1
|
Aldossary A, Campos-Gonzalez-Angulo JA, Pablo-García S, Leong SX, Rajaonson EM, Thiede L, Tom G, Wang A, Avagliano D, Aspuru-Guzik A. In Silico Chemical Experiments in the Age of AI: From Quantum Chemistry to Machine Learning and Back. ADVANCED MATERIALS (DEERFIELD BEACH, FLA.) 2024:e2402369. [PMID: 38794859 DOI: 10.1002/adma.202402369] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/15/2024] [Revised: 04/28/2024] [Indexed: 05/26/2024]
Abstract
Computational chemistry is an indispensable tool for understanding molecules and predicting chemical properties. However, traditional computational methods face significant challenges due to the difficulty of solving the Schrödinger equations and the increasing computational cost with the size of the molecular system. In response, there has been a surge of interest in leveraging artificial intelligence (AI) and machine learning (ML) techniques to in silico experiments. Integrating AI and ML into computational chemistry increases the scalability and speed of the exploration of chemical space. However, challenges remain, particularly regarding the reproducibility and transferability of ML models. This review highlights the evolution of ML in learning from, complementing, or replacing traditional computational chemistry for energy and property predictions. Starting from models trained entirely on numerical data, a journey set forth toward the ideal model incorporating or learning the physical laws of quantum mechanics. This paper also reviews existing computational methods and ML models and their intertwining, outlines a roadmap for future research, and identifies areas for improvement and innovation. Ultimately, the goal is to develop AI architectures capable of predicting accurate and transferable solutions to the Schrödinger equation, thereby revolutionizing in silico experiments within chemistry and materials science.
Collapse
Affiliation(s)
- Abdulrahman Aldossary
- Department of Chemistry, University of Toronto, 80 St. George Street, Toronto, ON, M5S 3H6, Canada
| | | | - Sergio Pablo-García
- Department of Chemistry, University of Toronto, 80 St. George Street, Toronto, ON, M5S 3H6, Canada
- Department of Computer Science, University of Toronto, 40 St. George Street, Toronto, ON, M5S 2E4, Canada
| | - Shi Xuan Leong
- Department of Chemistry, University of Toronto, 80 St. George Street, Toronto, ON, M5S 3H6, Canada
| | - Ella Miray Rajaonson
- Department of Chemistry, University of Toronto, 80 St. George Street, Toronto, ON, M5S 3H6, Canada
- Vector Institute for Artificial Intelligence, 661 University Ave. Suite 710, Toronto, ON, M5G 1M1, Canada
| | - Luca Thiede
- Department of Computer Science, University of Toronto, 40 St. George Street, Toronto, ON, M5S 2E4, Canada
- Vector Institute for Artificial Intelligence, 661 University Ave. Suite 710, Toronto, ON, M5G 1M1, Canada
| | - Gary Tom
- Department of Chemistry, University of Toronto, 80 St. George Street, Toronto, ON, M5S 3H6, Canada
- Vector Institute for Artificial Intelligence, 661 University Ave. Suite 710, Toronto, ON, M5G 1M1, Canada
| | - Andrew Wang
- Department of Chemistry, University of Toronto, 80 St. George Street, Toronto, ON, M5S 3H6, Canada
| | - Davide Avagliano
- Chimie ParisTech, PSL University, CNRS, Institute of Chemistry for Life and Health Sciences (iCLeHS UMR 8060), Paris, F-75005, France
| | - Alán Aspuru-Guzik
- Department of Chemistry, University of Toronto, 80 St. George Street, Toronto, ON, M5S 3H6, Canada
- Department of Computer Science, University of Toronto, 40 St. George Street, Toronto, ON, M5S 2E4, Canada
- Vector Institute for Artificial Intelligence, 661 University Ave. Suite 710, Toronto, ON, M5G 1M1, Canada
- Department of Materials Science & Engineering, University of Toronto, 184 College St., Toronto, ON, M5S 3E4, Canada
- Department of Chemical Engineering & Applied Chemistry, University of Toronto, 200 College St., Toronto, ON, M5S 3E5, Canada
- Lebovic Fellow, Canadian Institute for Advanced Research (CIFAR), 66118 University Ave., Toronto, M5G 1M1, Canada
- Acceleration Consortium, 80 St George St, Toronto, M5S 3H6, Canada
| |
Collapse
|
2
|
Lim H. Development of scoring-assisted generative exploration (SAGE) and its application to dual inhibitor design for acetylcholinesterase and monoamine oxidase B. J Cheminform 2024; 16:59. [PMID: 38790018 PMCID: PMC11127438 DOI: 10.1186/s13321-024-00845-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/18/2023] [Accepted: 04/26/2024] [Indexed: 05/26/2024] Open
Abstract
De novo molecular design is the process of searching chemical space for drug-like molecules with desired properties, and deep learning has been recognized as a promising solution. In this study, I developed an effective computational method called Scoring-Assisted Generative Exploration (SAGE) to enhance chemical diversity and property optimization through virtual synthesis simulation, the generation of bridged bicyclic rings, and multiple scoring models for drug-likeness. In six protein targets, SAGE generated molecules with high scores within reasonable numbers of steps by optimizing target specificity without a constraint and even with multiple constraints such as synthetic accessibility, solubility, and metabolic stability. Furthermore, I suggested a top-ranked molecule with SAGE as dual inhibitors of acetylcholinesterase and monoamine oxidase B through multiple desired property optimization. Therefore, SAGE can generate molecules with desired properties by optimizing multiple properties simultaneously, indicating the importance of de novo design strategies in the future of drug discovery and development. SCIENTIFIC CONTRIBUTION: The scientific contribution of this study lies in the development of the Scoring-Assisted Generative Exploration (SAGE) method, a novel computational approach that significantly enhances de novo molecular design. SAGE uniquely integrates virtual synthesis simulation, the generation of complex bridged bicyclic rings, and multiple scoring models to optimize drug-like properties comprehensively. By efficiently generating molecules that meet a broad spectrum of pharmacological criteria-including target specificity, synthetic accessibility, solubility, and metabolic stability-within a reasonable number of steps, SAGE represents a substantial advancement over traditional methods. Additionally, the application of SAGE to discover dual inhibitors for acetylcholinesterase and monoamine oxidase B not only demonstrates its potential to streamline and enhance the drug development process but also highlights its capacity to create more effective and precisely targeted therapies. This study emphasizes the critical and evolving role of de novo design strategies in reshaping the future of drug discovery and development, providing promising avenues for innovative therapeutic discoveries.
Collapse
Affiliation(s)
- Hocheol Lim
- Bioinformatics and Molecular Design Research Center (BMDRC), Incheon, Republic of Korea.
| |
Collapse
|
3
|
Schatz GC, Wodtke AM, Yang X. Spiers Memorial Lecture: New directions in molecular scattering. Faraday Discuss 2024. [PMID: 38764350 DOI: 10.1039/d4fd00015c] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/21/2024]
Abstract
The field of molecular scattering is reviewed as it pertains to gas-gas as well as gas-surface chemical reaction dynamics. We emphasize the importance of collaboration of experiment and theory, from which new directions of research are being pursued on increasingly complex problems. We review both experimental and theoretical advances that provide the modern toolbox available to molecular-scattering studies. We distinguish between two classes of work. The first involves simple systems and uses experiment to validate theory so that from the validated theory, one may learn far more than could ever be measured in the laboratory. The second class involves problems of great complexity that would be difficult or impossible to understand without a partnership of experiment and theory. Key topics covered in this review include crossed-beams reactive scattering and scattering at extremely low energies, where quantum effects dominate. They also include scattering from surfaces, reactive scattering and kinetics at surfaces, and scattering work done at liquid surfaces. The review closes with thoughts on future promising directions of research.
Collapse
Affiliation(s)
- George C Schatz
- Dept of Chemistry, Northwestern University, Evanston, Illinois 60208, USA
| | - Alec M Wodtke
- Institute for Physical Chemistry, Georg August University, Goettingen, Germany
- Max Planck Institute for Multidisciplinary Natural Sciences, Goettingen, Germany.
- International Center for the Advanced Studies of Energy Conversion, Georg August University, Goettingen, Germany
| | - Xueming Yang
- Dalian Institute for Chemical Physics, Chinese Academy of Sciences, Dalian, China
- Department of Chemistry, College of Science, Southern University of Science and Technology, Shenzhen, China
| |
Collapse
|
4
|
Shakiba M, Akimov AV. Machine-Learned Kohn-Sham Hamiltonian Mapping for Nonadiabatic Molecular Dynamics. J Chem Theory Comput 2024; 20:2992-3007. [PMID: 38581699 DOI: 10.1021/acs.jctc.4c00008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/08/2024]
Abstract
In this work, we report a simple, efficient, and scalable machine-learning (ML) approach for mapping non-self-consistent Kohn-Sham Hamiltonians constructed with one kind of density functional to the nearly self-consistent Hamiltonians constructed with another kind of density functional. This approach is designed as a fast surrogate Hamiltonian calculator for use in long nonadiabatic dynamics simulations of large atomistic systems. In this approach, the input and output features are Hamiltonian matrices computed from different levels of theory. We demonstrate that the developed ML-based Hamiltonian mapping method (1) speeds up the calculations by several orders of magnitude, (2) is conceptually simpler than alternative ML approaches, (3) is applicable to different systems and sizes and can be used for mapping Hamiltonians constructed with arbitrary density functionals, (4) requires a modest training data, learns fast, and generates molecular orbitals and their energies with the accuracy nearly matching that of conventional calculations, and (5) when applied to nonadiabatic dynamics simulation of excitation energy relaxation in large systems yields the corresponding time scales within the margin of error of the conventional calculations. Using this approach, we explore the excitation energy relaxation in C60 fullerene and Si75H64 quantum dot structures and derive qualitative and quantitative insights into dynamics in these systems.
Collapse
Affiliation(s)
- Mohammad Shakiba
- Department of Chemistry, University at Buffalo, The State University of New York, Buffalo, New York 14260, United States
| | - Alexey V Akimov
- Department of Chemistry, University at Buffalo, The State University of New York, Buffalo, New York 14260, United States
| |
Collapse
|
5
|
Gallegos M, Isamura BK, Popelier PLA, Martín Pendás Á. An Unsupervised Machine Learning Approach for the Automatic Construction of Local Chemical Descriptors. J Chem Inf Model 2024; 64:3059-3079. [PMID: 38498942 DOI: 10.1021/acs.jcim.3c01906] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/20/2024]
Abstract
Condensing the many physical variables defining a chemical system into a fixed-size array poses a significant challenge in the development of chemical Machine Learning (ML). Atom Centered Symmetry Functions (ACSFs) offer an intuitive featurization approach by means of a tedious and labor-intensive selection of tunable parameters. In this work, we implement an unsupervised ML strategy relying on a Gaussian Mixture Model (GMM) to automatically optimize the ACSF parameters. GMMs effortlessly decompose the vastness of the chemical and conformational spaces into well-defined radial and angular clusters, which are then used to build tailor-made ACSFs. The unsupervised exploration of the space has demonstrated general applicability across a diverse range of systems, spanning from various unimolecular landscapes to heterogeneous databases. The impact of the sampling technique and temperature on space exploration is also addressed, highlighting the particularly advantageous role of high-temperature Molecular Dynamics (MD) simulations. The reliability of the resulting features is assessed through the estimation of the atomic charges of a prototypical capped amino acid and a heterogeneous collection of CHON molecules. The automatically constructed ACSFs serve as high-quality descriptors, consistently yielding typical prediction errors below 0.010 electrons bound for the reported atomic charges. Altering the spatial distribution of the functions with respect to the cluster highlights the critical role of symmetry rupture in achieving significantly improved features. More specifically, using two separate functions to describe the lower and upper tails of the cluster results in the best performing models with errors as low as 0.006 electrons. Finally, the effectiveness of finely tuned features was checked across different architectures, unveiling the superior performance of Gaussian Process (GP) models over Feed Forward Neural Networks (FFNNs), particularly in low-data regimes, with nearly a 2-fold increase in prediction quality. Altogether, this approach paves the way toward an easier construction of local chemical descriptors, while providing valuable insights into how radial and angular spaces should be mapped. Finally, this work opens the possibility of encoding many-body information beyond angular terms into upcoming ML features.
Collapse
Affiliation(s)
- Miguel Gallegos
- Department of Analytical and Physical Chemistry, University of Oviedo, Oviedo E-33006, Spain
| | | | - Paul L A Popelier
- Department of Chemistry, The University of Manchester, Oxford Road, Manchester M13 9PL, U.K
| | - Ángel Martín Pendás
- Department of Analytical and Physical Chemistry, University of Oviedo, Oviedo E-33006, Spain
| |
Collapse
|
6
|
Unke OT, Stöhr M, Ganscha S, Unterthiner T, Maennel H, Kashubin S, Ahlin D, Gastegger M, Medrano Sandonas L, Berryman JT, Tkatchenko A, Müller KR. Biomolecular dynamics with machine-learned quantum-mechanical force fields trained on diverse chemical fragments. SCIENCE ADVANCES 2024; 10:eadn4397. [PMID: 38579003 DOI: 10.1126/sciadv.adn4397] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/10/2023] [Accepted: 02/29/2024] [Indexed: 04/07/2024]
Abstract
The GEMS method enables molecular dynamics simulations of large heterogeneous systems at ab initio quality.
