RMG Database for Chemical Property Prediction

Matthew S. Johnson; Xiaorui Dong; Alon Grinberg Dana; Yunsie Chung; David Farina; Ryan J. Gillis; Mengjie Liu; Nathan W. Yee; Katrin Blondal; Emily Mazeau; Colin A. Grambow; A. Mark Payne; Kevin A. Spiekermann; Hao Wei Pang; C. Franklin Goldsmith; Richard H. West; William H. Green

doi:10.1021/acs.jcim.2c00965

RMG Database for Chemical Property Prediction

Matthew S. Johnson, Xiaorui Dong, Alon Grinberg Dana, Yunsie Chung, David Farina, Ryan J. Gillis, Mengjie Liu, Nathan W. Yee, Katrin Blondal, Emily Mazeau, Colin A. Grambow, A. Mark Payne, Kevin A. Spiekermann, Hao Wei Pang, C. Franklin Goldsmith, Richard H. West, William H. Green

Research output: Contribution to journal › Article › peer-review

67 Scopus citations

Abstract

The Reaction Mechanism Generator (RMG) database for chemical property prediction is presented. The RMG database consists of curated datasets and estimators for accurately predicting the parameters necessary for constructing a wide variety of chemical kinetic mechanisms. These datasets and estimators are mostly published and enable prediction of thermodynamics, kinetics, solvation effects, and transport properties. For thermochemistry prediction, the RMG database contains 45 libraries of thermochemical parameters with a combination of 4564 entries and a group additivity scheme with 9 types of corrections including radical, polycyclic, and surface absorption corrections with 1580 total curated groups and parameters for a graph convolutional neural network trained using transfer learning from a set of >130 000 DFT calculations to 10 000 high-quality values. Correction schemes for solvent-solute effects, important for thermochemistry in the liquid phase, are available. They include tabulated values for 195 pure solvents and 152 common solutes and a group additivity scheme for predicting the properties of arbitrary solutes. For kinetics estimation, the database contains 92 libraries of kinetic parameters containing a combined 21000 reactions and contains rate rule schemes for 87 reaction classes trained on 8655 curated training reactions. Additional libraries and estimators are available for transport properties. All of this information is easily accessible through the graphical user interface at https://rmg.mit.edu. Bulk or on-the-fly use can be facilitated by interfacing directly with the RMG Python package which can be installed from Anaconda. The RMG database provides kineticists with easy access to estimates of the many parameters they need to model and analyze kinetic systems. This helps to speed up and facilitate kinetic analysis by enabling easy hypothesis testing on pathways, by providing parameters for model construction, and by providing checks on kinetic parameters from other sources.

Original language	English
Pages (from-to)	4906-4915
Number of pages	10
Journal	Journal of Chemical Information and Modeling
Volume	62
Issue number	20
DOIs	https://doi.org/10.1021/acs.jcim.2c00965
State	Published - Oct 24 2022
Externally published	Yes

Funding

Funding from the Gas Phase Chemical Physics Program of the US Department of Energy, Office of Basic Energy Sciences, Division of Chemical Sciences, Geosciences, and Biosciences (under award number DESC0014901), is appreciated. The work was also supported by the U.S. Department of Energy, Office of Science, Basic Energy Sciences, through the Exascale Catalytic Chemistry (ECC) Project as part of the Computational Chemical Sciences Program, and by the National Science Foundation under grant no. 1751720. A.G.D. was supported by The George J. Elbaum Scholarship in Engineering, The Ed Satell Foundation, and The Zuckerman STEM Leadership Program. H.P. was supported by the Think Global Education Trust Scholarship.

