A physics-inspired approach to the understanding of molecular representations and models
Name
d3me00189j.pdf
Description
Published version
Size
1.25 MB
Format
Adobe PDF
Checksum (MD5)
32b6fc49edf4152876f97d35d7b1fc8c
Author(s)
Dicks, Luke
Graff, David E
Jordan, Kirk E
Coley, Connor W
Pyzer-Knapp, Edward O
Date Issued
2024
Journal
Molecular Systems Design & Engineering
Publisher
Royal Society of Chemistry
Citation
Dicks, Luke, Graff, David E, Jordan, Kirk E, Coley, Connor W and Pyzer-Knapp, Edward O. 2024. "A physics-inspired approach to the understanding of molecular representations and models." Molecular Systems Design & Engineering, 9 (5).
Version
Final published version
Abstract
The story of machine learning in general, and its application to molecular design in particular, has been a tale of evolving representations of data. Understanding the implications of the use of a particular representation – including the existence of so-called ‘activity cliffs’ for cheminformatics models – is the key to their successful use for molecular discovery. In this work we present a physics-inspired methodology which exploits analogies between model response surfaces and energy landscapes to richly describe the relationship between the representation and the model. From these similarities, a metric emerges which is analogous to the commonly used frustration metric from the chemical physics community. This new property shows state-of-the-art prediction of model error, whilst belonging to a novel class of roughness measure that extends beyond the known data allowing the trivial identification of activity cliffs even in the absence of related training or evaluation data.
MIT Department
Massachusetts Institute of Technology. Department of Chemical Engineering
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1039/d3me00189j
