1
|
Cytter Y, Nandy A, Duan C, Kulik HJ. Insights into the deviation from piecewise linearity in transition metal complexes from supervised machine learning models. Phys Chem Chem Phys 2023; 25:8103-8116. [PMID: 36876903 DOI: 10.1039/d3cp00258f] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/25/2023]
Abstract
Virtual high-throughput screening (VHTS) and machine learning (ML) with density functional theory (DFT) suffer from inaccuracies from the underlying density functional approximation (DFA). Many of these inaccuracies can be traced to the lack of derivative discontinuity that leads to a curvature in the energy with electron addition or removal. Over a dataset of nearly one thousand transition metal complexes typical of VHTS applications, we computed and analyzed the average curvature (i.e., deviation from piecewise linearity) for 23 density functional approximations spanning multiple rungs of "Jacob's ladder". While we observe the expected dependence of the curvatures on Hartree-Fock exchange, we note limited correlation of curvature values between different rungs of "Jacob's ladder". We train ML models (i.e., artificial neural networks or ANNs) to predict the curvature and the associated frontier orbital energies for each of these 23 functionals and then interpret differences in curvature among the different DFAs through analysis of the ML models. Notably, we observe spin to play a much more important role in determining the curvature of range-separated and double hybrids in comparison to semi-local functionals, explaining why curvature values are weakly correlated between these and other families of functionals. Over a space of 187.2k hypothetical compounds, we use our ANNs to pinpoint DFAs for which representative transition metal complexes have near-zero curvature with low uncertainty, demonstrating an approach to accelerate screening of complexes with targeted optical gaps.
Collapse
Affiliation(s)
- Yael Cytter
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
| | - Aditya Nandy
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.,Department of Chemistry, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
| | - Chenru Duan
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.,Department of Chemistry, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
| | - Heather J Kulik
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.,Department of Chemistry, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
| |
Collapse
|
2
|
Duan C, Nandy A, Meyer R, Arunachalam N, Kulik HJ. A transferable recommender approach for selecting the best density functional approximations in chemical discovery. NATURE COMPUTATIONAL SCIENCE 2023; 3:38-47. [PMID: 38177951 DOI: 10.1038/s43588-022-00384-0] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/07/2022] [Accepted: 11/23/2022] [Indexed: 01/06/2024]
Abstract
Approximate density functional theory has become indispensable owing to its balanced cost-accuracy trade-off, including in large-scale screening. To date, however, no density functional approximation (DFA) with universal accuracy has been identified, leading to uncertainty in the quality of data generated from density functional theory. With electron density fitting and Δ-learning, we build a DFA recommender that selects the DFA with the lowest expected error with respect to the gold standard (but cost-prohibitive) coupled cluster theory in a system-specific manner. We demonstrate this recommender approach on the evaluation of vertical spin splitting energies of transition metal complexes. Our recommender predicts top-performing DFAs and yields excellent accuracy (about 2 kcal mol-1) for chemical discovery, outperforming both individual Δ-learning models and the best conventional single-functional approach from a set of 48 DFAs. By demonstrating transferability to diverse synthesized compounds, our recommender potentially addresses the accuracy versus scope dilemma broadly encountered in computational chemistry.
Collapse
Affiliation(s)
- Chenru Duan
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
- Department of Chemistry, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Aditya Nandy
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
- Department of Chemistry, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Ralf Meyer
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Naveen Arunachalam
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Heather J Kulik
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA.
- Department of Chemistry, Massachusetts Institute of Technology, Cambridge, MA, USA.
| |
Collapse
|
3
|
Kuntz D, Wilson AK. Machine learning, artificial intelligence, and chemistry: how smart algorithms are reshaping simulation and the laboratory. PURE APPL CHEM 2022. [DOI: 10.1515/pac-2022-0202] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Abstract
Machine learning and artificial intelligence are increasingly gaining in prominence through image analysis, language processing, and automation, to name a few applications. Machine learning is also making profound changes in chemistry. From revisiting decades-old analytical techniques for the purpose of creating better calibration curves, to assisting and accelerating traditional in silico simulations, to automating entire scientific workflows, to being used as an approach to deduce underlying physics of unexplained chemical phenomena, machine learning and artificial intelligence are reshaping chemistry, accelerating scientific discovery, and yielding new insights. This review provides an overview of machine learning and artificial intelligence from a chemist’s perspective and focuses on a number of examples of the use of these approaches in computational chemistry and in the laboratory.
