Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science

Austin Cheng, Cher Tian Ser, Marta Skreta, Andrés Guzmán-Cordero, Luca Thiede, Andreas Burger, Abdulrahman Aldossary, Shi Xuan Leong, Sergio Pablo-García, Felix Strieth-Kalthoff, Alán Aspuru-Guzik

TL;DR

Current applications across a diversity of problems in chemistry are outlined and how machine learning researchers view and approach problems in the field are discussed.

Abstract

Machine learning has been pervasively touching many fields of science. Chemistry and materials science are no exception. While machine learning has been making a great impact, it is still not reaching its full potential or maturity. In this perspective, we first outline current applications across a diversity of problems in chemistry. Then, we discuss how machine learning researchers view and approach problems in the field. Finally, we provide our considerations for maximizing impact when researching machine learning for chemistry.

Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science

TL;DR

Current applications across a diversity of problems in chemistry are outlined and how machine learning researchers view and approach problems in the field are discussed.

Abstract

Machine learning has been pervasively touching many fields of science. Chemistry and materials science are no exception. While machine learning has been making a great impact, it is still not reaching its full potential or maturity. In this perspective, we first outline current applications across a diversity of problems in chemistry. Then, we discuss how machine learning researchers view and approach problems in the field. Finally, we provide our considerations for maximizing impact when researching machine learning for chemistry.
Paper Structure (55 sections, 1 figure, 1 table)

This paper contains 55 sections, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Chemistry meets data: A taxonomy of problems
  3. Structure to property: property prediction
  4. Cheminformatics and quantitative structure-activity relationships.
  5. Representing molecules with expert descriptors.
  6. Learned chemical representations.
  7. Limits and open problems.
  8. Property to structure: designing molecules in chemical space
  9. Virtual screening.
  10. Generative models for inverse design.
  11. Limits and open problems.
  12. Structure to structure: synthesis planning and reaction condition prediction
  13. Synthesis planning.
  14. Prediction and optimization of reaction conditions.
  15. Limits and open problems.
  16. ...and 40 more sections

Figures (1)

  • Figure 1: A taxonomy of chemical problems related to machine learning. Each arrow indicates an application of ML and signifies how all these relate to each other. Foundation models and self-driving labs touch all these areas.