1
|
Gao P, Zhang Q, Keely D, Cleveland DW, Ye Y, Zheng W, Shen M, Yu H. Molecular Graph-Based Deep Learning Algorithm Facilitates an Imaging-Based Strategy for Rapid Discovery of Small Molecules Modulating Biomolecular Condensates. J Med Chem 2023; 66:15084-15093. [PMID: 37937963 PMCID: PMC10810226 DOI: 10.1021/acs.jmedchem.3c00490] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2023]
Abstract
Biomolecular condensates are proposed to cause diseases, such as cancer and neurodegeneration, by concentrating proteins at abnormal subcellular loci. Imaging-based compound screens have been used to identify small molecules that reverse or promote biomolecular condensates. However, limitations of conventional imaging-based methods restrict the screening scale. Here, we used a graph convolutional network (GCN)-based computational approach and identified small molecule candidates that reduce the nuclear liquid-liquid phase separation of TAR DNA-binding protein 43 (TDP-43), an essential protein that undergoes phase transition in neurodegenerative diseases. We demonstrated that the GCN-based deep learning algorithm is suitable for spatial information extraction from the molecular graph. Thus, this is a promising method to identify small molecule candidates with novel scaffolds. Furthermore, we validated that these candidates do not affect the normal splicing function of TDP-43. Taken together, a combination of an imaging-based screen and a GCN-based deep learning method dramatically improves the speed and accuracy of the compound screen for biomolecular condensates.
Collapse
Affiliation(s)
- Peng Gao
- The National Center for Advancing Translational Sciences (NCATS), National Institutes of Health (NIH), MD 20850, USA
| | - Qi Zhang
- The National Center for Advancing Translational Sciences (NCATS), National Institutes of Health (NIH), MD 20850, USA
| | - Devin Keely
- Center for Alzheimer’s and Neurodegenerative Diseases, Department of Molecular Biology, Peter O’Donnell Jr. Brain Institute, UT Southwestern Medical Center, TX, 75287, USA
| | - Don W. Cleveland
- Department of Cellular and Molecular Medicine, UC San Diego, CA, 92093, USA
| | - Yihong Ye
- National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK), National Institutes of Health (NIH), MD 20850, USA
| | - Wei Zheng
- The National Center for Advancing Translational Sciences (NCATS), National Institutes of Health (NIH), MD 20850, USA
| | - Min Shen
- The National Center for Advancing Translational Sciences (NCATS), National Institutes of Health (NIH), MD 20850, USA
| | - Haiyang Yu
- Center for Alzheimer’s and Neurodegenerative Diseases, Department of Molecular Biology, Peter O’Donnell Jr. Brain Institute, UT Southwestern Medical Center, TX, 75287, USA
| |
Collapse
|
2
|
Christiansen MPV, Rønne N, Hammer B. Atomistic Global Optimization X: A Python package for optimization of atomistic structures. J Chem Phys 2022; 157:054701. [DOI: 10.1063/5.0094165] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022] Open
Abstract
Modelling and understanding properties of materials from first principles require knowledge of the underlyingatomistic structure. This entails knowing the individual chemical identity and position of all atoms involved.Obtaining such information for macro-molecules, nano-particles, clusters, and for the surface, interface, andbulk phases of amorphous and solid materials represents a difficult high-dimensional global optimizationproblem. The rise of machine learning techniques in materials science has, however, led to many compellingdevelopments that may speed up structure searches. The complexity of such new methods has prompted aneed for an efficient way of assembling them into global optimization algorithms that can be experimentedwith. In this paper, we introduce the Atomistic Global Optimization X (AGOX) framework and code, asa customizable approach that enables efficient building and testing of global optimization algorithms. Amodular way of expressing global optimization algorithms is described and modern programming practicesare used to enable that modularity in the freely available AGOX python package. A number of examplesof global optimization approaches are implemented and analyzed. This ranges from random search andbasin-hopping to machine learning aided approaches with on-the-fly learnt surrogate energy landscapes. Themethods are show-cased on problems ranging from supported clusters over surface reconstructions to largecarbon clusters and metal-nitride clusters incorporated into graphene sheets.