Collapse
Affiliation(s)
- David Kuntz
- Department of Chemistry , University of North Texas , Denton , TX 76201 , USA
| | - Angela K. Wilson
- Department of Chemistry , Michigan State University , East Lansing , MI 48824 , USA
| |
Collapse
|
4
|
Duan C, Nandy A, Adamji H, Roman-Leshkov Y, Kulik HJ. Machine Learning Models Predict Calculation Outcomes with the Transferability Necessary for Computational Catalysis. J Chem Theory Comput 2022; 18:4282-4292. [PMID: 35737587 DOI: 10.1021/acs.jctc.2c00331] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
Virtual high-throughput screening (VHTS) and machine learning (ML) have greatly accelerated the design of single-site transition-metal catalysts. VHTS of catalysts, however, is often accompanied with a high calculation failure rate and wasted computational resources due to the difficulty of simultaneously converging all mechanistically relevant reactive intermediates to expected geometries and electronic states. We demonstrate a dynamic classifier approach, i.e., a convolutional neural network that monitors geometry optimizations on the fly, and exploit its good performance and transferability in identifying geometry optimization failures for catalyst design. We show that the dynamic classifier performs well on all reactive intermediates in the representative catalytic cycle of the radical rebound mechanism for the conversion of methane to methanol despite being trained on only one reactive intermediate. The dynamic classifier also generalizes to chemically distinct intermediates and metal centers absent from the training data without loss of accuracy or model confidence. We rationalize this superior model transferability as arising from the use of electronic structure and geometric information generated on-the-fly from density functional theory calculations and the convolutional layer in the dynamic classifier. When used in combination with uncertainty quantification, the dynamic classifier saves more than half of the computational resources that would have been wasted on unsuccessful calculations for all reactive intermediates being considered.
Collapse
Affiliation(s)
- Chenru Duan
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.,Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Aditya Nandy
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.,Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Husain Adamji
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Yuriy Roman-Leshkov
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Heather J Kulik
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| |
Collapse
|
5
|
Nandy A, Duan C, Kulik HJ. Audacity of huge: overcoming challenges of data scarcity and data quality for machine learning in computational materials discovery. Curr Opin Chem Eng 2022. [DOI: 10.1016/j.coche.2021.100778] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/22/2023]
|
6
|
Duan C, Chu DBK, Nandy A, Kulik HJ. Detection of multi-reference character imbalances enables a transfer learning approach for virtual high throughput screening with coupled cluster accuracy at DFT cost. Chem Sci 2022; 13:4962-4971. [PMID: 35655882 PMCID: PMC9067623 DOI: 10.1039/d2sc00393g] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2022] [Accepted: 04/04/2022] [Indexed: 01/08/2023] Open
Abstract
Appropriately identifying and treating molecules and materials with significant multi-reference (MR) character is crucial for achieving high data fidelity in virtual high-throughput screening (VHTS). Despite development of numerous MR diagnostics, the extent to which a single value of such a diagnostic indicates the MR effect on a chemical property prediction is not well established. We evaluate MR diagnostics for over 10 000 transition-metal complexes (TMCs) and compare to those for organic molecules. We observe that only some MR diagnostics are transferable from one chemical space to another. By studying the influence of MR character on chemical properties (i.e., MR effect) that involve multiple potential energy surfaces (i.e., adiabatic spin splitting, ΔE H-L, and ionization potential, IP), we show that differences in MR character are more important than the cumulative degree of MR character in predicting the magnitude of an MR effect. Motivated by this observation, we build transfer learning models to predict CCSD(T)-level adiabatic ΔE H-L and IP from lower levels of theory. By combining these models with uncertainty quantification and multi-level modeling, we introduce a multi-pronged strategy that accelerates data acquisition by at least a factor of three while achieving coupled cluster accuracy (i.e., to within 1 kcal mol-1 MAE) for robust VHTS.
