Learning from Failure: Predicting Electronic Structure Calculation Outcomes with Machine Learning Models

Duan, Chenru; Janet, Jon Paul; Liu, Fang; Nandy, Aditya; Kulik, Heather J.

doi:10.1021/acs.jctc.9b00057

Cited by 87 publications

(159 citation statements)

References 111 publications

(235 reference statements)

Supporting

Mentioning

157

Contrasting

Unclassified

Order By: Relevance

“…ML approaches have already proven successful in different elds of chemistry, [51][52][53] with a strong focus on materials science [54][55][56][57][58][59][60][61] and drug discovery. [62][63][64][65][66][67][68] In other areas, including organic synthesis, [69][70][71][72][73] and theoretical [74][75][76][77][78][79][80][81] and inorganic 82,83 chemistry, the use of ML is rapidly growing. In catalysis, 84,85 several examples have been reported for both heterogeneous [86][87][88][89][90][91][92][93] and homogeneous [94][95][96][97][98] systems.…”

Section: Introductionmentioning

confidence: 99%

Machine learning dihydrogen activation in the chemical space surrounding Vaska's complex

et al. 2020

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Machine learning dihydrogen activation in the chemical space surrounding Vaska's complex

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In recent years, machine learning approaches have been proposed to accelerate calculations with reasonable accuracy [108,109], showing an interesting potential of transferability to larger molecular scaffolds [110,111] like representing the training sets through Hartree-Fock molecular orbitals (MOs) [111]. Indeed, solving the electronic state density thereby learning the density models through DFT-based datasets, instead of using the gradient descent that requires the calculation of the functional derivative, has been shown to break down the typical cost of DFT [112].…”

Section: Outlooks On Machine Learning-based Methods and Large-scale Smentioning

confidence: 99%

Synergistic Approach of Ultrafast Spectroscopy and Molecular Simulations in the Characterization of Intramolecular Charge Transfer in Push-Pull Molecules

et al. 2020

View full text Add to dashboard Cite

The comprehensive characterization of Intramolecular Charge Transfer (ICT) stemming in push-pull molecules with a delocalized π-system of electrons is noteworthy for a bespoke design of organic materials, spanning widespread applications from photovoltaics to nanomedicine imaging devices. Photo-induced ICT is characterized by structural reorganizations, which allows the molecule to adapt to the new electronic density distribution. Herein, we discuss recent photophysical advances combined with recent progresses in the computational chemistry of photoactive molecular ensembles. We focus the discussion on femtosecond Transient Absorption Spectroscopy (TAS) enabling us to follow the transition from a Locally Excited (LE) state to the ICT and to understand how the environment polarity influences radiative and non-radiative decay mechanisms. In many cases, the charge transfer transition is accompanied by structural rearrangements, such as the twisting or molecule planarization. The possibility of an accurate prediction of the charge-transfer occurring in complex molecules and molecular materials represents an enormous advantage in guiding new molecular and materials design. We briefly report on recent advances in ultrafast multidimensional spectroscopy, in particular, Two-Dimensional Electronic Spectroscopy (2DES), in unraveling the ICT nature of push-pull molecular systems. A theoretical description at the atomistic level of photo-induced molecular transitions can predict with reasonable accuracy the properties of photoactive molecules. In this framework, the review includes a discussion on the advances from simulation and modeling, which have provided, over the years, significant information on photoexcitation, emission, charge-transport, and decay pathways. Density Functional Theory (DFT) coupled with the Time-Dependent (TD) framework can describe electronic properties and dynamics for a limited system size. More recently, Machine Learning (ML) or deep learning approaches, as well as free-energy simulations containing excited state potentials, can speed up the calculations with transferable accuracy to more complex molecules with extended system size. A perspective on combining ultrafast spectroscopy with molecular simulations is foreseen for optimizing the design of photoactive compounds with tunable properties.

show abstract

“…In new materials spaces, the accuracy of these decision models quickly erodes, so we have employed QM descriptors of the electronic and geometric structure to develop more general models. Analysis of these in situ simulation decision engines reveals that steps taken by a geometry optimization algorithm are essential in determining calculation outcomes and challenging to predict based on composition alone . With this model, 95–100% accuracy can be achieved on only the confidently predicted geometries when the model has sufficient information to predict the simulation outcome (Figure ).…”

Section: Autonomous Data Set Generation and Chemical Discoverymentioning

confidence: 99%

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

Kulik

2019

WIREs Comput Mol Sci

Self Cite

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

Learning from Failure: Predicting Electronic Structure Calculation Outcomes with Machine Learning Models

Cited by 87 publications

References 111 publications

Machine learning dihydrogen activation in the chemical space surrounding Vaska's complex

Machine learning dihydrogen activation in the chemical space surrounding Vaska's complex

Synergistic Approach of Ultrafast Spectroscopy and Molecular Simulations in the Characterization of Intramolecular Charge Transfer in Push-Pull Molecules

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

Contact Info

Product

Resources

About