Generating transition states of isomerization reactions with deep learning

Literature Information

Publication Date 2020-10-05
DOI 10.1039/D0CP04670A
Impact Factor 3.676
Authors

Lagnajit Pattanaik, John B. Ingraham, Colin A. Grambow, William H. Green


View Original

Abstract

Lack of quality data and difficulty generating these data hinder quantitative understanding of reaction kinetics. Specifically, conventional methods to generate transition state structures are deficient in speed, accuracy, or scope. We describe a novel method to generate three-dimensional transition state structures for isomerization reactions using reactant and product geometries. Our approach relies on a graph neural network to predict the transition state distance matrix and a least squares optimization to reconstruct the coordinates based on which entries of the distance matrix the model perceives to be important. We feed the structures generated by our algorithm through a rigorous quantum mechanics workflow to ensure the predicted transition state corresponds to the ground truth reactant and product. In both generating viable geometries and predicting accurate transition states, our method achieves excellent results. We envision workflows like this, which combine neural networks and quantum chemistry calculations, will become the preferred methods for computing chemical reactions.

Related Literature

Ligand-dependent blinking of zinc-blende CdSe/ZnS core/shell nanocrystals

Yongwook Kim, Hyunung Yu, Dae Won Moon, Sung Jun Lim, Wonjung Kim, Hye-Joo Yoon, Seung Koo Shin

2009-03-03 Paper

DOI: 10.1039/B822351C

Protein stability modulated by a conformational effector: effects of trifluoroethanol on bovine serum albumin

Rita Carrotta, Mauro Manno, Francesco Maria Giordano, Alessandro Longo, Giuseppe Portale, Vincenzo Martorana, Pier Luigi San Biagio

2009-03-05 Paper

DOI: 10.1039/B818687A

Growth of solid conical structures during multistage drying of sessile poly(ethylene oxide) droplets‡

David Willmer, Kyle Anthony Baldwin, David John Fairhurst

2010-03-03 Paper

DOI: 10.1039/B922727J

Inside front cover

Front/Back Matter

DOI: 10.1039/B907299N

Nature of proton dynamics in a polymer electrolyte membrane, nafion: a first-principles molecular dynamics study

Yoong-Kee Choe, Eiji Tsuchida, Tamio Ikeshoji, Shunsuke Yamakawa, Shi-aki Hyodo

2009-03-14 Paper

DOI: 10.1039/B819535H

Ligand dynamics on the surface of zirconium oxo clusters

Philip Walther, Michael Puchberger, F. Rene Kogler, Karlheinz Schwarz, Ulrich Schubert

2009-03-26 Paper

DOI: 10.1039/B820731C

Surprisingly high, bulk liquid-like mobility of silica-confined ionic liquids

Ronald Göbel, Peter Hesemann, Jens Weber, Eléonore Möller, Alwin Friedrich, Sabine Beuermann

2009-03-17 Paper

DOI: 10.1039/B821833A

Effect of polymer, poly(ethylene glycol)(PEG-400), on solvent and rotational relaxation of coumarin-480 in an ionic liquid containing microemulsions

Rajib Pramanik, Souravi Sarkar, Chiranjib Ghatak, Palash Setua, Nilmoni Sarkar

2010-02-24 Paper

DOI: 10.1039/B922867E

Surface-enhanced IR–visible sum frequency generation vibrational spectroscopy

Qifeng Li, Chiung Wen Kuo, Zheng Yang, Peilin Chen, Keng C. Chou

2009-02-25 Paper

DOI: 10.1039/B821045D

You might also like

Compound Q&A

How should waste containing 2-Ethyl-4-Methyl-1H-Imidazole-5-Carbaldehyde (CAS: 88634-80-4) be handled?

Waste containing 2-Ethyl-4-Methyl-1H-Imidazole-5-Carbaldehyde (CAS: 88634-80-4) ...

88634-80-42-Ethyl-4-Methyl-1H-...
Compound Q&A

What industries use Triethoxy(octyl)silane (CAS: 1385031-14-0)?

Triethoxy(octyl)silane (CAS: 1385031-14-0) is widely used in the pharmaceuticals...