Collapse
Affiliation(s)
- Chenru Duan
- Department of Chemical Engineering, Massachusetts Institute of Technology Cambridge MA 02139 USA
- Department of Chemistry, Massachusetts Institute of Technology Cambridge MA 02139 USA
| | - Daniel B K Chu
- Department of Chemical Engineering, Massachusetts Institute of Technology Cambridge MA 02139 USA
| | - Aditya Nandy
- Department of Chemical Engineering, Massachusetts Institute of Technology Cambridge MA 02139 USA
- Department of Chemistry, Massachusetts Institute of Technology Cambridge MA 02139 USA
| | - Heather J Kulik
- Department of Chemical Engineering, Massachusetts Institute of Technology Cambridge MA 02139 USA
| |
Collapse
|
7
|
Mroz AM, Davenport AM, Sterling J, Davis J, Hendon CH. An Electric Field–Based Approach for Quantifying Effective Volumes and Radii of Chemically Affected Space. Chem Sci 2022; 13:6558-6566. [PMID: 35756514 PMCID: PMC9172366 DOI: 10.1039/d2sc00780k] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2022] [Accepted: 04/29/2022] [Indexed: 11/21/2022] Open
Abstract
Chemical shape and size play a critical role in chemistry. The van der Waals (vdW) radius, a familiar manifold used to quantify size by assuming overlapping spheres, provides rapid estimates of size in atoms, molecules, and materials. However, the vdW method may be too rigid to describe highly polarized systems and chemical species that stray from spherical atomistic environments. To deal with these exotic chemistries, numerous alternate methods based on electron density have been presented. While each boasts inherent generality, all define the size of a chemical system, in one way or another, by its electron density. Herein, we revisit the longstanding problem of assessing sizes of atoms and molecules, instead through examination of the local electric field produced by them. While conceptually different than nuclei-centered methods like that of van der Waals, the field assesses chemically affected volumes. This approach implicitly accounts for long-range fields in highly polar systems and predicts that cations should affect more space than neutral counterparts. Computing atomic and molecular volumes from DFT and ab initio-based electric fields.![]()
Collapse
Affiliation(s)
- Austin M Mroz
- Department of Chemistry and Biochemistry, University of Oregon Eugene OR 97403 USA
| | - Audrey M Davenport
- Department of Chemistry and Biochemistry, University of Oregon Eugene OR 97403 USA
| | - Jasper Sterling
- Department of Chemistry and Biochemistry, University of Oregon Eugene OR 97403 USA
| | - Joshua Davis
- Department of Chemistry and Biochemistry, University of Oregon Eugene OR 97403 USA
| | - Christopher H Hendon
- Department of Chemistry and Biochemistry, University of Oregon Eugene OR 97403 USA
| |
Collapse
|
8
|
Duan C, Chen S, Taylor MG, Liu F, Kulik HJ. Machine learning to tame divergent density functional approximations: a new path to consensus materials design principles. Chem Sci 2021; 12:13021-13036. [PMID: 34745533 PMCID: PMC8513898 DOI: 10.1039/d1sc03701c] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2021] [Accepted: 09/01/2021] [Indexed: 01/17/2023] Open
Abstract
Virtual high-throughput screening (VHTS) with density functional theory (DFT) and machine-learning (ML)-acceleration is essential in rapid materials discovery. By necessity, efficient DFT-based workflows are carried out with a single density functional approximation (DFA). Nevertheless, properties evaluated with different DFAs can be expected to disagree for cases with challenging electronic structure (e.g., open-shell transition-metal complexes, TMCs) for which rapid screening is most needed and accurate benchmarks are often unavailable. To quantify the effect of DFA bias, we introduce an approach to rapidly obtain property predictions from 23 representative DFAs spanning multiple families, “rungs” (e.g., semi-local to double hybrid) and basis sets on over 2000 TMCs. Although computed property values (e.g., spin state splitting and frontier orbital gap) differ by DFA, high linear correlations persist across all DFAs. We train independent ML models for each DFA and observe convergent trends in feature importance, providing DFA-invariant, universal design rules. We devise a strategy to train artificial neural network (ANN) models informed by all 23 DFAs and use them to predict properties (e.g., spin-splitting energy) of over 187k TMCs. By requiring consensus of the ANN-predicted DFA properties, we improve correspondence of computational lead compounds with literature-mined, experimental compounds over the typically employed single-DFA approach. Machine learning (ML)-based feature analysis reveals universal design rules regardless of density functional choices. Using the consensus among multiple functionals, we identify robust lead complexes in ML-accelerated chemical discovery.![]()