Collapse
Affiliation(s)
| | - Nikolaj Rønne
- Aarhus University Department of Physics and Astronomy, Denmark
| | - Bjørk Hammer
- Department of Physics and Astronomy and Interdisciplinary Nanoscience Center (iNANO) and Department of Physics and Astronomy, Aarhus University Department of Physics and Astronomy, Denmark
| |
Collapse
|
3
|
Gao P, Xu M, Zhang Q, Chen CZ, Guo H, Ye Y, Zheng W, Shen M. Graph Convolutional Network-Based Screening Strategy for Rapid Identification of SARS-CoV-2 Cell-Entry Inhibitors. J Chem Inf Model 2022; 62:1988-1997. [PMID: 35404596 PMCID: PMC9016773 DOI: 10.1021/acs.jcim.2c00222] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2022] [Indexed: 11/29/2022]
Abstract
The cell entry of SARS-CoV-2 has emerged as an attractive drug development target. We previously reported that the entry of SARS-CoV-2 depends on the cell surface heparan sulfate proteoglycan (HSPG) and the cortex actin, which can be targeted by therapeutic agents identified by conventional drug repurposing screens. However, this drug identification strategy requires laborious library screening, which is time consuming, and often limited number of compounds can be screened. As an alternative approach, we developed and trained a graph convolutional network (GCN)-based classification model using information extracted from experimentally identified HSPG and actin inhibitors. This method allowed us to virtually screen 170,000 compounds, resulting in ∼2000 potential hits. A hit confirmation assay with the uptake of a fluorescently labeled HSPG cargo further shortlisted 256 active compounds. Among them, 16 compounds had modest to strong inhibitory activities against the entry of SARS-CoV-2 pseudotyped particles into Vero E6 cells. These results establish a GCN-based virtual screen workflow for rapid identification of new small molecule inhibitors against validated drug targets.
Collapse
Affiliation(s)
- Peng Gao
- The National Center for Advancing Translational Sciences (NCATS), National Institutes of Health (NIH), Bethesda, Maryland 20850, United States
| | - Miao Xu
- The National Center for Advancing Translational Sciences (NCATS), National Institutes of Health (NIH), Bethesda, Maryland 20850, United States
| | - Qi Zhang
- The National Center for Advancing Translational Sciences (NCATS), National Institutes of Health (NIH), Bethesda, Maryland 20850, United States
- National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK), National Institutes of Health (NIH), Bethesda, Maryland 20892, United States
| | - Catherine Z Chen
- The National Center for Advancing Translational Sciences (NCATS), National Institutes of Health (NIH), Bethesda, Maryland 20850, United States
| | - Hui Guo
- The National Center for Advancing Translational Sciences (NCATS), National Institutes of Health (NIH), Bethesda, Maryland 20850, United States
| | - Yihong Ye
- National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK), National Institutes of Health (NIH), Bethesda, Maryland 20892, United States
| | - Wei Zheng
- The National Center for Advancing Translational Sciences (NCATS), National Institutes of Health (NIH), Bethesda, Maryland 20850, United States
| | - Min Shen
- The National Center for Advancing Translational Sciences (NCATS), National Institutes of Health (NIH), Bethesda, Maryland 20850, United States
| |
Collapse
|
4
|
Tang Z, Hammer B. Dimerization of dehydrogenated polycyclic aromatic hydrocarbons on graphene. J Chem Phys 2022; 156:134703. [PMID: 35395907 DOI: 10.1063/5.0083253] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Abstract
Dimerization of polycyclic aromatic hydrocarbons (PAHs) is an important, yet poorly understood, step in the on-surface synthesis of graphene (nanoribbon), soot formation, and growth of carbonaceous dust grains in the interstellar medium (ISM). The on-surface synthesis of graphene and the growth of carbonaceous dust grains in the ISM require the chemical dimerization in which chemical bonds are formed between PAH monomers. An accurate and cheap method of exploring structure rearrangements is needed to reveal the mechanism of chemical dimerization on surfaces. This work has investigated the chemical dimerization of two dehydrogenated PAHs (coronene and pentacene) on graphene via an evolutionary algorithm augmented by machine learning surrogate potentials and a set of customized structure operators. Different dimer structures on surfaces have been successfully located by our structure search methods. Their binding energies are within the experimental errors of temperature programmed desorption measurements. The mechanism of coronene dimer formation on graphene is further studied and discussed.