Funders	Funder number
Exascale Catalytic Chemistry
Satell Foundation
National Science Foundation	1751720
U.S. Department of Energy
Office of Science
Basic Energy Sciences
Chemical Sciences, Geosciences, and Biosciences Division	DESC0014901

Access to Document

10.1021/acs.jcim.2c00965

Cite this

Johnson, M. S., Dong, X., Grinberg Dana, A., Chung, Y., Farina, D., Gillis, R. J., Liu, M., Yee, N. W., Blondal, K., Mazeau, E., Grambow, C. A., Payne, A. M., Spiekermann, K. A., Pang, H. W., Goldsmith, C. F., West, R. H., & Green, W. H. (2022). RMG Database for Chemical Property Prediction. Journal of Chemical Information and Modeling, 62(20), 4906-4915. https://doi.org/10.1021/acs.jcim.2c00965

@article{1f335a2f7bf546feabb3e6f43dcb39c7,

title = "RMG Database for Chemical Property Prediction",

abstract = "The Reaction Mechanism Generator (RMG) database for chemical property prediction is presented. The RMG database consists of curated datasets and estimators for accurately predicting the parameters necessary for constructing a wide variety of chemical kinetic mechanisms. These datasets and estimators are mostly published and enable prediction of thermodynamics, kinetics, solvation effects, and transport properties. For thermochemistry prediction, the RMG database contains 45 libraries of thermochemical parameters with a combination of 4564 entries and a group additivity scheme with 9 types of corrections including radical, polycyclic, and surface absorption corrections with 1580 total curated groups and parameters for a graph convolutional neural network trained using transfer learning from a set of >130 000 DFT calculations to 10 000 high-quality values. Correction schemes for solvent-solute effects, important for thermochemistry in the liquid phase, are available. They include tabulated values for 195 pure solvents and 152 common solutes and a group additivity scheme for predicting the properties of arbitrary solutes. For kinetics estimation, the database contains 92 libraries of kinetic parameters containing a combined 21000 reactions and contains rate rule schemes for 87 reaction classes trained on 8655 curated training reactions. Additional libraries and estimators are available for transport properties. All of this information is easily accessible through the graphical user interface at https://rmg.mit.edu. Bulk or on-the-fly use can be facilitated by interfacing directly with the RMG Python package which can be installed from Anaconda. The RMG database provides kineticists with easy access to estimates of the many parameters they need to model and analyze kinetic systems. This helps to speed up and facilitate kinetic analysis by enabling easy hypothesis testing on pathways, by providing parameters for model construction, and by providing checks on kinetic parameters from other sources.",

author = "Johnson, {Matthew S.} and Xiaorui Dong and {Grinberg Dana}, Alon and Yunsie Chung and David Farina and Gillis, {Ryan J.} and Mengjie Liu and Yee, {Nathan W.} and Katrin Blondal and Emily Mazeau and Grambow, {Colin A.} and Payne, {A. Mark} and Spiekermann, {Kevin A.} and Pang, {Hao Wei} and Goldsmith, {C. Franklin} and West, {Richard H.} and Green, {William H.}",

note = "Publisher Copyright: {\textcopyright} 2022 American Chemical Society.",

year = "2022",

month = oct,

day = "24",

doi = "10.1021/acs.jcim.2c00965",

language = "English",

volume = "62",

pages = "4906--4915",

journal = "Journal of Chemical Information and Modeling",

issn = "1549-9596",

publisher = "American Chemical Society",

number = "20",

}

Johnson, MS, Dong, X, Grinberg Dana, A, Chung, Y, Farina, D, Gillis, RJ, Liu, M, Yee, NW, Blondal, K, Mazeau, E, Grambow, CA, Payne, AM, Spiekermann, KA, Pang, HW, Goldsmith, CF, West, RH & Green, WH 2022, 'RMG Database for Chemical Property Prediction', Journal of Chemical Information and Modeling, vol. 62, no. 20, pp. 4906-4915. https://doi.org/10.1021/acs.jcim.2c00965

TY - JOUR

T1 - RMG Database for Chemical Property Prediction

AU - Johnson, Matthew S.

AU - Dong, Xiaorui

AU - Grinberg Dana, Alon

AU - Chung, Yunsie

AU - Farina, David

AU - Gillis, Ryan J.

AU - Liu, Mengjie

AU - Yee, Nathan W.

AU - Blondal, Katrin

AU - Mazeau, Emily

AU - Grambow, Colin A.