Collapse
Affiliation(s)
- Chenru Duan
- Department of Chemical Engineering, Massachusetts Institute of Technology Cambridge MA 02139 USA +1-617-253-4584.,Department of Chemistry, Massachusetts Institute of Technology Cambridge MA 02139 USA
| | - Shuxin Chen
- Department of Chemical Engineering, Massachusetts Institute of Technology Cambridge MA 02139 USA +1-617-253-4584.,Department of Chemistry, Massachusetts Institute of Technology Cambridge MA 02139 USA
| | - Michael G Taylor
- Department of Chemical Engineering, Massachusetts Institute of Technology Cambridge MA 02139 USA +1-617-253-4584
| | - Fang Liu
- Department of Chemical Engineering, Massachusetts Institute of Technology Cambridge MA 02139 USA +1-617-253-4584
| | - Heather J Kulik
- Department of Chemical Engineering, Massachusetts Institute of Technology Cambridge MA 02139 USA +1-617-253-4584
| |
Collapse
|
9
|
Nandy A, Duan C, Taylor MG, Liu F, Steeves AH, Kulik HJ. Computational Discovery of Transition-metal Complexes: From High-throughput Screening to Machine Learning. Chem Rev 2021; 121:9927-10000. [PMID: 34260198 DOI: 10.1021/acs.chemrev.1c00347] [Citation(s) in RCA: 70] [Impact Index Per Article: 23.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
Abstract
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.
Collapse
Affiliation(s)
- Aditya Nandy
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.,Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Chenru Duan
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.,Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Michael G Taylor
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Fang Liu
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Adam H Steeves
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Heather J Kulik
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| |
Collapse
|
10
|
Duan C, Liu F, Nandy A, Kulik HJ. Putting Density Functional Theory to the Test in Machine-Learning-Accelerated Materials Discovery. J Phys Chem Lett 2021; 12:4628-4637. [PMID: 33973793 DOI: 10.1021/acs.jpclett.1c00631] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/20/2023]
Abstract
Accelerated discovery with machine learning (ML) has begun to provide the advances in efficiency needed to overcome the combinatorial challenge of computational materials design. Nevertheless, ML-accelerated discovery both inherits the biases of training data derived from density functional theory (DFT) and leads to many attempted calculations that are doomed to fail. Many compelling functional materials and catalytic processes involve strained chemical bonds, open-shell radicals and diradicals, or metal-organic bonds to open-shell transition-metal centers. Although promising targets, these materials present unique challenges for electronic structure methods and combinatorial challenges for their discovery. In this Perspective, we describe the advances needed in accuracy, efficiency, and approach beyond what is typical in conventional DFT-based ML workflows. These challenges have begun to be addressed through ML models trained to predict the results of multiple methods or the differences between them, enabling quantitative sensitivity analysis. For DFT to be trusted for a given data point in a high-throughput screen, it must pass a series of tests. ML models that predict the likelihood of calculation success and detect the presence of strong correlation will enable rapid diagnoses and adaptation strategies. These "decision engines" represent the first steps toward autonomous workflows that avoid the need for expert determination of the robustness of DFT-based materials discoveries.
