Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions

Abstract

The optimal design of compounds through manipulating properties at the molecular level is often the key to considerable scientific advances and improved process systems performance. This paper highlights key trends, challenges, and opportunities underpinning the Computer-Aided Molecular Design (CAMD) problems. A brief review of knowledge-driven property estimation methods and solution techniques, as well as corresponding CAMD tools and applications, are first presented. In view of the computational challenges plaguing knowledge-based methods and techniques, we survey the current state-of-the-art applications of deep learning to molecular design as a fertile approach towards overcoming computational limitations and navigating uncharted territories of the chemical space. The main focus of the survey is given to deep generative modeling of molecules under various deep learning architectures and different molecular representations. Further, the importance of benchmarking and empirical rigor in building deep learning models is spotlighted. The review article also presents a detailed discussion of the current perspectives and challenges of knowledge-based and data-driven CAMD and identifies key areas for future research directions. Special emphasis is on the fertile avenue of hybrid modeling paradigm, in which deep learning approaches are exploited while leveraging the accumulated wealth of knowledge-driven CAMD methods and tools.

References in corpus (51)

• Auto-Encoding Variational Bayes
• Sequence to Sequence Learning with Neural Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Natural Language Processing (almost) from Scratch
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Automatic chemical design using a data-driven continuous representation of molecules
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
• Asynchronous Methods for Deep Reinforcement Learning
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Semi-Supervised Learning with Deep Generative Models
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Improved Techniques for Training GANs
• An Introduction to Deep Reinforcement Learning
• Deep Reinforcement Learning for De-Novo Drug Design
• Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
• GuacaMol: Benchmarking Models for De Novo Molecular Design
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• Deep learning for molecular design - a review of the state of the art
• Machine learning prediction errors better than DFT accuracy
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• 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
• Optimization under Uncertainty in the Era of Big Data and Deep Learning: When Machine Learning Meets Mathematical Programming
• Constrained Graph Variational Autoencoders for Molecule Design
• Adversarial Autoencoders
• A General Framework for Uncertainty Estimation in Deep Learning
• Mol-CycleGAN - a generative model for molecular optimization
• Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• Computer-aided molecular design: An introduction and review of tools, applications, and solution techniques
• A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
• Conditional molecular design with deep generative models
• Improving Chemical Autoencoder Latent Space and Molecular De novo Generation Diversity with Heteroencoders
• Input Convex Neural Networks
• Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets
• Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
• Toward Controlled Generation of Text
• Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations
• Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models
• ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity?
• Adversarial Generation of Natural Language
• Generative Models for Automatic Chemical Design
• Multi-Objective Deep Reinforcement Learning
• Connecting Generative Adversarial Networks and Actor-Critic Methods
• GraphNVP: An Invertible Flow Model for Generating Molecular Graphs
• Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
• Deep Learning for Computational Chemistry

Cited by in corpus (6)

• Computer-Aided Multi-Objective Optimization in Small Molecule Discovery
• Generative AI and Process Systems Engineering: The Next Frontier
• Graph Machine Learning for Design of High-Octane Fuels
• Graphical Gaussian Process Regression Model for Aqueous Solvation Free Energy Prediction of Organic Molecules in Redox Flow Battery
• Predicting performance-related properties of refrigerant based on tailored small-molecule functional group contribution
• An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design