AU - Payne, A. Mark

AU - Spiekermann, Kevin A.

AU - Pang, Hao Wei

AU - Goldsmith, C. Franklin

AU - West, Richard H.

AU - Green, William H.

PY - 2022/10/24

Y1 - 2022/10/24

N2 - The Reaction Mechanism Generator (RMG) database for chemical property prediction is presented. The RMG database consists of curated datasets and estimators for accurately predicting the parameters necessary for constructing a wide variety of chemical kinetic mechanisms. These datasets and estimators are mostly published and enable prediction of thermodynamics, kinetics, solvation effects, and transport properties. For thermochemistry prediction, the RMG database contains 45 libraries of thermochemical parameters with a combination of 4564 entries and a group additivity scheme with 9 types of corrections including radical, polycyclic, and surface absorption corrections with 1580 total curated groups and parameters for a graph convolutional neural network trained using transfer learning from a set of >130 000 DFT calculations to 10 000 high-quality values. Correction schemes for solvent-solute effects, important for thermochemistry in the liquid phase, are available. They include tabulated values for 195 pure solvents and 152 common solutes and a group additivity scheme for predicting the properties of arbitrary solutes. For kinetics estimation, the database contains 92 libraries of kinetic parameters containing a combined 21000 reactions and contains rate rule schemes for 87 reaction classes trained on 8655 curated training reactions. Additional libraries and estimators are available for transport properties. All of this information is easily accessible through the graphical user interface at https://rmg.mit.edu. Bulk or on-the-fly use can be facilitated by interfacing directly with the RMG Python package which can be installed from Anaconda. The RMG database provides kineticists with easy access to estimates of the many parameters they need to model and analyze kinetic systems. This helps to speed up and facilitate kinetic analysis by enabling easy hypothesis testing on pathways, by providing parameters for model construction, and by providing checks on kinetic parameters from other sources.

AB - The Reaction Mechanism Generator (RMG) database for chemical property prediction is presented. The RMG database consists of curated datasets and estimators for accurately predicting the parameters necessary for constructing a wide variety of chemical kinetic mechanisms. These datasets and estimators are mostly published and enable prediction of thermodynamics, kinetics, solvation effects, and transport properties. For thermochemistry prediction, the RMG database contains 45 libraries of thermochemical parameters with a combination of 4564 entries and a group additivity scheme with 9 types of corrections including radical, polycyclic, and surface absorption corrections with 1580 total curated groups and parameters for a graph convolutional neural network trained using transfer learning from a set of >130 000 DFT calculations to 10 000 high-quality values. Correction schemes for solvent-solute effects, important for thermochemistry in the liquid phase, are available. They include tabulated values for 195 pure solvents and 152 common solutes and a group additivity scheme for predicting the properties of arbitrary solutes. For kinetics estimation, the database contains 92 libraries of kinetic parameters containing a combined 21000 reactions and contains rate rule schemes for 87 reaction classes trained on 8655 curated training reactions. Additional libraries and estimators are available for transport properties. All of this information is easily accessible through the graphical user interface at https://rmg.mit.edu. Bulk or on-the-fly use can be facilitated by interfacing directly with the RMG Python package which can be installed from Anaconda. The RMG database provides kineticists with easy access to estimates of the many parameters they need to model and analyze kinetic systems. This helps to speed up and facilitate kinetic analysis by enabling easy hypothesis testing on pathways, by providing parameters for model construction, and by providing checks on kinetic parameters from other sources.

UR - http://www.scopus.com/inward/record.url?scp=85140418005&partnerID=8YFLogxK

U2 - 10.1021/acs.jcim.2c00965

DO - 10.1021/acs.jcim.2c00965

M3 - Article

C2 - 36222558

AN - SCOPUS:85140418005

SN - 1549-9596

VL - 62

SP - 4906

EP - 4915

JO - Journal of Chemical Information and Modeling

JF - Journal of Chemical Information and Modeling

IS - 20

ER -

RMG Database for Chemical Property Prediction

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Cite this