Collapse
Affiliation(s)
- Chenru Duan
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
- Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Fang Liu
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Aditya Nandy
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
- Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Heather J Kulik
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| |
Collapse
|
11
|
Affiliation(s)
- Heather J. Kulik
- Department of Chemical Engineering Massachusetts Institute of Technology 77 Massachusetts Ave Rm 66–464 Cambridge MA 02139 USA
| |
Collapse
|
12
|
Duan C, Liu F, Nandy A, Kulik HJ. Semi-supervised Machine Learning Enables the Robust Detection of Multireference Character at Low Cost. J Phys Chem Lett 2020; 11:6640-6648. [PMID: 32692570 DOI: 10.1021/acs.jpclett.0c02018] [Citation(s) in RCA: 23] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/26/2023]
Abstract
Multireference (MR) diagnostics are common tools for identifying strongly correlated electronic structure that makes single-reference (SR) methods (e.g., density functional theory or DFT) insufficient for accurate property prediction. However, MR diagnostics typically require computationally demanding correlated wave function theory (WFT) calculations, and diagnostics often disagree or fail to predict MR effects on properties. To overcome these challenges, we introduce a semi-supervised machine learning (ML) approach with virtual adversarial training (VAT) of an MR classifier using 15 WFT and DFT MR diagnostics as inputs. In semi-supervised learning, only the most extreme SR or MR points are labeled, and the remaining point labels are learned. The resulting VAT model outperforms the alternatives, as quantified by the distinct property distributions of SR- and MR-classified molecules. To reduce the cost of generating inputs to the VAT model, we leverage the VAT model's robustness to noisy inputs by replacing WFT MR diagnostics with regression predictions in an MR decision engine workflow that preserves excellent performance. We demonstrate the transferability of our approach to larger molecules and those with distinct chemical composition from the training set. This MR decision engine demonstrates promise as a low-cost, high-accuracy approach to the automatic detection of strong correlation for predictive high-throughput screening.
Collapse
Affiliation(s)
- Chenru Duan
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
- Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Fang Liu
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Aditya Nandy
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
- Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Heather J Kulik
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| |
Collapse
|
13
|
Duan C, Liu F, Nandy A, Kulik HJ. Data-Driven Approaches Can Overcome the Cost-Accuracy Trade-Off in Multireference Diagnostics. J Chem Theory Comput 2020; 16:4373-4387. [PMID: 32536161 DOI: 10.1021/acs.jctc.0c00358] [Citation(s) in RCA: 27] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
Abstract
High-throughput computational screening typically employs methods (i.e., density functional theory or DFT) that can fail to describe challenging molecules, such as those with strongly correlated electronic structure. In such cases, multireference (MR) correlated wavefunction theory (WFT) would be the appropriate choice but remains more challenging to carry out and automate than single-reference (SR) WFT or DFT. Numerous diagnostics have been proposed for identifying when MR character is likely to have an effect on the predictive power of SR calculations, but conflicting conclusions about diagnostic performance have been reached on small data sets. We compute 15 MR diagnostics, ranging from affordable DFT-based to more costly MR-WFT-based diagnostics, on a set of 3165 equilibrium and distorted small organic molecules containing up to six heavy atoms. Conflicting MR character assignments and low pairwise linear correlations among diagnostics are also observed over this set. We evaluate the ability of existing diagnostics to predict the percent recovery of the correlation energy, %Ecorr. None of the DFT-based diagnostics are nearly as predictive of %Ecorr as the best WFT-based diagnostics. To overcome the limitation of this cost-accuracy trade-off, we develop machine learning (ML, i.e., kernel ridge regression) models to predict WFT-based diagnostics from a combination of DFT-based diagnostics and a new, size-independent 3D geometric representation. The ML-predicted diagnostics correlate as well with MR effects as their computed (i.e., with WFT) values, significantly improving over the DFT-based diagnostics on which the models were trained. These ML models thus provide a promising approach to improve upon DFT-based diagnostic accuracy while remaining suitably low cost for high-throughput screening.
Collapse
Affiliation(s)
- Chenru Duan
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.,Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Fang Liu
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Aditya Nandy
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.,Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Heather J Kulik
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| |
Collapse
|
14
|
Mitrofanov A, Korolev V, Andreadi N, Petrov V, Kalmykov S. Simple Automatized Tool for Exchange-Correlation Functional Fitting. J Phys Chem A 2020; 124:2700-2707. [PMID: 32118431 DOI: 10.1021/acs.jpca.9b09093] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
Density functional theory is, perhaps, the most popular and convenient tool in computational chemistry. DFT methods allow solving different chemical tasks with a good balance of accuracy and computational time. Dozens of existing functionals cover a majority of possible systems, and the development of new ones is still ongoing. However, despite the existence of different databases with accurate quantum-chemical data, the functional design remains a complicated and time-demanding task. Here, we propose a novel approach for simplifying and accelerating this process. The approach is based on a Bayesian search with stochastic sub-sampling that allows considering the 'history' of fitting steps, reduces the computational time for each step, and avoids overfitting to training data. Besides the general testing of the approach efficiency, we also showed an example of training specialized DFT functionals, outperforming the popular ones. The approach is presented as a free code with built-in analysis tools. Using the code with an appropriate reference database can help in constructing a DFT approximation for a highly specialized task.