Collapse
Affiliation(s)
- Zeyuan Tang
- Center for Interstellar Catalysis, Department of Physics and Astronomy, Aarhus University, Ny Munkegade 120, Aarhus C 8000, Denmark
| | - Bjørk Hammer
- Center for Interstellar Catalysis, Department of Physics and Astronomy, Aarhus University, Ny Munkegade 120, Aarhus C 8000, Denmark
| |
Collapse
|
5
|
Shi X, Lin X, Luo R, Wu S, Li L, Zhao ZJ, Gong J. Dynamics of Heterogeneous Catalytic Processes at Operando Conditions. JACS AU 2021; 1:2100-2120. [PMID: 34977883 PMCID: PMC8715484 DOI: 10.1021/jacsau.1c00355] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/17/2021] [Indexed: 05/02/2023]
Abstract
The rational design of high-performance catalysts is hindered by the lack of knowledge of the structures of active sites and the reaction pathways under reaction conditions, which can be ideally addressed by an in situ/operando characterization. Besides the experimental insights, a theoretical investigation that simulates reaction conditions-so-called operando modeling-is necessary for a plausible understanding of a working catalyst system at the atomic scale. However, there is still a huge gap between the current widely used computational model and the concept of operando modeling, which should be achieved through multiscale computational modeling. This Perspective describes various modeling approaches and machine learning techniques that step toward operando modeling, followed by selected experimental examples that present an operando understanding in the thermo- and electrocatalytic processes. At last, the remaining challenges in this area are outlined.
Collapse
Affiliation(s)
- Xiangcheng Shi
- Key
Laboratory for Green Chemical Technology of Ministry of Education,
School of Chemical Engineering and Technology, Tianjin University, Tianjin 300072, China
- Collaborative
Innovation Center of Chemical Science and Engineering, Tianjin 300072, China
- Joint
School of National University of Singapore and Tianjin University,
International Campus of Tianjin University, Fuzhou 350207, China
| | - Xiaoyun Lin
- Key
Laboratory for Green Chemical Technology of Ministry of Education,
School of Chemical Engineering and Technology, Tianjin University, Tianjin 300072, China
- Collaborative
Innovation Center of Chemical Science and Engineering, Tianjin 300072, China
| | - Ran Luo
- Key
Laboratory for Green Chemical Technology of Ministry of Education,
School of Chemical Engineering and Technology, Tianjin University, Tianjin 300072, China
- Collaborative
Innovation Center of Chemical Science and Engineering, Tianjin 300072, China
| | - Shican Wu
- Key
Laboratory for Green Chemical Technology of Ministry of Education,
School of Chemical Engineering and Technology, Tianjin University, Tianjin 300072, China
- Collaborative
Innovation Center of Chemical Science and Engineering, Tianjin 300072, China
| | - Lulu Li
- Key
Laboratory for Green Chemical Technology of Ministry of Education,
School of Chemical Engineering and Technology, Tianjin University, Tianjin 300072, China
- Collaborative
Innovation Center of Chemical Science and Engineering, Tianjin 300072, China
| | - Zhi-Jian Zhao
- Key
Laboratory for Green Chemical Technology of Ministry of Education,
School of Chemical Engineering and Technology, Tianjin University, Tianjin 300072, China
- Collaborative
Innovation Center of Chemical Science and Engineering, Tianjin 300072, China
| | - Jinlong Gong
- Key
Laboratory for Green Chemical Technology of Ministry of Education,
School of Chemical Engineering and Technology, Tianjin University, Tianjin 300072, China
- Collaborative
Innovation Center of Chemical Science and Engineering, Tianjin 300072, China
- Joint
School of National University of Singapore and Tianjin University,
International Campus of Tianjin University, Fuzhou 350207, China
| |
Collapse
|
6
|
Posenitskiy E, Spiegelman F, Lemoine D. On application of deep learning to simplified quantum-classical dynamics in electronically excited states. MACHINE LEARNING: SCIENCE AND TECHNOLOGY 2021. [DOI: 10.1088/2632-2153/abfe3f] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022] Open
Abstract
Abstract
Deep learning (DL) is applied to simulate non-adiabatic molecular dynamics of phenanthrene, using the time-dependent density functional based tight binding (TD-DFTB) approach for excited states combined with mixed quantum–classical propagation. Reference calculations rely on Tully’s fewest-switches surface hopping (FSSH) algorithm coupled to TD-DFTB, which provides electronic relaxation dynamics in fair agreement with various available experimental results. Aiming at describing the coupled electron-nuclei dynamics in large molecular systems, we then examine the combination of DL for excited-state potential energy surfaces (PESs) with a simplified trajectory surface hopping propagation based on the Belyaev–Lebedev (BL) scheme. We start to assess the accuracy of the TD-DFTB approach upon comparison of the optical spectrum with experimental and higher-level theoretical results. Using the recently developed SchNetPack (Schütt et al 2019 J. Chem. Theory Comput.
