Transition1x - a dataset for building generalizable reactive machine learning potentials
Top Cited Papers
Open Access
- 24 December 2022
- journal article
- research article
- Published by Springer Nature in Scientific Data
- Vol. 9 (1) , 1-9
Abstract
Machine Learning (ML) models have, in contrast to their usefulness in molecular dynamics studies, had limited success as surrogate potentials for reaction barrier search. This is primarily because available datasets for training ML models on small molecular systems almost exclusively contain configurations at or near equilibrium. In this work, we present the dataset Transition1x containing 9.6 million Density Functional Theory (DFT) calculations of forces and energies of molecular configurations on and around reaction pathways at the ωB97x/6–31 G(d) level of theory. The data was generated by running Nudged Elastic Band (NEB) with DFT on 10k organic reactions of various types while saving intermediate calculations. We train equivariant graph message-passing neural network models on Transition1x and cross-validate on the popular ANI1x and QM9 datasets. We show that ML models cannot learn features in transition state regions solely by training on hitherto popular benchmark datasets. Transition1x is a new challenging benchmark that will provide an important step towards developing next-generation ML force fields that also work far away from equilibrium configurations and reactive systems.Keywords
All Related Versions
Funding Information
- Novo Nordisk Fonden (NNF19OC0057822, NNF19OC0057822), NNF19OC0057822), NNF19OC0057822), NNF20OC0062606)
- EC | Horizon 2020 Framework Programme (95718, 95718, 95718, 95718)
This publication has 33 references indexed in Scilit:
- Single‐ended transition state finding with the growing string methodJournal of Computational Chemistry, 2015
- Improved initial guess for minimum energy path calculationsThe Journal of Chemical Physics, 2014
- Enumeration of 166 Billion Organic Small Molecules in the Chemical Universe Database GDB-17Journal of Chemical Information and Modeling, 2012
- Optimization methods for finding minimum energy pathsThe Journal of Chemical Physics, 2008
- Systematic optimization of long-range corrected hybrid density functionalsThe Journal of Chemical Physics, 2008
- Theoretical investigation of the dissociation dynamics of vibrationally excited vinyl bromide on an ab initio potential-energy surface obtained using modified novelty sampling and feedforward neural networks. II. Numerical application of the methodThe Journal of Chemical Physics, 2007
- Generalized Neural-Network Representation of High-Dimensional Potential-Energy SurfacesPhysical Review Letters, 2007
- A climbing image nudged elastic band method for finding saddle points and minimum energy pathsThe Journal of Chemical Physics, 2000
- Self-Consistent Molecular-Orbital Methods. IX. An Extended Gaussian-Type Basis for Molecular-Orbital Studies of Organic MoleculesThe Journal of Chemical Physics, 1971
- The Convergence of a Class of Double-rank Minimization Algorithms 1. General ConsiderationsIMA Journal of Applied Mathematics, 1970