Collapse
Affiliation(s)
- Artem Mitrofanov
- Chemistry Department, Moscow State University, Moscow 119991, Russia
| | - Vadim Korolev
- Chemistry Department, Moscow State University, Moscow 119991, Russia
| | - Nikolai Andreadi
- Chemistry Department, Moscow State University, Moscow 119991, Russia
| | - Vladimir Petrov
- Chemistry Department, Moscow State University, Moscow 119991, Russia
| | - Stepan Kalmykov
- Chemistry Department, Moscow State University, Moscow 119991, Russia
| |
Collapse
|
15
|
Herr JE, Koh K, Yao K, Parkhill J. Compressing physics with an autoencoder: Creating an atomic species representation to improve machine learning models in the chemical sciences. J Chem Phys 2019; 151:084103. [DOI: 10.1063/1.5108803] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/06/2023] Open
Affiliation(s)
- John E. Herr
- Department of Chemistry and Biochemistry, The University of Notre Dame du Lac, 251 Nieuwland Science Hall, Notre Dame, Indiana 46556, USA
| | - Kevin Koh
- Department of Chemistry and Biochemistry, The University of Notre Dame du Lac, 251 Nieuwland Science Hall, Notre Dame, Indiana 46556, USA
| | - Kun Yao
- Department of Chemistry and Biochemistry, The University of Notre Dame du Lac, 251 Nieuwland Science Hall, Notre Dame, Indiana 46556, USA
| | - John Parkhill
- Department of Chemistry and Biochemistry, The University of Notre Dame du Lac, 251 Nieuwland Science Hall, Notre Dame, Indiana 46556, USA
| |
Collapse
|
16
|
Duan C, Janet JP, Liu F, Nandy A, Kulik HJ. Learning from Failure: Predicting Electronic Structure Calculation Outcomes with Machine Learning Models. J Chem Theory Comput 2019; 15:2331-2345. [DOI: 10.1021/acs.jctc.9b00057] [Citation(s) in RCA: 50] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
|
17
|
Gastegger M, González L, Marquetand P. Exploring density functional subspaces with genetic algorithms. MONATSHEFTE FUR CHEMIE 2018. [DOI: 10.1007/s00706-018-2335-3] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
18
|
Abstract
We investigate by explicit parameter optimization to what extent basis sets of polarized double-ζ quality can introduce compensating errors in five different density functional methods. It is shown that minor changes in the contraction coefficients of the valence functions in the basis sets can have a significant impact and allow different density functional methods to achieve very similar performances. This holds for nuclear magnetic shielding constants and for isomerization energies, barrier heights, and noncovalent interactions. It is furthermore shown that errors due to neglect of vibrational and solvent effects can be absorbed in the combined method and basis set errors. These findings hold for data sets consisting of 50-150 data points. This raises the question of whether the common practice of identifying combinations of density functional methods and basis sets that have a good performance against a selected set of reference data should be considered as data fitting in the combined parameter space spanned by the method and basis set.
Collapse
Affiliation(s)
- Frank Jensen
- Department of Chemistry , Aarhus University , DK-8000 Aarhus , Denmark
| |
Collapse
|
19
|
Amić A, Marković Z, Dimitrić Marković JM, Milenković D, Lučić B. The role of guaiacyl moiety in free radical scavenging by 3,5-dihydroxy-4-methoxybenzyl alcohol: thermodynamics of 3H+/3e− mechanisms. Mol Phys 2018. [DOI: 10.1080/00268976.2018.1506174] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/05/2023]
Affiliation(s)
- Ana Amić
- Department of Chemistry, Josip Juraj Strossmayer University of Osijek, Osijek, Croatia
| | - Zoran Marković
- Department of Chemical-Technological Sciences, State University of Novi Pazar, Novi Pazar, Serbia
| | | | - Dejan Milenković
- Bioengineering Research and Development Center, Kragujevac, Serbia
| | - Bono Lučić
- NMR Centre, Ruđer Bošković Institute, Zagreb, Croatia
| |
Collapse
|