15 448–55) for DL applications, we train several models and evaluate their performance in predicting excited-state energies and forces. Then, the main focus is given to the analysis of the electronic population of low-lying excited states computed with the aforementioned methods. We determine the relaxation timescales and compare them with experimental data. Our results show that DL demonstrates its ability to describe the excited-state PESs. When coupled to the simplified BL scheme considered in this study, it provides reliable description of the electronic relaxation in phenanthrene as compared with either the experimental data or the higher-level FSSH/TD-DFTB theoretical results. Furthermore, the DL performance allows high-throughput analysis at a negligible cost.
Collapse
|
7
|
Yashima Y, Okada Y, Harada M, Okada T. Structures of ions accommodated in salty ice Ih crystals. Phys Chem Chem Phys 2021; 23:17945-17952. [PMID: 34382049 DOI: 10.1039/d1cp01624e] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
Frozen aqueous electrolytes are ubiquitous and involved in various phenomena occurring in the natural environment. Although salts are expelled from ice during freezing of aqueous solutions, minor amounts of the constituent ions are accommodated in the crystal lattice of ice. This phenomenon was associated with the generation of the Workman-Reynolds freezing potential. Molecular simulations also confirmed the ion incorporation in the crystal lattice of ice Ih upon freezing of aqueous electrolytes and identified possible local structures of the ions. However, no experimental information is available on the structure of ions accommodated in the crystal lattice of ice Ih. In this work, we use X-ray absorption fine structure (XAFS) to study the local structures of K+ and Cl- accommodated in ice Ih single crystals. Previous molecular simulations predicted that ions are trapped in the hexagonal cavities of the ice structure or replace two water molecules in the crystal lattice. Four possible configurations are considered and optimized by the calculations using ONIOM (QM/QM/QM). The results are evaluated in terms of the agreement between the experimental XAFS spectra and those simulated from the optimized structures. The spectra are most reasonably interpreted by assuming that K+ replaces one water molecule in the ice crystal lattice and is accommodated in a tetrahedral coordination cage. Similarly, Cl- probably adopts the same configuration, because it explains the coordination number better than other structures, such as that assuming the replacement of two water molecules belonging to the same hexagonal planes.
Collapse
Affiliation(s)
- Yuga Yashima
- Department of Chemistry, Tokyo Institute of Technology, Meguro-ku, Tokyo 152-8551, Japan.
