Predicting Infrared Spectra with Message Passing Neural Networks
Name
Chemprop_IR_JCIM.pdf
Size
2.18 MB
Format
Adobe PDF
Checksum (MD5)
94a7e91125b875e3518f1913299c0539
Author(s)
McGill, Charles
Forsuelo, Michael
Guan, Yanfei
Green Jr, William H
Date Issued
May 2021
Journal
Journal of Chemical Information and Modeling
Publisher
American Chemical Society (ACS)
Citation
McGill, Charles et al. "Predicting Infrared Spectra with Message Passing Neural Networks." Forthcoming in Journal of Chemical Information and Modeling (2021): doi.org/10.1021/acs.jcim.1c00055. © 2021 American Chemical Society
Version
Author's final manuscript
Abstract
Infrared (IR) spectroscopy remains an important tool for chemical characterization and identification. Chemprop-IR has been developed as a software package for the prediction of IR spectra through the use of machine learning. This work serves the dual purpose of providing a trained general-purpose model for the prediction of IR spectra with ease and providing the Chemprop-IR software framework for the training of new models. In Chemprop-IR, molecules are encoded using a directed message passing neural network, allowing for molecule latent representations to be learned and optimized for the task of spectral predictions. Model training incorporates spectra metrics and normalization techniques that offer better performance with spectral predictions than standard practice in regression models. The model makes use of pretraining using quantum chemistry calculations and ensembling of multiple submodels to improve generalizability and performance. The spectral predictions that result are of high quality, showing capability to capture the extreme diversity of spectral forms over chemical space and represent complex peak structures.
MIT Department
Massachusetts Institute of Technology. Department of Chemical Engineering
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1021/acs.jcim.1c00055
