Multi-fidelity prediction of molecular optical peaks with deep learning
Name
d1sc05677h-combined.pdf
Size
4.47 MB
Format
Unknown
Checksum (MD5)
d61a505e43a5c1d5181c1eec854766ff
Author(s)
Greenman, Kevin P
Green Jr, William H
Gomez-Bombarelli, Rafael
Date Issued
January 4, 2022
Journal
Chemical Science
Publisher
Royal Society of Chemistry (RSC)
Citation
Greenman, Kevin P, Green, William H. and Gomez-Bombarelli, Rafael. 2022. "Multi-fidelity prediction of molecular optical peaks with deep learning." Chemical Science.
Version
Author's final manuscript
Abstract
Optical properties are central to molecular design for many applications, including solar cells and
biomedical imaging. A variety of ab initio and statistical methods have been developed for their
prediction, each with a trade-off between accuracy, generality, and cost. Existing theoretical methods
such as time-dependent density functional theory (TD-DFT) are generalizable across chemical space
because of their robust physics-based foundations but still exhibit random and systematic errors with
respect to experiment despite their high computational cost. Statistical methods can achieve high
accuracy at a lower cost, but data sparsity and unoptimized molecule and solvent representations
often limit their ability to generalize. Here, we utilize directed message passing neural networks (DMPNNs) to represent both dye molecules and solvents for predictions of molecular absorption peaks in
solution. Additionally, we demonstrate a multi-fidelity approach based on an auxiliary model trained
on over 28,000 TD-DFT calculations that further improves accuracy and generalizability, as shown
through rigorous splitting strategies. Combining several openly-available experimental datasets, we
benchmark these methods against a state-of-the-art regression tree algorithm and compare the DMPNN solvent representation to several alternatives. Finally, we explore the interpretability of the
learned representations using dimensionality reduction and evaluate the use of ensemble variance as
an estimator of the epistemic uncertainty in our predictions of molecular peak absorption in solution.
The prediction methods proposed herein can be integrated with active learning, generative modeling,
and experimental workflows to enable the more rapid design of molecules with targeted optical
properties.
MIT Department
Massachusetts Institute of Technology. Department of Chemical Engineering
Massachusetts Institute of Technology. Department of Materials Science and Engineering
Terms of Use
Creative Commons Attribution 3.0 unported license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1039/d1sc05677h