Collapse
Affiliation(s)
- Oliver T Unke
- Google DeepMind, Tucholskystraße 2, 10117 Berlin, Germany and Brandschenkestrasse 110, 8002 Zürich, Switzerland
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- DFG Cluster of Excellence "Unifying Systems in Catalysis" (UniSysCat), Technische Universität Berlin, 10623 Berlin, Germany
| | - Martin Stöhr
- Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Stefan Ganscha
- Google DeepMind, Tucholskystraße 2, 10117 Berlin, Germany and Brandschenkestrasse 110, 8002 Zürich, Switzerland
| | - Thomas Unterthiner
- Google DeepMind, Tucholskystraße 2, 10117 Berlin, Germany and Brandschenkestrasse 110, 8002 Zürich, Switzerland
| | - Hartmut Maennel
- Google DeepMind, Tucholskystraße 2, 10117 Berlin, Germany and Brandschenkestrasse 110, 8002 Zürich, Switzerland
| | - Sergii Kashubin
- Google DeepMind, Tucholskystraße 2, 10117 Berlin, Germany and Brandschenkestrasse 110, 8002 Zürich, Switzerland
| | - Daniel Ahlin
- Google DeepMind, Tucholskystraße 2, 10117 Berlin, Germany and Brandschenkestrasse 110, 8002 Zürich, Switzerland
| | - Michael Gastegger
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- DFG Cluster of Excellence "Unifying Systems in Catalysis" (UniSysCat), Technische Universität Berlin, 10623 Berlin, Germany
- BASLEARN - TU Berlin/BASF Joint Lab for Machine Learning, Technische Universität Berlin, 10587 Berlin, Germany
| | - Leonardo Medrano Sandonas
- Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Joshua T Berryman
- Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Alexandre Tkatchenko
- Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Klaus-Robert Müller
- Google DeepMind, Tucholskystraße 2, 10117 Berlin, Germany and Brandschenkestrasse 110, 8002 Zürich, Switzerland
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- Department of Artificial Intelligence, Korea University, Anam-dong, Seongbuk-gu, Seoul 02841, Korea
- Max Planck Institute for Informatics, Stuhlsatzenhausweg, 66123 Saarbrücken, Germany
- BIFOLD - Berlin Institute for the Foundations of Learning and Data, Berlin, Germany
| |
Collapse
|
7
|
Cignoni E, Suman D, Nigam J, Cupellini L, Mennucci B, Ceriotti M. Electronic Excited States from Physically Constrained Machine Learning. ACS CENTRAL SCIENCE 2024; 10:637-648. [PMID: 38559300 PMCID: PMC10979507 DOI: 10.1021/acscentsci.3c01480] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/30/2023] [Revised: 01/16/2024] [Accepted: 01/30/2024] [Indexed: 04/04/2024]
Abstract
Data-driven techniques are increasingly used to replace electronic-structure calculations of matter. In this context, a relevant question is whether machine learning (ML) should be applied directly to predict the desired properties or combined explicitly with physically grounded operations. We present an example of an integrated modeling approach in which a symmetry-adapted ML model of an effective Hamiltonian is trained to reproduce electronic excitations from a quantum-mechanical calculation. The resulting model can make predictions for molecules that are much larger and more complex than those on which it is trained and allows for dramatic computational savings by indirectly targeting the outputs of well-converged calculations while using a parametrization corresponding to a minimal atom-centered basis. These results emphasize the merits of intertwining data-driven techniques with physical approximations, improving the transferability and interpretability of ML models without affecting their accuracy and computational efficiency and providing a blueprint for developing ML-augmented electronic-structure methods.
Collapse
Affiliation(s)
- Edoardo Cignoni
- Dipartimento
di Chimica e Chimica Industriale, Università
di Pisa, 56126 Pisa, Italy
| | - Divya Suman
- Laboratory
of Computational Science and Modeling, Institut des Matériaux, École Polytechnique Fédérale
de Lausanne, 1015 Lausanne, Switzerland
| | - Jigyasa Nigam
- Laboratory
of Computational Science and Modeling, Institut des Matériaux, École Polytechnique Fédérale
de Lausanne, 1015 Lausanne, Switzerland
| | - Lorenzo Cupellini
- Dipartimento
di Chimica e Chimica Industriale, Università
di Pisa, 56126 Pisa, Italy
| | - Benedetta Mennucci
- Dipartimento
di Chimica e Chimica Industriale, Università
di Pisa, 56126 Pisa, Italy
| | - Michele Ceriotti
- Laboratory
of Computational Science and Modeling, Institut des Matériaux, École Polytechnique Fédérale
de Lausanne, 1015 Lausanne, Switzerland
- Division
of Chemistry and Chemical Engineering, California
Institute of Technology, Pasadena, California 91125, United States
| |
Collapse
|
8
|
Dral PO. AI in computational chemistry through the lens of a decade-long journey. Chem Commun (Camb) 2024; 60:3240-3258. [PMID: 38444290 DOI: 10.1039/d4cc00010b] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/07/2024]
Abstract
This article gives a perspective on the progress of AI tools in computational chemistry through the lens of the author's decade-long contributions put in the wider context of the trends in this rapidly expanding field. This progress over the last decade is tremendous: while a decade ago we had a glimpse of what was to come through many proof-of-concept studies, now we witness the emergence of many AI-based computational chemistry tools that are mature enough to make faster and more accurate simulations increasingly routine. Such simulations in turn allow us to validate and even revise experimental results, deepen our understanding of the physicochemical processes in nature, and design better materials, devices, and drugs. The rapid introduction of powerful AI tools gives rise to unique challenges and opportunities that are discussed in this article too.
Collapse
Affiliation(s)
- Pavlo O Dral
- State Key Laboratory of Physical Chemistry of Solid Surfaces, College of Chemistry and Chemical Engineering, Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry, and Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province (IKKEM), Xiamen University, Xiamen, Fujian 361005, China.
| |
Collapse
|
9
|
Issa AA, Kamel MD, El-Sayed DS. Depicted simulation model for removal of second-generation antipsychotic drugs adsorbed on Zn-MOF: adsorption locator assessment. J Mol Model 2024; 30:106. [PMID: 38491151 DOI: 10.1007/s00894-024-05896-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2024] [Accepted: 03/02/2024] [Indexed: 03/18/2024]
Abstract
CONTEXT Electronic durable behavior on the material surface was accompanied by a class of antipsychotic drugs (APD) to describe the surface modification in the designed adsorption model. Hierarchically Zn-MOF system was utilized for estimating its capacity for drug molecule removal. Geometrically optimized strategy on the studied systems was performed using DFT/GGA/PBE. FMOs analysis was depicted based on the same level of calculations, and molecular electrostatic potential surface (MEP) was generated for unadsorbed and adsorbed systems to illustrate the variation in the surface-active sites. By interpreting the electronic density of states (DOS), the atomic orbital can be identified as a major or minor electronic distribution by PDOS graph. Adsorption locating behavior was considered to detect the significant surface interaction mode between APD and Zn-MOF surface based on lower adsorption energy. The stability of the adsorbed model was best described through dynamic simulation analysis with time through elevated temperatures. The non-covalent interactions were described using RDG/NCI analysis to show the major favorable surface interaction predicting the highly stable adsorption system. METHODS The most accurate geometrical computations were performed using the materials studio software followed by surface cleavage and vacuum slab generation. The first principle of DFT was used to apply CASTEP module with GGA/PBE method for band structure and DOS calculations. Three systems of antipsychotic drugs were computationally studied using CASTEP simulation package and adsorbed on an optimized Zn-MOF surface. Adsorption locator module predicted the preferred adsorption mechanistic models, in which the first model was arranged to be more stable, to confirm the occurrence of some interactions in the adsorption mechanism.
Collapse
Affiliation(s)
- Ali Abdullah Issa
- Department of Applied Sciences, University of Technology, Baghdad, Iraq
| | | | - Doaa S El-Sayed
- Chemistry Department, Faculty of Science, Alexandria University, Alexandria, Egypt.
| |
Collapse
|
10
|
Pathirage PDVS, Phillips JT, Vogiatzis KD. Exploration of the Two-Electron Excitation Space with Data-Driven Coupled Cluster. J Phys Chem A 2024. [PMID: 38422511 DOI: 10.1021/acs.jpca.3c06600] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/02/2024]
Abstract
Computational cost limits the applicability of post-Hartree-Fock methods such as coupled-cluster on larger molecular systems. The data-driven coupled-cluster (DDCC) method applies machine learning to predict the coupled-cluster two-electron amplitudes (t2) using data from second-order perturbation theory (MP2). One major limitation of the DDCC models is the size of training sets that increases exponentially with the system size. Effective sampling of the amplitude space can resolve this issue. Five different amplitude selection techniques that reduce the amount of data used for training were evaluated, an approach that also prevents model overfitting and increases the portability of data-driven coupled-cluster singles and doubles to more complex molecules or larger basis sets. In combination with a localized orbital formalism to predict the CCSD t2 amplitudes, we have achieved a 10-fold error reduction for energy calculations.
Collapse
Affiliation(s)
- P D Varuna S Pathirage
- Department of Chemistry, University of Tennessee, Knoxville, Tennessee 37996-1600, United States
| | - Justin T Phillips
- Department of Chemistry, University of Tennessee, Knoxville, Tennessee 37996-1600, United States
| | - Konstantinos D Vogiatzis
- Department of Chemistry, University of Tennessee, Knoxville, Tennessee 37996-1600, United States
| |
Collapse
|
11
|
Briling K, Calvino Alonso Y, Fabrizio A, Corminboeuf C. SPA HM(a,b): Encoding the Density Information from Guess Hamiltonian in Quantum Machine Learning Representations. J Chem Theory Comput 2024; 20:1108-1117. [PMID: 38227222 PMCID: PMC10867806 DOI: 10.1021/acs.jctc.3c01040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2023] [Revised: 12/20/2023] [Accepted: 12/26/2023] [Indexed: 01/17/2024]
Abstract
Recently, we introduced a class of molecular representations for kernel-based regression methods─the spectrum of approximated Hamiltonian matrices (SPAHM)─that takes advantage of lightweight one-electron Hamiltonians traditionally used as a self-consistent field initial guess. The original SPAHM variant is built from occupied-orbital energies (i.e., eigenvalues) and naturally contains all of the information about nuclear charges, atomic positions, and symmetry requirements. Its advantages were demonstrated on data sets featuring a wide variation of charge and spin, for which traditional structure-based representations commonly fail. SPAHM(a,b), as introduced here, expand the eigenvalue SPAHM into local and transferable representations. They rely upon one-electron density matrices to build fingerprints from atomic and bond density overlap contributions inspired from preceding state-of-the-art representations. The performance and efficiency of SPAHM(a,b) is assessed on the predictions for data sets of prototypical organic molecules (QM7) of different charges and azoheteroarene dyes in an excited state. Overall, both SPAHM(a) and SPAHM(b) outperform state-of-the-art representations on difficult prediction tasks such as the atomic properties of charged open-shell species and of π-conjugated systems.
Collapse
Affiliation(s)
- Ksenia
R. Briling
- Laboratory
for Computational Molecular Design, Institute of Chemical Sciences
and Engineering, École Polytechnique
Fédérale de Lausanne, 1015 Lausanne, Switzerland
| | - Yannick Calvino Alonso
- Laboratory
for Computational Molecular Design, Institute of Chemical Sciences
and Engineering, École Polytechnique
Fédérale de Lausanne, 1015 Lausanne, Switzerland
| | - Alberto Fabrizio
- Laboratory
for Computational Molecular Design, Institute of Chemical Sciences
and Engineering, École Polytechnique
Fédérale de Lausanne, 1015 Lausanne, Switzerland
- National
Centre for Computational Design and Discovery of Novel Materials (MARVEL), École Polytechnique Fédérale
de Lausanne, 1015 Lausanne, Switzerland
| | - Clemence Corminboeuf
- Laboratory
for Computational Molecular Design, Institute of Chemical Sciences
and Engineering, École Polytechnique
Fédérale de Lausanne, 1015 Lausanne, Switzerland
- National
Centre for Computational Design and Discovery of Novel Materials (MARVEL), École Polytechnique Fédérale
de Lausanne, 1015 Lausanne, Switzerland
| |
Collapse
|
12
|
Jijila B, Nirmala V, Selvarengan P, Kavitha D, Arun Muthuraj V, Rajagopal A. Employing neural density functionals to generate potential energy surfaces. J Mol Model 2024; 30:65. [PMID: 38340208 DOI: 10.1007/s00894-024-05834-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Accepted: 01/04/2024] [Indexed: 02/12/2024]
Abstract
CONTEXT With the union of machine learning (ML) and quantum chemistry, amid the debate between machine-learned functionals and human-designed functionals in density functional theory (DFT), this paper aims to demonstrate the generation of potential energy surfaces using computations with machine-learned density functional approximation (ML-DFA). A recent research trend is the application of ML in quantum sciences in the design of density functionals such as DeepMind's Deep Learning model (DeepMind21, DM21). Though science reported the state-of-the-art performance of DM21, the opportunity to utilize DeepMind's pretrained DM21 neural networks in computations in quantum chemistry has not yet been tapped. So far in the literature, the Deep Learning density functionals (DM21) have not been applied to generate potential energy surfaces. While the superior accuracy of DM21 has been reported, there is still a scarcity of publications that apply DM21 in calculations in the field. In this context, for the first time in literature, neural density functionals inferring 2D potential energy surfaces (ML-DFA-PES) based on machine-learned DFA-based computational method is contributed in this paper. This paper reports the ML-DFA-generated PES for C4H8, H2O, H2, and H2+ by employing a pretrained DM21m TensorFlow model with cc-pVDZ basis set. In addition, we also analyze the long-range behavior of DM21 based PES to investigate the ability to describe a system at long ranges. Furthermore, we compare PES diagrams from DM21 with popular DFT functionals (b3lyp/ PW6B95) and CCSD(T). METHODS In this method, 2D potential energy surfaces are obtained using a method that relies upon the neural network's ability to accurately learn the mapping between 3D electron density and exchange-correlation potential. By inserting Deep Learning inference in DFT with a pretrained neural network, self-consistent field (SCF) energy at different geometries along the coordinates of interest is computed, and then, potential energy surfaces are plotted. In this method, first, the electron density is computed mathematically, and this computed 3D electron density is used as a ML feature vector to predict the exchange correlation potential as a ML inference computed by a forward pass of pre-trained DM21 TensorFlow computational graph, followed by the computation of self-consistent field energy at multiple geometries, and then, SCF energies at different bond lengths/angles are plotted as 2D PES. We implement this in a python source code using frameworks such as PySCF and DM21. This paper contributes this implementation in open source. The source code and DM21-DFA-based PES are contributed at https://sites.google.com/view/MLfunctionals-DeepMind-PES .
