Dataset Design for Building Models of Chemical Reactivity
Name
raghavan-et-al-2023-dataset-design-for-building-models-of-chemical-reactivity.pdf
Description
Published version
Size
2.4 MB
Format
Adobe PDF
Checksum (MD5)
4760da699741999b9a976d269b370cf0
Author(s)
Raghavan, Priyanka
Haas, Brittany C
Ruos, Madeline E
Schleinitz, Jules
Doyle, Abigail G
Reisman, Sarah E
Sigman, Matthew S
Coley, Connor W
Date Issued
December 27, 2023
Journal
ACS Central Science
Publisher
American Chemical Society
Citation
Priyanka Raghavan, Brittany C. Haas, Madeline E. Ruos, Jules Schleinitz, Abigail G. Doyle, Sarah E. Reisman, Matthew S. Sigman, and Connor W. Coley. ACS Central Science 2023 9 (12), 2196-2204.
Version
Final published version
Abstract
Models can codify our understanding of chemical reactivity and serve a useful purpose in the development of new synthetic processes via, for example, evaluating hypothetical reaction conditions or in silico substrate tolerance. Perhaps the most determining factor is the composition of the training data and whether it is sufficient to train a model that can make accurate predictions over the full domain of interest. Here, we discuss the design of reaction datasets in ways that are conducive to data-driven modeling, emphasizing the idea that training set diversity and model generalizability rely on the choice of molecular or reaction representation. We additionally discuss the experimental constraints associated with generating common types of chemistry datasets and how these considerations should influence dataset design and model building.
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/10.1021/acscentsci.3c01163
