto-Encoders
• Generating Videos with Scene Dynamics
• GuacaMol: Benchmarking Models for De Novo Molecular Design
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Adversarial Feature Learning
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• MolGAN: An implicit generative model for small molecular graphs
• Learning Deep Generative Models of Graphs
• A note on the evaluation of generative models
• How Powerful are Graph Neural Networks?
• SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
• SMILES Enumeration as Data Augmentation for Neural Network Modeling of Molecules
• Neural Machine Translation in Linear Time
• DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
• Syntax-Directed Variational Autoencoder for Structured Data
• Mode Regularized Generative Adversarial Networks
• Conditional molecular design with deep generative models
• GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
• NetGAN: Generating Graphs via Random Walks
• Wasserstein Auto-Encoders
• Least Squares Generative Adversarial Networks
• Grammar Variational Autoencoder
• Boundary-Seeking Generative Adversarial Networks
• N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
• Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network
• Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules
• PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications
• Genetic Design of Enhanced Valley Splitting towards a Spin Qubit in Silicon
• DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation
• Variational auto-encoding of protein sequences
• Atomistic structure learning
• All SMILES Variational Autoencoder
• A gradient-directed Monte Carlo approach to molecular design
• Graphite: Iterative Generative Modeling of Graphs
• In silico generation of novel, drug-like chemical matter using the LSTM neural network
• Multi-Objective De Novo Drug Design with Conditional Graph Generative Model
• Distance Metric Learning using Graph Convolutional Networks: Application to Functional Brain Networks
• Generating equilibrium molecules with deep neural networks
• Invertible and Non-invertible Alloy Ising Models
• Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models
• A Model to Search for Synthesizable Molecules
• PHOENICS: A universal deep Bayesian optimizer
• Attentional Multilabel Learning over Graphs: A Message Passing Approach
• Leveraging binding-site structure for drug discovery with point-cloud methods
• Machine Learning of coarse-grained Molecular Dynamics Force Fields
• Comparing large-scale graphs based on quantum probability theory

Cited by in corpus (19)

• Autonomous discovery in the chemical sciences part II: Outlook
• Perspective on integrating machine learning into computational chemistry and materials science
• Constrained crystals deep convolutional generative adversarial network for the inverse design of crystal structures
• Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
• Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
• Machine learning-assisted design of material properties
• Constrained Bayesian Optimization for Automatic Chemical Design
• MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
• Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
• Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design
• Study of Deep Generative Models for Inorganic Chemical Compositions
• Automated patent extraction powers generative modeling in focused chemical spaces
• Molecular Dipole Moment Learning via Rotationally Equivariant Gaussian Process Regression with Derivatives in Molecular-orbital-based Machine Learning
• Enhanced sampling of robust molecular datasets with uncertainty-based collective variables
• Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spaces
• Molecular design method based on novel molecular representation and variational auto-encoder
• A Generative Diffusion Model for Amorphous Materials
• Quantum Chemistry Driven Molecular Inverse Design with Data-free Reinforcement Learning
• The Quantum Ensemble Variational Optimization Algorithm: Applications to Molecular Inverse Design