Collapse
Affiliation(s)
- B Jijila
- Queen Mary's College, Chennai, India
| | - V Nirmala
- Queen Mary's College, Chennai, India.
| | - P Selvarengan
- Kalasalingam Academy of Research & Education, Krishnankoil, India
| | - D Kavitha
- Dr. MGR Educational and Research Institute, Chennai, India
| | | | - A Rajagopal
- Indian Institute of Technology, Madras, India
| |
Collapse
|
13
|
Lewis L, Huang HY, Tran VT, Lehner S, Kueng R, Preskill J. Improved machine learning algorithm for predicting ground state properties. Nat Commun 2024; 15:895. [PMID: 38291046 PMCID: PMC10828424 DOI: 10.1038/s41467-024-45014-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2023] [Accepted: 01/08/2024] [Indexed: 02/01/2024] Open
Abstract
Finding the ground state of a quantum many-body system is a fundamental problem in quantum physics. In this work, we give a classical machine learning (ML) algorithm for predicting ground state properties with an inductive bias encoding geometric locality. The proposed ML model can efficiently predict ground state properties of an n-qubit gapped local Hamiltonian after learning from only [Formula: see text] data about other Hamiltonians in the same quantum phase of matter. This improves substantially upon previous results that require [Formula: see text] data for a large constant c. Furthermore, the training and prediction time of the proposed ML model scale as [Formula: see text] in the number of qubits n. Numerical experiments on physical systems with up to 45 qubits confirm the favorable scaling in predicting ground state properties using a small training dataset.
Collapse
Affiliation(s)
- Laura Lewis
- California Institute of Technology, Pasadena, CA, USA
- University of Cambridge, Cambridge, UK
| | - Hsin-Yuan Huang
- California Institute of Technology, Pasadena, CA, USA.
- Massachusetts Institute of Technology, Cambridge, MA, USA.
- Google Quantum AI, Venice, CA, USA.
| | | | | | | | - John Preskill
- California Institute of Technology, Pasadena, CA, USA
- AWS Center for Quantum Computing, Pasadena, CA, USA
| |
Collapse
|
14
|
Xu X, Soriano-Agueda L, López X, Ramos-Cordoba E, Matito E. All-Purpose Measure of Electron Correlation for Multireference Diagnostics. J Chem Theory Comput 2024; 20:721-727. [PMID: 38157841 PMCID: PMC10809408 DOI: 10.1021/acs.jctc.3c01073] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2023] [Revised: 11/24/2023] [Accepted: 11/27/2023] [Indexed: 01/03/2024]
Abstract
We present an analytical relationship between two natural orbital occupancy-based indices, I N D ¯ and INDmax, and two established electron correlation metrics: the leading term of a configuration interaction expansion, c0, and the D2 diagnostic. Numerical validation revealed that I N D ¯ and INDmax can effectively substitute for c0 and D2, respectively. These indices offer three distinct advantages: (i) they are universally applicable across all electronic structure methods, (ii) their interpretation is more intuitive, and (iii) they can be readily incorporated into the development of hybrid electronic structure methods. Additionally, we draw a distinction between correlation measures and correlation diagnostics, establishing MP2 and CCSD numerical thresholds for INDmax, which are to be used as a multireference diagnostic. Our findings further demonstrate that establishing thresholds for other electronic structure methods can be easily accomplished using small data sets.
Collapse
Affiliation(s)
- Xiang Xu
- Donostia
International Physics Center (DIPC), 20018 Donostia, Euskadi, Spain
- Polimero
eta Material Aurreratuak: Fisika, Kimika eta Teknologia, Kimika Fakultatea, Euskal Herriko Unibertsitatea UPV/EHU, P.K. 1072, 20080 Donostia, Euskadi, Spain
| | - Luis Soriano-Agueda
- Donostia
International Physics Center (DIPC), 20018 Donostia, Euskadi, Spain
| | - Xabier López
- Donostia
International Physics Center (DIPC), 20018 Donostia, Euskadi, Spain
- Polimero
eta Material Aurreratuak: Fisika, Kimika eta Teknologia, Kimika Fakultatea, Euskal Herriko Unibertsitatea UPV/EHU, P.K. 1072, 20080 Donostia, Euskadi, Spain
| | - Eloy Ramos-Cordoba
- Donostia
International Physics Center (DIPC), 20018 Donostia, Euskadi, Spain
- Polimero
eta Material Aurreratuak: Fisika, Kimika eta Teknologia, Kimika Fakultatea, Euskal Herriko Unibertsitatea UPV/EHU, P.K. 1072, 20080 Donostia, Euskadi, Spain
- Ikerbasque
Foundation for Science, Plaza Euskadi 5, 48009 Bilbao, Spain
| | - Eduard Matito
- Donostia
International Physics Center (DIPC), 20018 Donostia, Euskadi, Spain
- Ikerbasque
Foundation for Science, Plaza Euskadi 5, 48009 Bilbao, Spain
| |
Collapse
|
15
|
Barrett R, Westermayr J. Reinforcement Learning for Traversing Chemical Structure Space: Optimizing Transition States and Minimum Energy Paths of Molecules. J Phys Chem Lett 2024; 15:349-356. [PMID: 38170921 PMCID: PMC10788951 DOI: 10.1021/acs.jpclett.3c02771] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2023] [Revised: 12/05/2023] [Accepted: 12/08/2023] [Indexed: 01/05/2024]
Abstract
In recent years, deep learning has made remarkable strides, surpassing human capabilities in tasks, such as strategy games, and it has found applications in complex domains, including protein folding. In the realm of quantum chemistry, machine learning methods have primarily served as predictive tools or design aids using generative models, while reinforcement learning remains in its early stages of exploration. This work introduces an actor-critic reinforcement learning framework suitable for diverse optimization tasks, such as searching for molecular structures with specific properties within conformational spaces. As an example, we show an implementation of this scheme for calculating minimum energy pathways of a Claisen rearrangement reaction and a number of SN2 reactions. The results show that the algorithm is able to accurately predict minimum energy pathways and, thus, transition states, providing the first steps in using actor-critic methods to study chemical reactions.
Collapse
Affiliation(s)
- Rhyan Barrett
- Institute
of Chemistry, Faculty of Chemistry and Mineralogy, University of Leipzig, Johannisallee 29, 04103 Leipzig, Germany
| | - Julia Westermayr
- Institute
of Chemistry, Faculty of Chemistry and Mineralogy, University of Leipzig, Johannisallee 29, 04103 Leipzig, Germany
- Center
for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI),
Dresden/Leipzig, Humboldtstraße
25, 04105 Leipzig, Germany
| |
Collapse
|
16
|
Lin HH, Wang CI, Yang CH, Secario MK, Hsu CP. Two-Step Machine Learning Approach for Charge-Transfer Coupling with Structurally Diverse Data. J Phys Chem A 2024; 128:271-280. [PMID: 38157315 DOI: 10.1021/acs.jpca.3c04524] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/03/2024]
Abstract
Electronic coupling is important in determining charge-transfer rates and dynamics. Coupling strength is sensitive to both intermolecular, e.g., orientation or distance, and intramolecular degrees of freedom. Hence, it is challenging to build an accurate machine learning model to predict electronic coupling of molecular pairs, especially for those derived from the amorphous phase, for which intermolecular configurations are much more diverse than those derived from crystals. In this work, we devise a new prediction algorithm that employs two consecutive KRR models. The first model predicts molecular orbitals (MOs) from structural variation for each fragment, and coupling is further predicted by using the overlap integral included in a second model. With our two-step procedure, we achieved mean absolute errors of 0.27 meV for an ethylene dimer and 1.99 meV for a naphthalene pair, much improved accuracy amounting to 14-fold and 3-fold error reductions, respectively. In addition, MOs from the first model can also be the starting point to obtain other quantum chemical properties from atomistic structures. This approach is also compatible with a MO predictor with sufficient accuracy.
Collapse
Affiliation(s)
- Hung-Hsuan Lin
- Institute of Chemistry, Academia Sinica, 128 Section 2 Academia Road, Nankang, Taipei 115, Taiwan
- Molecular Science and Digital Innovation Center, Genetics Generation Advancement Corp, No. 28, Ln. 36, Xinhu First Rd., Neihu, Taipei 114, Taiwan
| | - Chun-I Wang
- Institute of Chemistry, Academia Sinica, 128 Section 2 Academia Road, Nankang, Taipei 115, Taiwan
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, Illinois 61801, United States
| | - Chou-Hsun Yang
- Institute of Chemistry, Academia Sinica, 128 Section 2 Academia Road, Nankang, Taipei 115, Taiwan
| | - Muhammad Khari Secario
- Institute of Chemistry, Academia Sinica, 128 Section 2 Academia Road, Nankang, Taipei 115, Taiwan
- Taiwan International Graduate Program on Sustainable Chemical Science & Technology, Academia Sinica Institute of Chemistry, 128 Academia Road Sec.2, Nankang, Taipei 115, Taiwan
- Department of Applied Chemistry, National Yang Ming Chiao Tung University, 1001 University Road, Hsinchu 300, Taiwan
| | - Chao-Ping Hsu
- Institute of Chemistry, Academia Sinica, 128 Section 2 Academia Road, Nankang, Taipei 115, Taiwan
- Division of Physics, National Center for Theoretical Sciences, 1, Section 4, Roosevelt Road, Taipei 106, Taiwan
| |
Collapse
|
17
|
Venturella C, Hillenbrand C, Li J, Zhu T. Machine Learning Many-Body Green's Functions for Molecular Excitation Spectra. J Chem Theory Comput 2024; 20:143-154. [PMID: 38150268 DOI: 10.1021/acs.jctc.3c01146] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/28/2023]
Abstract
We present a machine learning (ML) framework for predicting Green's functions of molecular systems, from which photoemission spectra and quasiparticle energies at quantum many-body level can be obtained. Kernel ridge regression is adopted to predict self-energy matrix elements on compact imaginary frequency grids from static and dynamical mean-field electronic features, which gives direct access to real-frequency many-body Green's functions through analytic continuation and Dyson's equation. Feature and self-energy matrices are represented in a symmetry-adapted intrinsic atomic orbital plus projected atomic orbital basis to enforce rotational invariance. We demonstrate good transferability and high data efficiency of the proposed ML method across molecular sizes and chemical species by showing accurate predictions of density of states (DOS) and quasiparticle energies at the level of many-body perturbation theory (GW) or full configuration interaction. For the ML model trained on 48 out of 1995 molecules randomly sampled from the QM7 and QM9 data sets, we report the mean absolute errors of ML-predicted highest occupied and lowest unoccupied molecular orbital energies to be 0.13 and 0.10 eV, respectively, compared to GW@PBE0. We further showcase the capability of this method by applying the same ML model to predict DOS for significantly larger organic molecules with up to 44 heavy atoms.
Collapse
Affiliation(s)
- Christian Venturella
- Department of Chemistry, Yale University, New Haven, Connecticut 06520, United States
| | | | - Jiachen Li
- Department of Chemistry, Yale University, New Haven, Connecticut 06520, United States
| | - Tianyu Zhu
- Department of Chemistry, Yale University, New Haven, Connecticut 06520, United States
| |
Collapse
|
18
|
Scherbela M, Gerard L, Grohs P. Towards a transferable fermionic neural wavefunction for molecules. Nat Commun 2024; 15:120. [PMID: 38168035 PMCID: PMC10762074 DOI: 10.1038/s41467-023-44216-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2023] [Accepted: 12/05/2023] [Indexed: 01/05/2024] Open
Abstract
Deep neural networks have become a highly accurate and powerful wavefunction ansatz in combination with variational Monte Carlo methods for solving the electronic Schrödinger equation. However, despite their success and favorable scaling, these methods are still computationally too costly for wide adoption. A significant obstacle is the requirement to optimize the wavefunction from scratch for each new system, thus requiring long optimization. In this work, we propose a neural network ansatz, which effectively maps uncorrelated, computationally cheap Hartree-Fock orbitals, to correlated, high-accuracy neural network orbitals. This ansatz is inherently capable of learning a single wavefunction across multiple compounds and geometries, as we demonstrate by successfully transferring a wavefunction model pre-trained on smaller fragments to larger compounds. Furthermore, we provide ample experimental evidence to support the idea that extensive pre-training of such a generalized wavefunction model across different compounds and geometries could lead to a foundation wavefunction model. Such a model could yield high-accuracy ab-initio energies using only minimal computational effort for fine-tuning and evaluation of observables.
Collapse
Affiliation(s)
| | - Leon Gerard
- Research Network Data Science, University of Vienna, Vienna, Austria
| | - Philipp Grohs
- Faculty of Mathematics, University of Vienna, Vienna, Austria.
- Research Network Data Science, University of Vienna, Vienna, Austria.
