Timezone: »

 
GAUCHE: A Library for Gaussian Processes in Chemistry
Ryan-Rhys Griffiths · Leo Klarner · Henry Moss · Aditya Ravuri · Sang Truong · Yuanqi Du · Arian Jamasb · Julius Schwartz · Austin Tripp · Bojana Ranković · Philippe Schwaller · Gregory Kell · Anthony Bourached · Alexander Chan · Jacob Moss · Chengzhi Guo · Alpha Lee · Jian Tang

@
in AI for Science »
Event URL: https://openreview.net/forum?id=i9MKI7zrWal »

We introduce GAUCHE, a library for GAUssian processes in CHEmistry. Gaussian processes have long been a cornerstone of probabilistic machine learning, affording particular advantages for uncertainty quantification and Bayesian optimisation. Extending Gaussian processes to chemical representations however is nontrivial, necessitating kernels defined over structured inputs such as graphs, strings and bit vectors. By defining such kernels in GAUCHE, we seek to open the door to powerful tools for uncertainty quantification and Bayesian optimisation in chemistry. Motivated by scenarios frequently encountered in experimental chemistry, we showcase applications for GAUCHE in molecule discovery, chemical reaction optimisation and protein engineering.

Author Information

Ryan-Rhys Griffiths (University of Cambridge)
Leo Klarner (University of Oxford)
Henry Moss (Secondmind.ai)
Henry Moss

Research Scientist at Secondmind.ai (formerly Prowler.io). Interested in: 1. Bayesian optimisation 2. Gaussian Processes 3. Information Theory 4. Experimental Design

Aditya Ravuri (University of Cambridge)
Sang Truong (Stanford University)
Yuanqi Du (Cornell University)
Arian Jamasb (University of Cambridge)
Julius Schwartz
Austin Tripp (University of Cambridge)
Bojana Ranković
Philippe Schwaller (Swiss Federal Institute of Technology Lausanne)
Gregory Kell
Anthony Bourached (University College London)
Alexander Chan (University of Cambridge)
Jacob Moss (University of Cambridge)
Chengzhi Guo (University of Cambridge)
Alpha Lee
Jian Tang (Mila)

More from the Same Authors