Accelerating the search for global minima on potential energy surfaces using machine learning

Carr, Shane; Garnett, Roman; Lo, Cynthia S.

doi:10.1063/1.4964671

Cited by 18 publications

(14 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML models have also been demonstrated to reduce the number of explicit calculations required during time-consuming geometry optimization and transition-state search in mechanism discovery. These techniques include using surrogate models (e.g., Gaussian processes or ANNs) to estimate the local potential energy surface, − to reduce the time to self-consistent energy evaluation, or to estimate when a candidate mechanistic step in a reaction network will be too high in energy to contribute to a reaction mechanism. , …”

Section: Transition-metal Chemical Space Explorationmentioning

confidence: 99%

Computational Discovery of Transition-metal Complexes: From High-throughput Screening to Machine Learning

et al. 2021

View full text Add to dashboard Cite

Transition-metal complexes are attractive targets for the design of catalysts and functional materials. The behavior of the metal−organic bond, while very tunable for achieving target properties, is challenging to predict and necessitates searching a wide and complex space to identify needles in haystacks for target applications. This review will focus on the techniques that make high-throughput search of transition-metal chemical space feasible for the discovery of complexes with desirable properties. The review will cover the development, promise, and limitations of "traditional" computational chemistry (i.e., force field, semiempirical, and density functional theory methods) as it pertains to data generation for inorganic molecular discovery. The review will also discuss the opportunities and limitations in leveraging experimental data sources. We will focus on how advances in statistical modeling, artificial intelligence, multiobjective optimization, and automation accelerate discovery of lead compounds and design rules. The overall objective of this review is to showcase how bringing together advances from diverse areas of computational chemistry and computer science have enabled the rapid uncovering of structure−property relationships in transition-metal chemistry. We aim to highlight how unique considerations in motifs of metal−organic bonding (e.g., variable spin and oxidation state, and bonding strength/nature) set them and their discovery apart from more commonly considered organic molecules. We will also highlight how uncertainty and relative data scarcity in transition-metal chemistry motivate specific developments in machine learning representations, model training, and in computational chemistry. Finally, we will conclude with an outlook of areas of opportunity for the accelerated discovery of transition-metal complexes.

show abstract

Section: Transition-metal Chemical Space Explorationmentioning

confidence: 99%

Computational Discovery of Transition-metal Complexes: From High-throughput Screening to Machine Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The shift has been made possible by the availability of ever‐faster hardware and methods over the past couple of decades along with workflows that enable the automated simulation of molecules and materials . The resulting large data sets, along with widely available open source tools for ML model training, have in large part ushered in the advances in the application of ML for the replacement or augmentation of traditional theoretical chemistry for property prediction. My own group's entrance into ML model development for open‐shell transition metal chemistry is an example of this trend.…”

Section: The Data Model and Representation Trade‐offmentioning

confidence: 99%

Making machine learning a useful tool in the accelerated discovery of transition metal complexes

Kulik

2019

WIREs Comput Mol Sci

View full text Add to dashboard Cite

As machine learning (ML) has matured, it has opened a new frontier in theoretical and computational chemistry by offering the promise of simultaneous paradigm shifts in accuracy and efficiency. Nowhere is this advance more needed, but also more challenging to achieve, than in the discovery of open-shell transition metal complexes. Here, localized d or f electrons exhibit variable bonding that is challenging to capture even with the most computationally demanding methods. Thus, despite great promise, clear obstacles remain in constructing ML models that can supplement or even replace explicit electronic structure calculations. In this article, I outline the recent advances in building ML models in transition metal chemistry, including the ability to approach sub-kcal/mol accuracy on a range of properties with tailored representations, to discover and enumerate complexes in large chemical spaces, and to reveal opportunities for design through analysis of feature importance. I discuss unique considerations that have been essential to enabling ML in open-shell transition metal chemistry, including (a) the relationship of data set size/diversity, model complexity, and representation choice, (b) the importance of quantitative assessments of both theory and model domain of applicability, and (c) the need to enable autonomous generation of reliable, large data sets both for ML model training and in active learning or discovery contexts. Finally, I summarize the next steps toward making ML a mainstream tool in the accelerated discovery of transition metal complexes.

show abstract

“…By contrast, sampling algorithms have proven to be robust search tools in chemical physics. For example, BO has been used to optimize density functionals, 4,5 generate low energy molecular conformers, 6,7 and inverse design potential energy surfaces for reactive molecular systems 8 . BO has also been successfully applied for screening chemical compounds [9][10][11] , minimizing the energy of the Ising model 12 , and has recently been used to optimize laser pulses for molecular control 13,14 .…”

Section: Introductionmentioning

confidence: 99%

Multi-objective optimization for retinal photoisomerization models with respect to experimental observables

Vargas-Hernández,

Chuang,

Brumer

2021

Preprint

View full text Add to dashboard Cite

The fitting of physical models is often done only using a single target observable. However, when multiple targets are considered, the fitting procedure becomes cumbersome, there being no easy way to quantify the robustness of the model for all different observables. Here, we illustrate that one can jointly search for the best model for each desired observable through multi-objective optimization. To do so we construct the Pareto front to study if there exists a set of parameters of the model that can jointly describe multiple, or all, observables. To alleviate the computational cost, the predicted error for each targeted objective is approximated with a Gaussian process model, as it is commonly done in the Bayesian optimization framework. We applied this methodology to improve three different models used in the simulation of stationary state cis − trans photoisomerization of retinal in rhodopsin. Optimization was done with respect to different experimental measurements, including emission spectra, peak absorption frequencies for the cis and trans conformers, and the energy storage.

show abstract

Accelerating the search for global minima on potential energy surfaces using machine learning

Cited by 18 publications

References 43 publications

Computational Discovery of Transition-metal Complexes: From High-throughput Screening to Machine Learning

Computational Discovery of Transition-metal Complexes: From High-throughput Screening to Machine Learning

Making machine learning a useful tool in the accelerated discovery of transition metal complexes

Multi-objective optimization for retinal photoisomerization models with respect to experimental observables

Contact Info

Product

Resources

About