- Johann Radon Institute for Computational and Applied Mathematics, Austrian Academy of Sciences, Linz, Austria.
| |
Collapse
|
19
|
Niu J, Miao B, Guo J, Ding Z, He Y, Chi Z, Wang F, Ma X. Leveraging Deep Neural Networks for Estimating Vickers Hardness from Nanoindentation Hardness. MATERIALS (BASEL, SWITZERLAND) 2023; 17:148. [PMID: 38204003 PMCID: PMC10780037 DOI: 10.3390/ma17010148] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/11/2023] [Revised: 12/22/2023] [Accepted: 12/26/2023] [Indexed: 01/12/2024]
Abstract
This research presents a comprehensive analysis of deep neural network models (DNNs) for the precise prediction of Vickers hardness (HV) in nitrided and carburized M50NiL steel samples, with hardness values spanning from 400 to 1000 HV. By conducting rigorous experimentation and obtaining corresponding nanoindentation data, we evaluated the performance of four distinct neural network architectures: Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory network (LSTM), and Transformer. Our findings reveal that MLP and LSTM models excel in predictive accuracy and efficiency, with MLP showing exceptional iteration efficiency and predictive precision. The study validates models for broad application in various steel types and confirms nanoindentation as an effective direct measure for HV hardness in thin films and gradient-variable regions. This work contributes a validated and versatile approach to the hardness assessment of thin-film materials and those with intricate microstructures, enhancing material characterization and potential application in advanced material engineering.
Collapse
Affiliation(s)
- Junbo Niu
- School of Material Science & Engineering, Harbin Institute of Technology, Harbin 150001, China; (B.M.); (J.G.); (Z.D.); (Y.H.); (Z.C.); (F.W.)
| | - Bin Miao
- School of Material Science & Engineering, Harbin Institute of Technology, Harbin 150001, China; (B.M.); (J.G.); (Z.D.); (Y.H.); (Z.C.); (F.W.)
| | - Jiaxu Guo
- School of Material Science & Engineering, Harbin Institute of Technology, Harbin 150001, China; (B.M.); (J.G.); (Z.D.); (Y.H.); (Z.C.); (F.W.)
| | - Zhifeng Ding
- School of Material Science & Engineering, Harbin Institute of Technology, Harbin 150001, China; (B.M.); (J.G.); (Z.D.); (Y.H.); (Z.C.); (F.W.)
| | - Yin He
- School of Material Science & Engineering, Harbin Institute of Technology, Harbin 150001, China; (B.M.); (J.G.); (Z.D.); (Y.H.); (Z.C.); (F.W.)
| | - Zhiyu Chi
- School of Material Science & Engineering, Harbin Institute of Technology, Harbin 150001, China; (B.M.); (J.G.); (Z.D.); (Y.H.); (Z.C.); (F.W.)
| | - Feilong Wang
- School of Material Science & Engineering, Harbin Institute of Technology, Harbin 150001, China; (B.M.); (J.G.); (Z.D.); (Y.H.); (Z.C.); (F.W.)
| | - Xinxin Ma
- School of Material Science & Engineering, Harbin Institute of Technology, Harbin 150001, China; (B.M.); (J.G.); (Z.D.); (Y.H.); (Z.C.); (F.W.)
- State Key Laboratory of Advanced Welding and Joining, Harbin Institute of Technology, Harbin 150001, China
| |
Collapse
|
20
|
McGibbon M, Shave S, Dong J, Gao Y, Houston DR, Xie J, Yang Y, Schwaller P, Blay V. From intuition to AI: evolution of small molecule representations in drug discovery. Brief Bioinform 2023; 25:bbad422. [PMID: 38033290 PMCID: PMC10689004 DOI: 10.1093/bib/bbad422] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2023] [Revised: 10/13/2023] [Accepted: 11/01/2023] [Indexed: 12/02/2023] Open
Abstract
Within drug discovery, the goal of AI scientists and cheminformaticians is to help identify molecular starting points that will develop into safe and efficacious drugs while reducing costs, time and failure rates. To achieve this goal, it is crucial to represent molecules in a digital format that makes them machine-readable and facilitates the accurate prediction of properties that drive decision-making. Over the years, molecular representations have evolved from intuitive and human-readable formats to bespoke numerical descriptors and fingerprints, and now to learned representations that capture patterns and salient features across vast chemical spaces. Among these, sequence-based and graph-based representations of small molecules have become highly popular. However, each approach has strengths and weaknesses across dimensions such as generality, computational cost, inversibility for generative applications and interpretability, which can be critical in informing practitioners' decisions. As the drug discovery landscape evolves, opportunities for innovation continue to emerge. These include the creation of molecular representations for high-value, low-data regimes, the distillation of broader biological and chemical knowledge into novel learned representations and the modeling of up-and-coming therapeutic modalities.
Collapse
Affiliation(s)
- Miles McGibbon
- Institute of Quantitative Biology, Biochemistry and Biotechnology, University of Edinburgh, Edinburgh, Scotland EH9 3BF, United Kingdom
| | - Steven Shave
- Institute of Quantitative Biology, Biochemistry and Biotechnology, University of Edinburgh, Edinburgh, Scotland EH9 3BF, United Kingdom
| | - Jie Dong
- Xiangya School of Pharmaceutical Sciences, Central South University, Changsha, 410013, China
| | - Yumiao Gao
- Institute of Quantitative Biology, Biochemistry and Biotechnology, University of Edinburgh, Edinburgh, Scotland EH9 3BF, United Kingdom
| | - Douglas R Houston
- Institute of Quantitative Biology, Biochemistry and Biotechnology, University of Edinburgh, Edinburgh, Scotland EH9 3BF, United Kingdom
| | - Jiancong Xie
- Key Laboratory of Machine Intelligence and Advanced Computing, Sun Yat-Sen University, Guangzhou, 510000, China
| | - Yuedong Yang
- Key Laboratory of Machine Intelligence and Advanced Computing, Sun Yat-Sen University, Guangzhou, 510000, China
| | - Philippe Schwaller
- Laboratory of Artificial Chemical Intelligence (LIAC), Institut des Sciences et Ingénierie Chimiques, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
| | - Vincent Blay
- Institute of Quantitative Biology, Biochemistry and Biotechnology, University of Edinburgh, Edinburgh, Scotland EH9 3BF, United Kingdom
| |
Collapse
|
21
|
Huguenin-Dumittan K, Loche P, Haoran N, Ceriotti M. Physics-Inspired Equivariant Descriptors of Nonbonded Interactions. J Phys Chem Lett 2023; 14:9612-9618. [PMID: 37862712 PMCID: PMC10626632 DOI: 10.1021/acs.jpclett.3c02375] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2023] [Accepted: 10/13/2023] [Indexed: 10/22/2023]
Abstract
One essential ingredient in many machine learning (ML) based methods for atomistic modeling of materials and molecules is the use of locality. While allowing better system-size scaling, this systematically neglects long-range (LR) effects such as electrostatic or dispersion interactions. We present an extension of the long distance equivariant (LODE) framework that can handle diverse LR interactions in a consistent way and seamlessly integrates with preexisting methods by building new sets of atom centered features. We provide a direct physical interpretation of these using the multipole expansion, which allows for simpler and more efficient implementations. The framework is applied to simple toy systems as proof of concept and a heterogeneous set of molecular dimers to push the method to its limits. By generalizing LODE to arbitrary asymptotic behaviors, we provide a coherent approach to treat arbitrary two- and many-body nonbonded interactions in the data-driven modeling of matter.
Collapse
Affiliation(s)
- Kevin
K. Huguenin-Dumittan
- Laboratory
of Computational Science and Modeling, IMX,
École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland
| | - Philip Loche
- Laboratory
of Computational Science and Modeling, IMX,
École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland
| | - Ni Haoran
- Laboratory
of Computational Science and Modeling, IMX,
École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland
| | - Michele Ceriotti
- Laboratory
of Computational Science and Modeling, IMX,
École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland
| |
Collapse
|
22
|
Shao X, Paetow L, Tuckerman ME, Pavanello M. Machine learning electronic structure methods based on the one-electron reduced density matrix. Nat Commun 2023; 14:6281. [PMID: 37805614 PMCID: PMC10560258 DOI: 10.1038/s41467-023-41953-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2023] [Accepted: 09/18/2023] [Indexed: 10/09/2023] Open
Abstract
The theorems of density functional theory (DFT) establish bijective maps between the local external potential of a many-body system and its electron density, wavefunction and, therefore, one-particle reduced density matrix. Building on this foundation, we show that machine learning models based on the one-electron reduced density matrix can be used to generate surrogate electronic structure methods. We generate surrogates of local and hybrid DFT, Hartree-Fock and full configuration interaction theories for systems ranging from small molecules such as water to more complex compounds like benzene and propanol. The surrogate models use the one-electron reduced density matrix as the central quantity to be learned. From the predicted density matrices, we show that either standard quantum chemistry or a second machine-learning model can be used to compute molecular observables, energies, and atomic forces. The surrogate models can generate essentially anything that a standard electronic structure method can, ranging from band gaps and Kohn-Sham orbitals to energy-conserving ab-initio molecular dynamics simulations and infrared spectra, which account for anharmonicity and thermal effects, without the need to employ computationally expensive algorithms such as self-consistent field theory. The algorithms are packaged in an efficient and easy to use Python code, QMLearn, accessible on popular platforms.
Collapse
Affiliation(s)
- Xuecheng Shao
- Department of Chemistry, Rutgers University, Newark, NJ, 07102, USA.
| | - Lukas Paetow
- Department of Chemistry, Rutgers University, Newark, NJ, 07102, USA
| | - Mark E Tuckerman
- Department of Chemistry, New York University, New York, NY, 10003, USA.
- Courant Institute of Mathematical Science, New York University, New York, NY, 10003, USA.
- Simons Center for Computational Physical Chemistry, New York University, New York, NY, 10003, USA.
- NYU-ECNU Center for Computational Chemistry at NYU Shanghai, 200062, Shanghai, China.
| | - Michele Pavanello
- Department of Chemistry, Rutgers University, Newark, NJ, 07102, USA.
- Department of Physics, Rutgers University, Newark, NJ, 07102, USA.
| |
Collapse
|
23
|
Lederer J, Gastegger M, Schütt KT, Kampffmeyer M, Müller KR, Unke OT. Automatic identification of chemical moieties. Phys Chem Chem Phys 2023; 25:26370-26379. [PMID: 37750554 PMCID: PMC10548786 DOI: 10.1039/d3cp03845a] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2023] [Accepted: 08/18/2023] [Indexed: 09/27/2023]
Abstract
In recent years, the prediction of quantum mechanical observables with machine learning methods has become increasingly popular. Message-passing neural networks (MPNNs) solve this task by constructing atomic representations, from which the properties of interest are predicted. Here, we introduce a method to automatically identify chemical moieties (molecular building blocks) from such representations, enabling a variety of applications beyond property prediction, which otherwise rely on expert knowledge. The required representation can either be provided by a pretrained MPNN, or be learned from scratch using only structural information. Beyond the data-driven design of molecular fingerprints, the versatility of our approach is demonstrated by enabling the selection of representative entries in chemical databases, the automatic construction of coarse-grained force fields, as well as the identification of reaction coordinates.
Collapse
Affiliation(s)
- Jonas Lederer
- Berlin Institute of Technology (TU Berlin), 10587 Berlin, Germany.
- BIFOLD - Berlin Institute for the Foundations of Learning and Data, Germany
| | - Michael Gastegger
- Berlin Institute of Technology (TU Berlin), 10587 Berlin, Germany.
- BIFOLD - Berlin Institute for the Foundations of Learning and Data, Germany
| | - Kristof T Schütt
- Berlin Institute of Technology (TU Berlin), 10587 Berlin, Germany.
- BIFOLD - Berlin Institute for the Foundations of Learning and Data, Germany
| | - Michael Kampffmeyer
- Department of Physics and Technology, UiT The Arctic University of Norway, 9019 Tromsø, Norway
| | - Klaus-Robert Müller
- Berlin Institute of Technology (TU Berlin), 10587 Berlin, Germany.
- BIFOLD - Berlin Institute for the Foundations of Learning and Data, Germany
- Google Deepmind, Germany
- Department of Artificial Intelligence, Korea University, Seoul 136-713, Korea
- Max Planck Institut für Informatik, 66123 Saarbrücken, Germany
| | - Oliver T Unke
- Berlin Institute of Technology (TU Berlin), 10587 Berlin, Germany.
- BIFOLD - Berlin Institute for the Foundations of Learning and Data, Germany
- Google Deepmind, Germany
| |
Collapse
|
24
|
Hermann J, Spencer J, Choo K, Mezzacapo A, Foulkes WMC, Pfau D, Carleo G, Noé F. Ab initio quantum chemistry with neural-network wavefunctions. Nat Rev Chem 2023; 7:692-709. [PMID: 37558761 DOI: 10.1038/s41570-023-00516-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/16/2023] [Indexed: 08/11/2023]
Abstract
Deep learning methods outperform human capabilities in pattern recognition and data processing problems and now have an increasingly important role in scientific discovery. A key application of machine learning in molecular science is to learn potential energy surfaces or force fields from ab initio solutions of the electronic Schrödinger equation using data sets obtained with density functional theory, coupled cluster or other quantum chemistry (QC) methods. In this Review, we discuss a complementary approach using machine learning to aid the direct solution of QC problems from first principles. Specifically, we focus on quantum Monte Carlo methods that use neural-network ansatzes to solve the electronic Schrödinger equation, in first and second quantization, computing ground and excited states and generalizing over multiple nuclear configurations. Although still at their infancy, these methods can already generate virtually exact solutions of the electronic Schrödinger equation for small systems and rival advanced conventional QC methods for systems with up to a few dozen electrons.