1385031-14-0Triethoxy(octyl)sila...
Compound Q&A

Are there alternatives to 3-iodo-7-nitro-1H-indazole (CAS: 864724-64-1) in synthesis?

Several alternatives to 3-iodo-7-nitro-1H-indazole (CAS: 864724-64-1) exist in t...

864724-64-13-iodo-7-nitro-1H-in...
Compound Q&A

Are there alternatives to Benzene, bis[(trimethoxysilyl)ethyl] (CAS: 266317-71-9) in synthesis?

Yes, there are alternatives to Benzene, bis[(trimethoxysilyl)ethyl] (CAS: 266317...

266317-71-9Benzene, bis[(trimet...
Compound Q&A

Is Isothiazole-3-carbonitrile (CAS: 1452-17-1) safe?

Isothiazole-3-carbonitrile (CAS: 1452-17-1) is generally considered safe when us...

1452-17-1Isothiazole-3-carbon...
Compound Q&A

Is (3-Chlorophenyl)methanol (CAS: 873-63-2) safe?

(3-Chlorophenyl)methanol (CAS: 873-63-2) is considered low to moderately toxic. ...

873-63-2(3-Chlorophenyl)meth...
Compound Q&A

How is (2S,3S)-2-Hydroxy-3-({[(2-methyl-2-propanyl)oxy]carbonyl}amino)-3-(2-naphthyl)propanoic acid (CAS: 959583-98-3) typically synthesized?

(2S,3S)-2-Hydroxy-3-({[(2-methyl-2-propanyl)oxy]carbonyl}amino)-3-(2-naphthyl)pr...

959583-98-3(2S,3S)-2-Hydroxy-3-...
Compound Q&A

What precautions should be taken when handling Methyl 2-(bromomethyl)-5-methoxybenzoate (CAS: 788081-99-2)?

Proper handling of methyl 2-(bromomethyl)-5-methoxybenzoate requires the use of ...

788081-99-2Methyl 2-(bromomethy...
Compound Q&A

What is 6,8-Dibromoimidazo[1,2-a]pyridine-2-carboxylic acid (CAS: 904805-36-3)?

6,8-Dibromoimidazo[1,2-a]pyridine-2-carboxylic acid (CAS: 904805-36-3) is an aro...

904805-36-36,8-Dibromoimidazo[1...
Compound Q&A

Is 3-Amino-5-bromo-2-pyridinecarbonitrile (CAS: 573675-27-1) safe?

3-Amino-5-bromo-2-pyridinecarbonitrile is considered safe when handled under pro...

573675-27-13-Amino-5-bromo-2-py...

Source Journal

Physical Chemistry Chemical Physics

Physical Chemistry Chemical Physics
CiteScore: 5.5
Self-citation Rate: 10.3%
Articles per Year: 3036

Physical Chemistry Chemical Physics (PCCP) is an international journal co-owned by 19 physical chemistry and physics societies from around the world. This journal publishes original, cutting-edge research in physical chemistry, chemical physics and biophysical chemistry. To be suitable for publication in PCCP, articles must include significant innovation and/or insight into physical chemistry; this is the most important criterion that reviewers and Editors will judge against when evaluating submissions. The journal has a broad scope and welcomes contributions spanning experiment, theory, computation and data science. Topical coverage includes spectroscopy, dynamics, kinetics, statistical mechanics, thermodynamics, electrochemistry, catalysis, surface science, quantum mechanics, quantum computing and machine learning. Interdisciplinary research areas such as polymers and soft matter, materials, nanoscience, energy, surfaces/interfaces, and biophysical chemistry are welcomed if they demonstrate significant innovation and/or insight into physical chemistry. Joined experimental/theoretical studies are particularly appreciated when complementary and based on up-to-date approaches.

Recommended Compounds

Recommended Suppliers

Disclaimer
This page provides academic journal information for reference and research purposes only. We are not affiliated with any journal publishers and do not handle publication submissions. For publication-related inquiries, please contact the respective journal publishers directly.
If you notice any inaccuracies in the information displayed, please contact us at support@chemtradehub.com. We will promptly review and address your concerns.