Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
Автоматическое проектирование химических соединений с использованием управляемого данными непрерывного представления молекул
2018-01-12
SCID: 54.1/4ws6fbd8
Discuss with AI
continuous molecular representationdeep neural networkdrug-like moleculeslatent space optimizationmolecular property prediction
Figures from the paper
Abstract (AI)
We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration and optimization through open-ended spaces of chemical compounds. A deep neural network was trained on hundreds of thousands of existing chemical structures to construct three coupled functions: an encoder, a decoder, and a predictor. The encoder converts the discrete representation of a molecule into a real-valued continuous vector, and the decoder converts these continuous vectors back to discrete molecular representations. The predictor estimates chemical properties from the latent continuous vector representation of the molecule. Continuous representations of molecules allow us to automatically generate novel chemical structures by performing simple operations in the latent space, such as decoding random vectors, perturbing known chemical structures, or interpolating between molecules. Continuous representations also allow the use of powerful gradient-based optimization to efficiently guide the search for optimized functional compounds. We demonstrate our method in the domain of drug-like molecules and also in a set of molecules with fewer that nine heavy atoms.
Key Findings
1
A deep neural network learns coupled encoder, decoder, and predictor functions that map molecular structures into and out of a multidimensional continuous latent space.
2
Latent-space representations support gradient-based optimization for efficiently searching chemical compounds with improved predicted properties.
3
The approach enables open-ended exploration and optimization across chemical compound spaces from discrete molecular representations.
4
The continuous representation enables generation of novel molecules through random-vector decoding, perturbation of known molecules, and interpolation between molecular structures.
5
The method is demonstrated on drug-like molecules and molecules containing fewer than nine heavy atoms.
Research Object
drug-like molecules and molecules with fewer than nine heavy atoms
Research Subject
automatic generation, exploration, and gradient-based optimization of novel chemical structures using their continuous latent-space representations
Publication Details
Publication Date
2018-01-12
Journal
Publisher
ISSN
Cited by
4548
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai6
Sequence to Sequence Learning with Neural Networks2014
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling2014
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks2015
Gaussian Processes for Machine Learning2005
MoleculeNet: a benchmark for molecular machine learning2017
Quantum chemistry structures and properties of 134 kilo molecules2014
Cited by20
A Comprehensive Survey on Graph Neural Networks2020
MoleculeNet: a benchmark for molecular machine learning2017
The rise of deep learning in drug discovery2018
Machine learning in materials science2019
Machine Learning Interatomic Potentials as Emerging Tools for Materials Science2019
Tackling Climate Change with Machine Learning2022
DScribe: Library of descriptors for machine learning in materials science2019
Augmenting large language models with chemistry tools2024
Accelerating the discovery of materials for clean energy in the era of smart automation2018
Self-Driving Laboratories for Chemistry and Materials Science2024
The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies2023
Machine Learning Methods for Small Data Challenges in Molecular Science2023
Artificial intelligence in drug discovery: recent advances and future perspectives2021
Computer-Aided Drug Design and Drug Discovery: A Prospective Analysis2023
Artificial Intelligence and Machine Learning Technology Driven Modern Drug Discovery and Development2023
Graph Neural Networks for Natural Language Processing: A Survey2023
A review of large language models and autonomous agents in chemistry2024
Transformer neural network for protein-specific de novo drug generation as a machine translation problem2021
TITAN: T-cell receptor specificity prediction with bimodal attention networks2021
Predictive chemistry: machine learning for reaction deployment, reaction development, and reaction discovery2022