Collapse
Affiliation(s)
- Jan Hermann
- Microsoft Research AI4Science, Berlin, Germany
- FU Berlin, Department of Mathematics and Computer Science, Berlin, Germany
| | | | - Kenny Choo
- Department of Physics, University of Zurich, Zurich, Switzerland
- IBM Quantum, IBM Research Zurich, Ruschlikon, Switzerland
| | | | - W M C Foulkes
- Imperial College London, Department of Physics, London, UK
| | - David Pfau
- DeepMind, London, UK.
- Imperial College London, Department of Physics, London, UK.
| | | | - Frank Noé
- Microsoft Research AI4Science, Berlin, Germany.
- FU Berlin, Department of Mathematics and Computer Science, Berlin, Germany.
- FU Berlin, Department of Physics, Berlin, Germany.
- Department of Chemistry,Rice University, Houston, TX, USA.
| |
Collapse
|
25
|
Srinivasan V, Muller KR, Samek W, Nakajima S. Langevin Cooling for Unsupervised Domain Translation. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023; 34:7675-7688. [PMID: 35133968 DOI: 10.1109/tnnls.2022.3145812] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Domain translation is the task of finding correspondence between two domains. Several deep neural network (DNN) models, e.g., CycleGAN and cross-lingual language models, have shown remarkable successes on this task under the unsupervised setting-the mappings between the domains are learned from two independent sets of training data in both domains (without paired samples). However, those methods typically do not perform well on a significant proportion of test samples. In this article, we hypothesize that many of such unsuccessful samples lie at the fringe-relatively low-density areas-of data distribution, where the DNN was not trained very well, and propose to perform the Langevin dynamics to bring such fringe samples toward high-density areas. We demonstrate qualitatively and quantitatively that our strategy, called Langevin cooling (L-Cool), enhances state-of-the-art methods in image translation and language translation tasks.
Collapse
|
26
|
Hu F, He F, Yaron DJ. Treating Semiempirical Hamiltonians as Flexible Machine Learning Models Yields Accurate and Interpretable Results. J Chem Theory Comput 2023; 19:6185-6196. [PMID: 37705220 PMCID: PMC10536991 DOI: 10.1021/acs.jctc.3c00491] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/11/2023] [Indexed: 09/15/2023]
Abstract
Quantum chemistry provides chemists with invaluable information, but the high computational cost limits the size and type of systems that can be studied. Machine learning (ML) has emerged as a means to dramatically lower the cost while maintaining high accuracy. However, ML models often sacrifice interpretability by using components such as the artificial neural networks of deep learning that function as black boxes. These components impart the flexibility needed to learn from large volumes of data but make it difficult to gain insight into the physical or chemical basis for the predictions. Here, we demonstrate that semiempirical quantum chemical (SEQC) models can learn from large volumes of data without sacrificing interpretability. The SEQC model is that of density-functional-based tight binding (DFTB) with fixed atomic orbital energies and interactions that are one-dimensional functions of the interatomic distance. This model is trained to ab initio data in a manner that is analogous to that used to train deep learning models. Using benchmarks that reflect the accuracy of the training data, we show that the resulting model maintains a physically reasonable functional form while achieving an accuracy, relative to coupled cluster energies with a complete basis set extrapolation (CCSD(T)*/CBS), that is comparable to that of density functional theory (DFT). This suggests that trained SEQC models can achieve a low computational cost and high accuracy without sacrificing interpretability. Use of a physically motivated model form also substantially reduces the amount of ab initio data needed to train the model compared to that required for deep learning models.
Collapse
Affiliation(s)
- Frank Hu
- Department of Chemistry, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States
| | - Francis He
- Department of Chemistry, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States
| | - David J. Yaron
- Department of Chemistry, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, United States
| |
Collapse
|
27
|
Fedik N, Nebgen B, Lubbers N, Barros K, Kulichenko M, Li YW, Zubatyuk R, Messerly R, Isayev O, Tretiak S. Synergy of semiempirical models and machine learning in computational chemistry. J Chem Phys 2023; 159:110901. [PMID: 37712780 DOI: 10.1063/5.0151833] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2023] [Accepted: 07/11/2023] [Indexed: 09/16/2023] Open
Abstract
Catalyzed by enormous success in the industrial sector, many research programs have been exploring data-driven, machine learning approaches. Performance can be poor when the model is extrapolated to new regions of chemical space, e.g., new bonding types, new many-body interactions. Another important limitation is the spatial locality assumption in model architecture, and this limitation cannot be overcome with larger or more diverse datasets. The outlined challenges are primarily associated with the lack of electronic structure information in surrogate models such as interatomic potentials. Given the fast development of machine learning and computational chemistry methods, we expect some limitations of surrogate models to be addressed in the near future; nevertheless spatial locality assumption will likely remain a limiting factor for their transferability. Here, we suggest focusing on an equally important effort-design of physics-informed models that leverage the domain knowledge and employ machine learning only as a corrective tool. In the context of material science, we will focus on semi-empirical quantum mechanics, using machine learning to predict corrections to the reduced-order Hamiltonian model parameters. The resulting models are broadly applicable, retain the speed of semiempirical chemistry, and frequently achieve accuracy on par with much more expensive ab initio calculations. These early results indicate that future work, in which machine learning and quantum chemistry methods are developed jointly, may provide the best of all worlds for chemistry applications that demand both high accuracy and high numerical efficiency.
Collapse
Affiliation(s)
- Nikita Fedik
- Theoretical Division, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
- Center for Nonlinear Studies, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
| | - Benjamin Nebgen
- Theoretical Division, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
| | - Nicholas Lubbers
- Computer, Computational, and Statistical Sciences Division, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
| | - Kipton Barros
- Theoretical Division, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
- Center for Nonlinear Studies, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
| | - Maksim Kulichenko
- Theoretical Division, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
| | - Ying Wai Li
- Computer, Computational, and Statistical Sciences Division, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
| | - Roman Zubatyuk
- Department of Chemistry, Mellon College of Science, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA
| | - Richard Messerly
- Theoretical Division, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
| | - Olexandr Isayev
- Department of Chemistry, Mellon College of Science, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA
| | - Sergei Tretiak
- Theoretical Division, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
- Center for Nonlinear Studies, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
- Center for Integrated Nanotechnologies Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
| |
Collapse
|
28
|
M V, Singh S, Bononi F, Andreussi O, Karmodak N. Thermodynamic and kinetic modeling of electrocatalytic reactions using a first-principles approach. J Chem Phys 2023; 159:111001. [PMID: 37728202 DOI: 10.1063/5.0165835] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Accepted: 08/28/2023] [Indexed: 09/21/2023] Open
Abstract
The computational modeling of electrochemical interfaces and their applications in electrocatalysis has attracted great attention in recent years. While tremendous progress has been made in this area, however, the accurate atomistic descriptions at the electrode/electrolyte interfaces remain a great challenge. The Computational Hydrogen Electrode (CHE) method and continuum modeling of the solvent and electrolyte interactions form the basis for most of these methodological developments. Several posterior corrections have been added to the CHE method to improve its accuracy and widen its applications. The most recently developed grand canonical potential approaches with the embedded diffuse layer models have shown considerable improvement in defining interfacial interactions at electrode/electrolyte interfaces over the state-of-the-art computational models for electrocatalysis. In this Review, we present an overview of these different computational models developed over the years to quantitatively probe the thermodynamics and kinetics of electrochemical reactions in the presence of an electrified catalyst surface under various electrochemical environments. We begin our discussion by giving a brief picture of the different continuum solvation approaches, implemented within the ab initio method to effectively model the solvent and electrolyte interactions. Next, we present the thermodynamic and kinetic modeling approaches to determine the activity and stability of the electrocatalysts. A few applications to these approaches are also discussed. We conclude by giving an outlook on the different machine learning models that have been integrated with the thermodynamic approaches to improve their efficiency and widen their applicability.
Collapse
Affiliation(s)
- Vasanthapandiyan M
- Department of Chemistry, Shiv Nadar Institution of Eminence, Dadri, Gautam Buddha Nagar, Uttar Pradesh 201314, India
| | - Shagun Singh
- Department of Chemistry, Shiv Nadar Institution of Eminence, Dadri, Gautam Buddha Nagar, Uttar Pradesh 201314, India
| | - Fernanda Bononi
- Department of Physics, University of North Texas, Denton, Texas 76203, USA
| | - Oliviero Andreussi
- Department of Chemistry and Biochemistry, Boise State University, Boise, Idaho 83725, USA
| | - Naiwrit Karmodak
- Department of Chemistry, Shiv Nadar Institution of Eminence, Dadri, Gautam Buddha Nagar, Uttar Pradesh 201314, India
| |
Collapse
|
29
|
von der Heyde J, Malone W, Zaman N, Kara A. Combining Deep Learning Neural Networks with Genetic Algorithms to Map Nanocluster Configuration Spaces with Quantum Accuracy at Low Computational Cost. J Chem Inf Model 2023; 63:5045-5055. [PMID: 37579032 DOI: 10.1021/acs.jcim.3c00609] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/16/2023]
Abstract
The configuration spaces for bimetallic AuPd nanoclusters of various sizes are explored efficiently and analyzed accurately by combining genetic algorithms with neural networks trained on density functional theory. The methodology demonstrated herein provides an optimizable solution to the problem of searching vast configuration spaces with quantum accuracy in a way that is computationally practical. We implement a machine learning algorithm which learns the density functional theory potential with increasing performance while simultaneously generating and relaxing structures within the system's global configuration space unbiasedly. As a result, the algorithm naturally converges onto the system's energy minima while mapping the configuration space as a function of energy. The algorithm's simple design applies not only to nanocluster configurations, as demonstrated, but to bulk, substrate, and adsorption sites as well, and it is designed to scale. To demonstrate its computational efficiency, we work with AuPd nanoclusters of sizes 15, 20, and 25 atoms. Results focus primarily on evaluating the algorithm's performance; however, several physical insights into possible configurations for these nanoclusters naturally emerge as well, such as geometric Au surface segregation and stoichiometric Au minimization as a function of stability.
Collapse
Affiliation(s)
- Johnathan von der Heyde
- Department of Physics, University of Central Florida, 4000 Central Florida Blvd., Orlando, Florida 32816, United States
| | - Walter Malone
- Department of Physics, Tuskegee University, 1200 W. Montgomery Rd., Tuskegee, Alabama 36088, United States
| | - Nusaiba Zaman
- Department of Physics, University of Central Florida, 4000 Central Florida Blvd., Orlando, Florida 32816, United States
| | - Abdelkader Kara
- Department of Physics, University of Central Florida, 4000 Central Florida Blvd., Orlando, Florida 32816, United States
| |
Collapse
|
30
|
Liang C, Rouzhahong Y, Ye C, Li C, Wang B, Li H. Material symmetry recognition and property prediction accomplished by crystal capsule representation. Nat Commun 2023; 14:5198. [PMID: 37626032 PMCID: PMC10457372 DOI: 10.1038/s41467-023-40756-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2023] [Accepted: 08/07/2023] [Indexed: 08/27/2023] Open
Abstract
Learning the global crystal symmetry and interpreting the equivariant information is crucial for accurately predicting material properties, yet remains to be fully accomplished by existing algorithms based on convolution networks. To overcome this challenge, here we develop a machine learning (ML) model, named symmetry-enhanced equivariance network (SEN), to build material representation with joint structure-chemical patterns, to encode important clusters embedded in the crystal structure, and to learn pattern equivariance in different scales via capsule transformers. Quantitative analyses of the intermediate matrices demonstrate that the intrinsic crystal symmetries and interactions between clusters have been exactly perceived by the SEN model and critically affect the prediction performances by reducing effective feature space. The mean absolute errors (MAEs) of 0.181 eV and 0.0161 eV/atom are obtained for predicting bandgap and formation energy in the MatBench dataset. The general and interpretable SEN model reveals the potential to design ML models by implicitly encoding feature relationship based on physical mechanisms.
Collapse
Affiliation(s)
- Chao Liang
- School of Physics, Sun Yat-Sen University, Guangzhou, China
| | | | - Caiyuan Ye
- School of Physics, Sun Yat-Sen University, Guangzhou, China
| | - Chong Li
- School of Physics, Sun Yat-Sen University, Guangzhou, China
| | - Biao Wang
- School of Physics, Sun Yat-Sen University, Guangzhou, China.
| | - Huashan Li
- School of Physics, Sun Yat-Sen University, Guangzhou, China.
- Guangdong Provincial Key Laboratory of Magnetoelectric Physics and Devices, School of Physics, Sun Yat-sen University, Guangzhou, China.
- Center for Neutron Science and Technology, School of Physics, Sun Yat-sen University, Guangzhou, China.
| |
Collapse
|
31
|
Ng WP, Liang Q, Yang J. Low-Data Deep Quantum Chemical Learning for Accurate MP2 and Coupled-Cluster Correlations. J Chem Theory Comput 2023; 19:5439-5449. [PMID: 37506400 DOI: 10.1021/acs.jctc.3c00518] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/30/2023]
Abstract
Accurate ab initio prediction of electronic energies is very expensive for macromolecules by explicitly solving post-Hartree-Fock equations. We here exploit the physically justified local correlation feature in a compact basis of small molecules and construct an expressive low-data deep neural network (dNN) model to obtain machine-learned electron correlation energies on par with MP2 and CCSD levels of theory for more complex molecules and different datasets that are not represented in the training set. We show that our dNN-powered model is data efficient and makes highly transferable predictions across alkanes of various lengths, organic molecules with non-covalent and biomolecular interactions, as well as water clusters of different sizes and morphologies. In particular, by training 800 (H2O)8 clusters with the local correlation descriptors, accurate MP2/cc-pVTZ correlation energies up to (H2O)128 can be predicted with a small random error within chemical accuracy from exact values, while a majority of prediction deviations are attributed to an intrinsically systematic error. Our results reveal that an extremely compact local correlation feature set, which is poor for any direct post-Hartree-Fock calculations, has however a prominent advantage in reserving important electron correlation patterns for making accurate transferable predictions across distinct molecular compositions, bond types, and geometries.
