Putting Chemical Knowledge to Work in Machine Learning for Reactivity


Loading...

Author / Producer

Date

2023-02-22

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Machine learning has been used to study chemical reactivity for a long time in fields such as physical organic chemistry, chemometrics and cheminformatics. Recent advances in computer science have resulted in deep neural networks that can learn directly from the molecular structure. Neural networks are a good choice when large amounts of data are available. However, many datasets in chemistry are small, and models utilizing chemical knowledge are required for good performance. Adding chemical knowledge can be achieved either by adding more information about the molecules or by adjusting the model architecture itself. The current method of choice for adding more information is descriptors based on computed quantum-chemical properties. Exciting new research directions show that it is possible to augment deep learning with such descriptors for better per formance in the low-data regime. To modify the models, differentiable programming enables seamless merging of neural networks with mathematical models from chemistry and physics. The resulting methods are also more data-efficient and make better predictions for molecules that are different from the initial dataset on which they were trained. Application of these chemistry-informed machine learning methods promise to accelerate research in fields such as drug design, materials design, catalysis and reactivity.

Publication status

published

Editor

Book title

Journal / series

Volume

77 (1/2)

Pages / Article No.

22 - 30

Publisher

Swiss Chemical Society

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Digital chemistry; Machine learning; Reactivity

Organisational unit

09781 - Jorner, Kjell / Jorner, Kjell check_circle

Notes

Funding

Related publications and datasets