Collapse
Affiliation(s)
- Wai-Pan Ng
- Department of Chemistry, The University of Hong Kong, Hong Kong 999077, P. R. China
- Hong Kong Quantum AI Lab Limited, Hong Kong 999077, P. R. China
| | - Qiujiang Liang
- Department of Chemistry, The University of Hong Kong, Hong Kong 999077, P. R. China
| | - Jun Yang
- Department of Chemistry, The University of Hong Kong, Hong Kong 999077, P. R. China
- Hong Kong Quantum AI Lab Limited, Hong Kong 999077, P. R. China
| |
Collapse
|
32
|
Kirschbaum T, von Seggern B, Dzubiella J, Bande A, Noé F. Machine Learning Frontier Orbital Energies of Nanodiamonds. J Chem Theory Comput 2023; 19:4461-4473. [PMID: 37053438 DOI: 10.1021/acs.jctc.2c01275] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/15/2023]
Abstract
Nanodiamonds have a wide range of applications including catalysis, sensing, tribology, and biomedicine. To leverage nanodiamond design via machine learning, we introduce the new data set ND5k, consisting of 5089 diamondoid and nanodiamond structures and their frontier orbital energies. ND5k structures are optimized via tight-binding density functional theory (DFTB) and their frontier orbital energies are computed using density functional theory (DFT) with the PBE0 hybrid functional. From this data set we derive a qualitative design suggestion for nanodiamonds in photocatalysis. We also compare recent machine learning models for predicting frontier orbital energies for similar structures as they have been trained on (interpolation on ND5k), and we test their abilities to extrapolate predictions to larger structures. For both the interpolation and extrapolation task, we find the best performance using the equivariant message passing neural network PaiNN. The second best results are achieved with a message passing neural network using a tailored set of atomic descriptors proposed here.
Collapse
Affiliation(s)
- Thorren Kirschbaum
- Helmholtz-Zentrum Berlin für Materialien und Energie GmbH, Hahn-Meitner-Platz 1, 14109 Berlin, Germany
- Department of Mathematics and Computer Science, Freie Universität Berlin, Arnimallee 12, 14195 Berlin, Germany
| | - Börries von Seggern
- Helmholtz-Zentrum Berlin für Materialien und Energie GmbH, Hahn-Meitner-Platz 1, 14109 Berlin, Germany
- Department of Biology, Chemistry and Pharmacy, Freie Universität Berlin, Arnimallee 22, 14195 Berlin, Germany
| | - Joachim Dzubiella
- Institute of Physics, Albert-Ludwigs-Universität Freiburg, Hermann-Herder-Straße 3, 79104 Freiburg im Breisgau, Germany
| | - Annika Bande
- Helmholtz-Zentrum Berlin für Materialien und Energie GmbH, Hahn-Meitner-Platz 1, 14109 Berlin, Germany
| | - Frank Noé
- Department of Mathematics and Computer Science, Freie Universität Berlin, Arnimallee 12, 14195 Berlin, Germany
- Microsoft Research AI4Science, Karl-Liebknecht Str. 32, 10178 Berlin, Germany
- Department of Physics, Freie Universität Berlin, Arnimallee 12, 14195 Berlin, Germany
- Department of Chemistry, Rice University, 6100 Main Street, Houston, Texas 77005, United States
| |
Collapse
|
33
|
Huang B, von Rudorff GF, von Lilienfeld OA. The central role of density functional theory in the AI age. Science 2023; 381:170-175. [PMID: 37440654 DOI: 10.1126/science.abn3445] [Citation(s) in RCA: 13] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2023] [Accepted: 05/30/2023] [Indexed: 07/15/2023]
Abstract
Density functional theory (DFT) plays a pivotal role in chemical and materials science because of its relatively high predictive power, applicability, versatility, and computational efficiency. We review recent progress in machine learning (ML) model developments, which have relied heavily on DFT for synthetic data generation and for the design of model architectures. The general relevance of these developments is placed in a broader context for chemical and materials sciences. DFT-based ML models have reached high efficiency, accuracy, scalability, and transferability and pave the way to the routine use of successful experimental planning software within self-driving laboratories.
Collapse
Affiliation(s)
- Bing Huang
- University of Vienna, Faculty of Physics, AT1090 Wien, Austria
| | - Guido Falk von Rudorff
- University Kassel, Department of Chemistry, 34132 Kassel, Germany
- Center for Interdisciplinary Nanostructure Science and Technology (CINSaT), 34132 Kassel, Germany
| | - O Anatole von Lilienfeld
- Vector Institute for Artificial Intelligence, Toronto, Ontario M5S 1M1, Canada
- Department of Chemistry, University of Toronto, St. George Campus, Toronto, Ontario M5S 3H6, Canada
- Department of Materials Science and Engineering, University of Toronto, St. George Campus, Toronto, Ontario M5S 3E4, Canada
- Department of Physics, University of Toronto, St. George Campus, Toronto, Ontario M5S 1A7, Canada
- Machine Learning Group, Technische Universität Berlin and Berlin Institute for the Foundations of Learning and Data, 10587 Berlin, Germany
| |
Collapse
|
34
|
Gong X, Li H, Zou N, Xu R, Duan W, Xu Y. General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian. Nat Commun 2023; 14:2848. [PMID: 37208320 DOI: 10.1038/s41467-023-38468-8] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/01/2022] [Accepted: 04/27/2023] [Indexed: 05/21/2023] Open
Abstract
The combination of deep learning and ab initio calculation has shown great promise in revolutionizing future scientific research, but how to design neural network models incorporating a priori knowledge and symmetry requirements is a key challenging subject. Here we propose an E(3)-equivariant deep-learning framework to represent density functional theory (DFT) Hamiltonian as a function of material structure, which can naturally preserve the Euclidean symmetry even in the presence of spin-orbit coupling. Our DeepH-E3 method enables efficient electronic structure calculation at ab initio accuracy by learning from DFT data of small-sized structures, making the routine study of large-scale supercells (>104 atoms) feasible. The method can reach sub-meV prediction accuracy at high training efficiency, showing state-of-the-art performance in our experiments. The work is not only of general significance to deep-learning method development but also creates opportunities for materials research, such as building a Moiré-twisted material database.
Collapse
Affiliation(s)
- Xiaoxun Gong
- State Key Laboratory of Low Dimensional Quantum Physics and Department of Physics, Tsinghua University, 100084, Beijing, China
- School of Physics, Peking University, 100871, Beijing, China
| | - He Li
- State Key Laboratory of Low Dimensional Quantum Physics and Department of Physics, Tsinghua University, 100084, Beijing, China
- Institute for Advanced Study, Tsinghua University, 100084, Beijing, China
- Tencent Quantum Laboratory, Tencent, 518057, Shenzhen, Guangdong, China
| | - Nianlong Zou
- State Key Laboratory of Low Dimensional Quantum Physics and Department of Physics, Tsinghua University, 100084, Beijing, China
| | - Runzhang Xu
- State Key Laboratory of Low Dimensional Quantum Physics and Department of Physics, Tsinghua University, 100084, Beijing, China
| | - Wenhui Duan
- State Key Laboratory of Low Dimensional Quantum Physics and Department of Physics, Tsinghua University, 100084, Beijing, China.
- Institute for Advanced Study, Tsinghua University, 100084, Beijing, China.
- Tencent Quantum Laboratory, Tencent, 518057, Shenzhen, Guangdong, China.
- Frontier Science Center for Quantum Information, Beijing, China.
| | - Yong Xu
- State Key Laboratory of Low Dimensional Quantum Physics and Department of Physics, Tsinghua University, 100084, Beijing, China.
- Tencent Quantum Laboratory, Tencent, 518057, Shenzhen, Guangdong, China.
- Frontier Science Center for Quantum Information, Beijing, China.
- RIKEN Center for Emergent Matter Science (CEMS), Wako, Saitama, 351-0198, Japan.
| |
Collapse
|
35
|
Chen K, Kunkel C, Cheng B, Reuter K, Margraf JT. Physics-inspired machine learning of localized intensive properties. Chem Sci 2023; 14:4913-4922. [PMID: 37181767 PMCID: PMC10171074 DOI: 10.1039/d3sc00841j] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2023] [Accepted: 04/10/2023] [Indexed: 05/16/2023] Open
Abstract
Machine learning (ML) has been widely applied to chemical property prediction, most prominently for the energies and forces in molecules and materials. The strong interest in predicting energies in particular has led to a 'local energy'-based paradigm for modern atomistic ML models, which ensures size-extensivity and a linear scaling of computational cost with system size. However, many electronic properties (such as excitation energies or ionization energies) do not necessarily scale linearly with system size and may even be spatially localized. Using size-extensive models in these cases can lead to large errors. In this work, we explore different strategies for learning intensive and localized properties, using HOMO energies in organic molecules as a representative test case. In particular, we analyze the pooling functions that atomistic neural networks use to predict molecular properties, and suggest an orbital weighted average (OWA) approach that enables the accurate prediction of orbital energies and locations.
Collapse
Affiliation(s)
- Ke Chen
- Fritz-Haber-Institut der Max-Planck-Gesellschaft Faradayweg 4-6 D-14195 Berlin Germany
- Chair for Theoretical Chemistry and Catalysis Research Center, Technische Universität München Lichtenbergstraße 4 D-85747 Garching Germany
- Institute of Science and Technology Am Campus 1 3400 Klosterneuburg Austria
| | - Christian Kunkel
- Fritz-Haber-Institut der Max-Planck-Gesellschaft Faradayweg 4-6 D-14195 Berlin Germany
| | - Bingqing Cheng
- Institute of Science and Technology Am Campus 1 3400 Klosterneuburg Austria
| | - Karsten Reuter
- Fritz-Haber-Institut der Max-Planck-Gesellschaft Faradayweg 4-6 D-14195 Berlin Germany
- Chair for Theoretical Chemistry and Catalysis Research Center, Technische Universität München Lichtenbergstraße 4 D-85747 Garching Germany
| | - Johannes T Margraf
- Fritz-Haber-Institut der Max-Planck-Gesellschaft Faradayweg 4-6 D-14195 Berlin Germany
| |
Collapse
|
36
|
Zhang B, Lin J, Du L, Zhang L. Harnessing Data Augmentation and Normalization Preprocessing to Improve the Performance of Chemical Reaction Predictions of Data-Driven Model. Polymers (Basel) 2023; 15:polym15092224. [PMID: 37177370 PMCID: PMC10180765 DOI: 10.3390/polym15092224] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2023] [Revised: 05/03/2023] [Accepted: 05/03/2023] [Indexed: 05/15/2023] Open
Abstract
As a template-free, data-driven methodology, the molecular transformer model provides an alternative by which to predict the outcome of chemical reactions and design the route of the retrosynthetic plane in the field of organic synthesis and polymer chemistry. However, in consideration of the small datasets of chemical reactions, the data-driven model suffers from the difficulty of low accuracy in the prediction tasks of chemical reactions. In this contribution, we integrate the molecular transformer model with the strategies of data augmentation and normalization preprocessing to accomplish the three tasks of chemical reactions, including the forward predictions of chemical reactions, and single-step retrosynthetic predictions with and without the reaction classes. It is clearly demonstrated that the prediction accuracy of the molecular transformer model can be significantly raised by the use of proposed strategies for the three tasks of chemical reactions. Notably, after the introduction of the 40-level data augmentation and normalization preprocessing, the top-1 accuracy of the forward prediction increases markedly from 71.6% to 84.2% and the top-1 accuracy of the single-step retrosynthetic prediction with additional reaction class increases from 53.2% to 63.4%. Furthermore, it is found that the superior performance of the data-driven model originates from the correction of the grammatical errors of the SMILES strings, especially for the case of the reaction classes with small datasets.
Collapse
Affiliation(s)
- Boyu Zhang
- Shanghai Key Laboratory of Advanced Polymeric Materials, School of Materials Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Jiaping Lin
- Shanghai Key Laboratory of Advanced Polymeric Materials, School of Materials Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Lei Du
- Shanghai Key Laboratory of Advanced Polymeric Materials, School of Materials Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Liangshun Zhang
- Shanghai Key Laboratory of Advanced Polymeric Materials, School of Materials Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
| |
Collapse
|
37
|
Schütt KT, Hessmann SSP, Gebauer NWA, Lederer J, Gastegger M. SchNetPack 2.0: A neural network toolbox for atomistic machine learning. J Chem Phys 2023; 158:144801. [PMID: 37061495 DOI: 10.1063/5.0138367] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/17/2023] Open
Abstract
SchNetPack is a versatile neural network toolbox that addresses both the requirements of method development and the application of atomistic machine learning. Version 2.0 comes with an improved data pipeline, modules for equivariant neural networks, and a PyTorch implementation of molecular dynamics. An optional integration with PyTorch Lightning and the Hydra configuration framework powers a flexible command-line interface. This makes SchNetPack 2.0 easily extendable with a custom code and ready for complex training tasks, such as the generation of 3D molecular structures.
Collapse
Affiliation(s)
- Kristof T Schütt
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
| | | | - Niklas W A Gebauer
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
| | - Jonas Lederer
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
| | - Michael Gastegger
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
| |
Collapse
|
38
|
Li H, Tang Z, Gong X, Zou N, Duan W, Xu Y. Deep-learning electronic-structure calculation of magnetic superstructures. NATURE COMPUTATIONAL SCIENCE 2023; 3:321-327. [PMID: 38177932 PMCID: PMC10766521 DOI: 10.1038/s43588-023-00424-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/02/2022] [Accepted: 03/01/2023] [Indexed: 01/06/2024]
Abstract
Ab initio studies of magnetic superstructures are indispensable to research on emergent quantum materials, but are currently bottlenecked by the formidable computational cost. Here, to break this bottleneck, we have developed a deep equivariant neural network framework to represent the density functional theory Hamiltonian of magnetic materials for efficient electronic-structure calculation. A neural network architecture incorporating a priori knowledge of fundamental physical principles, especially the nearsightedness principle and the equivariance requirements of Euclidean and time-reversal symmetries ([Formula: see text]), is designed, which is critical to capture the subtle magnetic effects. Systematic experiments on spin-spiral, nanotube and moiré magnets were performed, making the challenging study of magnetic skyrmions feasible.
Collapse
Affiliation(s)
- He Li
- State Key Laboratory of Low Dimensional Quantum Physics and Department of Physics, Tsinghua University, Beijing, China
- Tencent Quantum Laboratory, Tencent, Shenzhen, China
- Institute for Advanced Study, Tsinghua University, Beijing, China
| | - Zechen Tang
- State Key Laboratory of Low Dimensional Quantum Physics and Department of Physics, Tsinghua University, Beijing, China
| | - Xiaoxun Gong
- State Key Laboratory of Low Dimensional Quantum Physics and Department of Physics, Tsinghua University, Beijing, China
- School of Physics, Peking University, Beijing, China
| | - Nianlong Zou
- State Key Laboratory of Low Dimensional Quantum Physics and Department of Physics, Tsinghua University, Beijing, China
| | - Wenhui Duan
- State Key Laboratory of Low Dimensional Quantum Physics and Department of Physics, Tsinghua University, Beijing, China.
- Tencent Quantum Laboratory, Tencent, Shenzhen, China.
- Institute for Advanced Study, Tsinghua University, Beijing, China.
- Frontier Science Center for Quantum Information, Beijing, China.
| | - Yong Xu
- State Key Laboratory of Low Dimensional Quantum Physics and Department of Physics, Tsinghua University, Beijing, China.
- Tencent Quantum Laboratory, Tencent, Shenzhen, China.
- Frontier Science Center for Quantum Information, Beijing, China.
- RIKEN Center for Emergent Matter Science (CEMS), Wako, Japan.
| |
Collapse
|
39
|
de Armas-Morejón CM, Montero-Cabrera LA, Rubio A, Jornet-Somoza J. Electronic Descriptors for Supervised Spectroscopic Predictions. J Chem Theory Comput 2023; 19:1818-1826. [PMID: 36877528 DOI: 10.1021/acs.jctc.2c01039] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/07/2023]
Abstract
Spectroscopic properties of molecules hold great importance for the description of the molecular response under the effect of UV/vis electromagnetic radiation. Computationally expensive ab initio (e.g., MultiConfigurational SCF, Coupled Cluster) or TDDFT methods are commonly used by the quantum chemistry community to compute these properties. In this work, we propose a (supervised) Machine Learning approach to model the absorption spectra of organic molecules. Several supervised ML methods have been tested such as Kernel Ridge Regression (KRR), Multiperceptron Neural Networs (MLP), and Convolutional Neural Networks. [Ramakrishnan et al. J. Chem. Phys. 2015, 143, 084111. Ghosh et al. Adv. Sci. 2019, 6, 1801367.] The use of only geometrical-atomic number descriptors (e.g., Coulomb Matrix) proved to be insufficient for an accurate training. [Ramakrishnan et al. J. Chem. Phys. 2015, 143, 084111.] Inspired by the TDDFT theory, we propose to use a set of electronic descriptors obtained from low-cost DFT methods: orbital energy differences (Δϵia = ϵa - ϵi), transition dipole moment between occupied and unoccupied Kohn-Sham orbitals (⟨ϕi|r|ϕa⟩), and when relevant, charge-transfer character of monoexcitations (Ria). We demonstrate that with these electronic descriptors and the use of Neural Networks we can predict not only a density of excited states but also get a very good estimation of the absorption spectrum and charge-transfer character of the electronic excited states, reaching results close to chemical accuracy (∼2 kcal/mol or ∼0.1 eV).
Collapse
Affiliation(s)
- Carlos Manuel de Armas-Morejón
- Nano-Bio Spectroscopy Group, Departamento de Polímeros y Materiales Avanzados: Fisica, Química y Tecnología, Universidad del País Vasco UPV/EHU, 20018 San Sebastián, Spain.,Laboratorio de Química Computacional y Teórica, Facultad de Química, Universidad de La Habana, 10400 La Habana, Cuba
| | - Luis A Montero-Cabrera
- Laboratorio de Química Computacional y Teórica, Facultad de Química, Universidad de La Habana, 10400 La Habana, Cuba.,Donostia International Physics Center, Manuel Lardizabal Ibilbidea, 4, 20018 Donostia, Spain
| | - Angel Rubio
- Nano-Bio Spectroscopy Group, Departamento de Polímeros y Materiales Avanzados: Fisica, Química y Tecnología, Universidad del País Vasco UPV/EHU, 20018 San Sebastián, Spain.,Theory Department, Max Planck Institute for the Structure and Dynamics of Matter and Center for Free-Electron Laser Science, Luruper Chaussee 149, 22761 Hamburg, Germany
| | - Joaquim Jornet-Somoza
- Nano-Bio Spectroscopy Group, Departamento de Polímeros y Materiales Avanzados: Fisica, Química y Tecnología, Universidad del País Vasco UPV/EHU, 20018 San Sebastián, Spain.,Theory Department, Max Planck Institute for the Structure and Dynamics of Matter and Center for Free-Electron Laser Science, Luruper Chaussee 149, 22761 Hamburg, Germany
| |
Collapse
|
40
|
General implementation of quantum physics-informed neural network. ARRAY 2023. [DOI: 10.1016/j.array.2023.100287] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/17/2023] Open
|
41
|
Feng C, Xi J, Zhang Y, Jiang B, Zhou Y. Accurate and Interpretable Dipole Interaction Model-Based Machine Learning for Molecular Polarizability. J Chem Theory Comput 2023; 19:1207-1217. [PMID: 36753749 DOI: 10.1021/acs.jctc.2c01094] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/10/2023]
Abstract
Polarizabilities play significant roles in describing dispersive and inductive interactions of the atom and molecular systems. However, an accurate prediction of molecular polarizabilities from first principles is computationally prohibitive. Although physical models or statistical machine learning models have been proposed, either a lack of accurate description of local chemical environments or demanding a large number of samples for training has limited their practical applications. In this study, we combine a physically inspired dipole interaction model and an accurate neural network method for predicting the polarizability tensors of molecules. With the local chemical environment precisely described and the requirement of rotational covariance naturally fulfilled, this hybrid model is proven to give an accurate molecular polarizability prediction, essentially reducing the number of training samples. The atomic polarizabilities are physically interpretable and transferable to larger molecules unseen in the training set. This promising method may find its wide range of applications, such as spectroscopic simulations and the construction of polarizable force fields.
Collapse
Affiliation(s)
- Chaoqiang Feng
- Anhui Key Laboratory of Optoelectric Materials Science and Technology, Department of Physics, Anhui Normal University, Wuhu, Anhui 241000, China.,Hefei National Research Center for Physical Sciences at the Microscale, Department of Chemical Physics, Key Laboratory of Surface and Interface Chemistry and Energy Catalysis of Anhui Higher Education Institutes, University of Science and Technology of China, Hefei, Anhui 230026, China
| | - Jin Xi
- Anhui Key Laboratory of Optoelectric Materials Science and Technology, Department of Physics, Anhui Normal University, Wuhu, Anhui 241000, China
| | - Yaolong Zhang
- Hefei National Research Center for Physical Sciences at the Microscale, Department of Chemical Physics, Key Laboratory of Surface and Interface Chemistry and Energy Catalysis of Anhui Higher Education Institutes, University of Science and Technology of China, Hefei, Anhui 230026, China
| | - Bin Jiang
- Hefei National Research Center for Physical Sciences at the Microscale, Department of Chemical Physics, Key Laboratory of Surface and Interface Chemistry and Energy Catalysis of Anhui Higher Education Institutes, University of Science and Technology of China, Hefei, Anhui 230026, China
| | - Yong Zhou
- Anhui Key Laboratory of Optoelectric Materials Science and Technology, Department of Physics, Anhui Normal University, Wuhu, Anhui 241000, China
| |
Collapse
|
42
|
Kříž K, Schmidt L, Andersson AT, Walz MM, van der Spoel D. An Imbalance in the Force: The Need for Standardized Benchmarks for Molecular Simulation. J Chem Inf Model 2023; 63:412-431. [PMID: 36630710 PMCID: PMC9875315 DOI: 10.1021/acs.jcim.2c01127] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/06/2022] [Indexed: 01/12/2023]
Abstract
Force fields (FFs) for molecular simulation have been under development for more than half a century. As with any predictive model, rigorous testing and comparisons of models critically depends on the availability of standardized data sets and benchmarks. While such benchmarks are rather common in the fields of quantum chemistry, this is not the case for empirical FFs. That is, few benchmarks are reused to evaluate FFs, and development teams rather use their own training and test sets. Here we present an overview of currently available tests and benchmarks for computational chemistry, focusing on organic compounds, including halogens and common ions, as FFs for these are the most common ones. We argue that many of the benchmark data sets from quantum chemistry can in fact be reused for evaluating FFs, but new gas phase data is still needed for compounds containing phosphorus and sulfur in different valence states. In addition, more nonequilibrium interaction energies and forces, as well as molecular properties such as electrostatic potentials around compounds, would be beneficial. For the condensed phases there is a large body of experimental data available, and tools to utilize these data in an automated fashion are under development. If FF developers, as well as researchers in artificial intelligence, would adopt a number of these data sets, it would become easier to compare the relative strengths and weaknesses of different models and to, eventually, restore the balance in the force.
Collapse
Affiliation(s)
- Kristian Kříž
- Department
of Cell and Molecular Biology, Uppsala University, Box 596, SE-75124Uppsala, Sweden
| | - Lisa Schmidt
- Faculty
of Biosciences, University of Heidelberg, Heidelberg69117, Germany
| | - Alfred T. Andersson
- Department
of Cell and Molecular Biology, Uppsala University, Box 596, SE-75124Uppsala, Sweden
| | - Marie-Madeleine Walz
- Department
of Cell and Molecular Biology, Uppsala University, Box 596, SE-75124Uppsala, Sweden
| | - David van der Spoel
- Department
of Cell and Molecular Biology, Uppsala University, Box 596, SE-75124Uppsala, Sweden
| |
Collapse
|
43
|
Chmiela S, Vassilev-Galindo V, Unke OT, Kabylda A, Sauceda HE, Tkatchenko A, Müller KR. Accurate global machine learning force fields for molecules with hundreds of atoms. SCIENCE ADVANCES 2023; 9:eadf0873. [PMID: 36630510 PMCID: PMC9833674 DOI: 10.1126/sciadv.adf0873] [Citation(s) in RCA: 16] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/29/2022] [Accepted: 11/28/2022] [Indexed: 05/25/2023]
Abstract
Global machine learning force fields, with the capacity to capture collective interactions in molecular systems, now scale up to a few dozen atoms due to considerable growth of model complexity with system size. For larger molecules, locality assumptions are introduced, with the consequence that nonlocal interactions are not described. Here, we develop an exact iterative approach to train global symmetric gradient domain machine learning (sGDML) force fields (FFs) for several hundred atoms, without resorting to any potentially uncontrolled approximations. All atomic degrees of freedom remain correlated in the global sGDML FF, allowing the accurate description of complex molecules and materials that present phenomena with far-reaching characteristic correlation lengths. We assess the accuracy and efficiency of sGDML on a newly developed MD22 benchmark dataset containing molecules from 42 to 370 atoms. The robustness of our approach is demonstrated in nanosecond path-integral molecular dynamics simulations for supramolecular complexes in the MD22 dataset.
Collapse
Affiliation(s)
- Stefan Chmiela
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- Berlin Institute for the Foundations of Learning and Data – BIFOLD, Germany
| | - Valentin Vassilev-Galindo
- Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Oliver T. Unke
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- Google Research, Brain Team, Berlin, Germany
| | - Adil Kabylda
- Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Huziel E. Sauceda
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- Berlin Institute for the Foundations of Learning and Data – BIFOLD, Germany
- Departamento de Materia Condensada, Instituto de Física, Universidad Nacional Autónoma de México, Cd. de México C.P. 04510, Mexico
- BASLEARN - TU Berlin/BASF Joint Lab for Machine Learning, Technische Universität Berlin, 10587 Berlin, Germany
| | - Alexandre Tkatchenko
- Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg
| | - Klaus-Robert Müller
- Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany
- Berlin Institute for the Foundations of Learning and Data – BIFOLD, Germany
- Google Research, Brain Team, Berlin, Germany
- Max Planck Institute for Informatics, Stuhlsatzenhausweg, 66123 Saarbrücken, Germany
- Department of Artificial Intelligence, Korea University, Anam-dong, Seongbuk-gu, Seoul 02841, Korea
| |
Collapse
|
44
|
Chen MW, Chang MS, Mao Y, Hu S, Kung CC. Machine learning in the evaluation and prediction models of biochar application: A review. Sci Prog 2023; 106:368504221148842. [PMID: 36628421 PMCID: PMC10450295 DOI: 10.1177/00368504221148842] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/12/2023]
Abstract
This article reviews recent studies applying machine learning (ML) approaches to biochar applications. We first briefly introduce the general biochar production process. Various aspects are contained, including the biochar application in the elimination of heavy metals and/or organic compounds and the biochar application in environmental and economic scopes, for instance, food security, energy, and carbon emission. The utilization of ML methods, including ANN, RF, and NN, plays a vital role in evaluating and predicting the efficiency of biochar absorption. It has been proved that ML methods can validly predict the adsorption effectiveness of biochar for water heavy metals with higher accuracy. Moreover, the literature proposed a comprehensive data-driven model to forecast biochar yield and compositions under various biomass input feedstock and different pyrolysis criteria. They said a 12.7% improvement in prediction accuracy compared to the existing literature. However, it might need further optimization in this direction. In summary, this review concludes increasing studies that a well-trained ML method can sufficiently reduce the number of experiment trials and working times associated with higher prediction accuracy. Moreover, further studies on ML applications are needed to optimize the trade-off between biochar yield and its composition.
Collapse
Affiliation(s)
- Meng-Wei Chen
- Institute of Economics and Finance, Nanjing Audit University, Nanjing, China
| | | | - Yuehua Mao
- School of International Economics, University of International Business and Economics, Beijing, China
| | - Shuyin Hu
- School of Economics, Jiangxi University of Finance and Economics, Nanchang, China
| | - Chih-Chun Kung
- School of Economics, Jiangxi University of Finance and Economics, Nanchang, China
| |
Collapse
|
45
|
Grisafi A, Lewis AM, Rossi M, Ceriotti M. Electronic-Structure Properties from Atom-Centered Predictions of the Electron Density. J Chem Theory Comput 2022. [PMID: 36453538 DOI: 10.1021/acs.jctc.2c00850] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/05/2022]
Abstract
The electron density of a molecule or material has recently received major attention as a target quantity of machine-learning models. A natural choice to construct a model that yields transferable and linear-scaling predictions is to represent the scalar field using a multicentered atomic basis analogous to that routinely used in density fitting approximations. However, the nonorthogonality of the basis poses challenges for the learning exercise, as it requires accounting for all the atomic density components at once. We devise a gradient-based approach to directly minimize the loss function of the regression problem in an optimized and highly sparse feature space. In so doing, we overcome the limitations associated with adopting an atom-centered model to learn the electron density over arbitrarily complex data sets, obtaining very accurate predictions using a comparatively small training set. The enhanced framework is tested on 32-molecule periodic cells of liquid water, presenting enough complexity to require an optimal balance between accuracy and computational efficiency. We show that starting from the predicted density a single Kohn-Sham diagonalization step can be performed to access total energy components that carry an error of just 0.1 meV/atom with respect to the reference density functional calculations. Finally, we test our method on the highly heterogeneous QM9 benchmark data set, showing that a small fraction of the training data is enough to derive ground-state total energies within chemical accuracy.
Collapse
Affiliation(s)
- Andrea Grisafi
- PASTEUR, Département de chimie, École Normale Supérieure, PSL University, Sorbonne Université, CNRS, 75005 Paris, France
| | - Alan M. Lewis
- Max Planck Institute for the Structure and Dynamics of Matter, Luruper Chaussee 149, 22761 Hamburg, Germany
| | - Mariana Rossi
- Max Planck Institute for the Structure and Dynamics of Matter, Luruper Chaussee 149, 22761 Hamburg, Germany
| | - Michele Ceriotti
- Laboratory of Computational Science and Modeling, IMX, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, Switzerland
| |
Collapse
|
46
|
Reiser P, Neubert M, Eberhard A, Torresi L, Zhou C, Shao C, Metni H, van Hoesel C, Schopmans H, Sommer T, Friederich P. Graph neural networks for materials science and chemistry. COMMUNICATIONS MATERIALS 2022; 3:93. [PMID: 36468086 PMCID: PMC9702700 DOI: 10.1038/s43246-022-00315-6] [Citation(s) in RCA: 38] [Impact Index Per Article: 19.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/10/2022] [Accepted: 11/07/2022] [Indexed: 05/14/2023]
Abstract
Machine learning plays an increasingly important role in many areas of chemistry and materials science, being used to predict materials properties, accelerate simulations, design new structures, and predict synthesis routes of new materials. Graph neural networks (GNNs) are one of the fastest growing classes of machine learning models. They are of particular relevance for chemistry and materials science, as they directly work on a graph or structural representation of molecules and materials and therefore have full access to all relevant information required to characterize materials. In this Review, we provide an overview of the basic principles of GNNs, widely used datasets, and state-of-the-art architectures, followed by a discussion of a wide range of recent applications of GNNs in chemistry and materials science, and concluding with a road-map for the further development and application of GNNs.
Collapse
Affiliation(s)
- Patrick Reiser
- Institute of Theoretical Informatics, Karlsruhe Institute of Technology, Am Fasanengarten 5, 76131 Karlsruhe, Germany
- Institute of Nanotechnology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany
| | - Marlen Neubert
- Institute of Theoretical Informatics, Karlsruhe Institute of Technology, Am Fasanengarten 5, 76131 Karlsruhe, Germany
| | - André Eberhard
- Institute of Theoretical Informatics, Karlsruhe Institute of Technology, Am Fasanengarten 5, 76131 Karlsruhe, Germany
| | - Luca Torresi
- Institute of Theoretical Informatics, Karlsruhe Institute of Technology, Am Fasanengarten 5, 76131 Karlsruhe, Germany
| | - Chen Zhou
- Institute of Theoretical Informatics, Karlsruhe Institute of Technology, Am Fasanengarten 5, 76131 Karlsruhe, Germany
| | - Chen Shao
- Institute of Theoretical Informatics, Karlsruhe Institute of Technology, Am Fasanengarten 5, 76131 Karlsruhe, Germany
- Present Address: Institute for Applied Informatics and Formal Description Systems, Karlsruhe Institute of Technology, Kaiserstr. 89, 76133 Karlsruhe, Germany
| | - Houssam Metni
- Institute of Theoretical Informatics, Karlsruhe Institute of Technology, Am Fasanengarten 5, 76131 Karlsruhe, Germany
- ECPM, Université de Strasbourg, 25 Rue Becquerel, 67087 Strasbourg, France
| | - Clint van Hoesel
- Institute of Theoretical Informatics, Karlsruhe Institute of Technology, Am Fasanengarten 5, 76131 Karlsruhe, Germany
- Department of Applied Physics, Eindhoven University of Technology, Groene Loper 19, 5612 AP Eindhoven, The Netherlands
| | - Henrik Schopmans
- Institute of Theoretical Informatics, Karlsruhe Institute of Technology, Am Fasanengarten 5, 76131 Karlsruhe, Germany
- Institute of Nanotechnology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany
| | - Timo Sommer
- Institute of Theoretical Informatics, Karlsruhe Institute of Technology, Am Fasanengarten 5, 76131 Karlsruhe, Germany
- Institute for Theory of Condensed Matter, Karlsruhe Institute of Technology, Wolfgang-Gaede-Str. 1, 76131 Karlsruhe, Germany
- Present Address: School of Chemistry, Trinity College Dublin, College Green, Dublin 2, Ireland
| | - Pascal Friederich
- Institute of Theoretical Informatics, Karlsruhe Institute of Technology, Am Fasanengarten 5, 76131 Karlsruhe, Germany
- Institute of Nanotechnology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen, Germany
| |
Collapse
|
47
|
Machine learning the Hohenberg-Kohn map for molecular excited states. Nat Commun 2022; 13:7044. [DOI: 10.1038/s41467-022-34436-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2022] [Accepted: 10/25/2022] [Indexed: 11/18/2022] Open
Abstract
AbstractThe Hohenberg-Kohn theorem of density-functional theory establishes the existence of a bijection between the ground-state electron density and the external potential of a many-body system. This guarantees a one-to-one map from the electron density to all observables of interest including electronic excited-state energies. Time-Dependent Density-Functional Theory (TDDFT) provides one framework to resolve this map; however, the approximations inherent in practical TDDFT calculations, together with their computational expense, motivate finding a cheaper, more direct map for electronic excitations. Here, we show that determining density and energy functionals via machine learning allows the equations of TDDFT to be bypassed. The framework we introduce is used to perform the first excited-state molecular dynamics simulations with a machine-learned functional on malonaldehyde and correctly capture the kinetics of its excited-state intramolecular proton transfer, allowing insight into how mechanical constraints can be used to control the proton transfer reaction in this molecule. This development opens the door to using machine-learned functionals for highly efficient excited-state dynamics simulations.
Collapse
|
48
|
Zhang Y, Lin Q, Jiang B. Atomistic neural network representations for chemical dynamics simulations of molecular, condensed phase, and interfacial systems: Efficiency, representability, and generalization. WIRES COMPUTATIONAL MOLECULAR SCIENCE 2022. [DOI: 10.1002/wcms.1645] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Affiliation(s)
- Yaolong Zhang
- Department of Chemical Physics, School of Chemistry and Materials Science, Key Laboratory of Surface and Interface Chemistry and Energy Catalysis of Anhui Higher Education Institutes University of Science and Technology of China Hefei Anhui China
| | - Qidong Lin
- Department of Chemical Physics, School of Chemistry and Materials Science, Key Laboratory of Surface and Interface Chemistry and Energy Catalysis of Anhui Higher Education Institutes University of Science and Technology of China Hefei Anhui China
| | - Bin Jiang
- Department of Chemical Physics, School of Chemistry and Materials Science, Key Laboratory of Surface and Interface Chemistry and Energy Catalysis of Anhui Higher Education Institutes University of Science and Technology of China Hefei Anhui China
| |
Collapse
|
49
|
Mazouin B, Schöpfer AA, von Lilienfeld OA. Selected machine learning of HOMO-LUMO gaps with improved data-efficiency. MATERIALS ADVANCES 2022; 3:8306-8316. [PMID: 36561279 PMCID: PMC9662596 DOI: 10.1039/d2ma00742h] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 06/27/2022] [Accepted: 09/12/2022] [Indexed: 06/17/2023]
Abstract
Despite their relevance for organic electronics, quantum machine learning (QML) models of molecular electronic properties, such as HOMO-LUMO-gaps, often struggle to achieve satisfying data-efficiency as measured by decreasing prediction errors for increasing training set sizes. We demonstrate that partitioning training sets into different chemical classes prior to training results in independently trained QML models with overall reduced training data needs. For organic molecules drawn from previously published QM7 and QM9-data-sets we have identified and exploited three relevant classes corresponding to compounds containing either aromatic rings and carbonyl groups, or single unsaturated bonds, or saturated bonds The selected QML models of band-gaps (considered at GW and hybrid DFT levels of theory) reach mean absolute prediction errors of ∼0.1 eV for up to an order of magnitude fewer training molecules than for QML models trained on randomly selected molecules. Comparison to Δ-QML models of band-gaps indicates that selected QML exhibit superior data-efficiency. Our findings suggest that selected QML, e.g. based on simple classifications prior to training, could help to successfully tackle challenging quantum property screening tasks of large libraries with high fidelity and low computational burden.
Collapse
Affiliation(s)
- Bernard Mazouin
- University of Vienna, Faculty of Physics and Vienna Doctoral School in Physics Kolingasse 14-16 1090 Vienna Austria
| | | | - O Anatole von Lilienfeld
- Departments of Chemistry, Materials Science and Engineering, and Physics, University of Toronto St. George Campus Toronto ON Canada
- Vector Institute for Artificial Intelligence Toronto ON M5S 1M1 Canada
- Machine Learning Group, Technische Universität Berlin and Institute for the Foundations of Learning and Data 10587 Berlin Germany
| |
Collapse
|
50
|
Fan G, McSloy A, Aradi B, Yam CY, Frauenheim T. Obtaining Electronic Properties of Molecules through Combining Density Functional Tight Binding with Machine Learning. J Phys Chem Lett 2022; 13:10132-10139. [PMID: 36269857 DOI: 10.1021/acs.jpclett.2c02586] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/16/2023]
Abstract
We have introduced a machine learning workflow that allows for optimizing electronic properties in the density functional tight binding method (DFTB). The workflow allows for the optimization of electronic properties by generating two-center integrals, either by training basis function parameters directly or by training a spline model for the diatomic integrals, which are then used to build the Hamiltonian and the overlap matrices. Using our workflow, we have managed to obtain improved electronic properties, such as charge distributions, dipole moments, and approximated polarizabilities. While both machine learning approaches enabled us to improve on the electronic properties of the molecules as compared with existing DFTB parametrizations, only by training on the basis function parameters we were able to obtain consistent Hamiltonians and overlap matrices in the physically reasonable ranges or to improve on multiple electronic properties simultaneously.
Collapse
Affiliation(s)
- Guozheng Fan
- Bremen Center for Computational Materials Science, University of Bremen, 28359Bremen, Germany
| | - Adam McSloy
- Bremen Center for Computational Materials Science, University of Bremen, 28359Bremen, Germany
| | - Bálint Aradi
- Bremen Center for Computational Materials Science, University of Bremen, 28359Bremen, Germany
| | - Chi-Yung Yam
- Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, 518000China
| | - Thomas Frauenheim
- Bremen Center for Computational Materials Science, University of Bremen, 28359Bremen, Germany
- Beijing Computational Science Research Center, 100193Beijing, China
- Shenzhen JL Computational Science and Applied Research Institute, 518110Shenzhen, China
| |
Collapse
|