| | | | | | | |
Collapse
|
8
|
Gao P, Zhang J, Qiu H, Zhao S. A general QSPR protocol for the prediction of atomic/inter-atomic properties: a fragment based graph convolutional neural network (F-GCN). Phys Chem Chem Phys 2021; 23:13242-13249. [PMID: 34086015 DOI: 10.1039/d1cp00677k] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
In this study, a general quantitative structure-property relationship (QSPR) protocol, fragment based graph convolutional neural network (F-GCN), was developed for the prediction of atomic/inter-atomic properties. We applied this novel artificial intelligence (AI) tool in predictions of NMR chemical shifts and bond dissociation energies (BDEs). The obtained results were comparable to experimental measurements, while the computational cost was substantially reduced, with respect to pure density functional theory (DFT) calculations. The two important features of F-GCN can be summarised as: first, it could utilise different levels of molecular fragments for atomic/inter-atomic information extraction; second, the designed architecture is also open to include additional descriptors for a more accurate solution of the local environment at atomic level, making itself more efficient for structural solutions. And during our test, the averaged prediction error of 1H NMR chemical shifts is as small as 0.32 ppm, and the error of C-H BDE estimation is 2.7 kcal mol-1. Moreover, we further demonstrated the applicability of this developed F-GCN model via several challenging structural assignments. The success of the F-GCN in atomic and inter-atomic predictions also indicates an essential improvement of computational chemistry with the assistance of AI tools.
Collapse
Affiliation(s)
- Peng Gao
- School of Chemistry and Molecular Bioscience, University of Wollongong, NSW 2500, Australia
| | - Jie Zhang
- Centre of Chemistry and Chemical Biology, Bioland Laboratory (Guangzhou Regenerative Medicine and Health-Guangdong Laboratory), Guangzhou 53000, China. and School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Hongbo Qiu
- Department of Chemical Engineering, Monash University, Clayton, VIC 3800, Australia
| | - Shuaifei Zhao
- Institute for Frontier Materials (IFM), Deakin University, Perth, WA, Australia
| |
Collapse
|
9
|
Hu J, Yang W, Dilanga Siriwardane EM. Distance Matrix-Based Crystal Structure Prediction Using Evolutionary Algorithms. J Phys Chem A 2020; 124:10909-10919. [DOI: 10.1021/acs.jpca.0c08775] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Jianjun Hu
- Department of Computer Science and Engineering, University of South Carolina, Columbia, South Carolina 29201, United States
| | - Wenhui Yang
- School of Mechanical Engineering, Guizhou University, Guiyang 550050, China
| | | |
Collapse
|
10
|
Gao P, Zhang J, Sun Y, Yu J. Toward Accurate Predictions of Atomic Properties via Quantum Mechanics Descriptors Augmented Graph Convolutional Neural Network: Application of This Novel Approach in NMR Chemical Shifts Predictions. J Phys Chem Lett 2020; 11:9812-9818. [PMID: 33151693 DOI: 10.1021/acs.jpclett.0c02654] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
In this study, an augmented Graph Convolutional Network (GCN) with quantum mechanics (QM) descriptors was reported for its accurate predictions of NMR chemical shifts with respect to experimental values. The prediction errors of 13C/1H NMR chemical shifts can be as small as 2.14/0.11 ppm. There are two crucial characteristics for this modified GCN: in one aspect, such a novel neural network could efficiently extract the overall molecule structure information; in another aspect, it could accurately solve the chemical environment of the target atom. As there exists an imperfect linear regression between the experimental NMR chemical shifts (δ) and the density functional theory (DFT) calculated isotropic shielding constants (σ), the inclusion of QM descriptors within GCN can largely improve its performance. Moreover, few-shot learning also becomes feasible with these descriptors. The success of this novel GCN in chemical shifts predictions also indicates its potential applicability for other computational studies.
Collapse
Affiliation(s)
- Peng Gao
- School of Chemistry and Molecular Bioscience, University of Wollongong, Wollongong, NSW 2500, Australia
| | - Jie Zhang
- Centre of Chemistry and Chemical Biology, Bioland Laboratory (Guangzhou Regenerative Medicine and Health-Guangdong Laboratory), Guangzhou 53000, China
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Yuzhu Sun
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| | - Jianguo Yu
- School of Chemical Engineering, East China University of Science and Technology, Shanghai 200237, China
| |
Collapse
|
11
|
Gao P, Zhang J, Sun Y, Yu J. Accurate predictions of aqueous solubility of drug molecules via the multilevel graph convolutional network (MGCN) and SchNet architectures. Phys Chem Chem Phys 2020; 22:23766-23772. [PMID: 33063077 DOI: 10.1039/d0cp03596c] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/25/2022]
Abstract
Deep learning based methods have been widely applied to predict various kinds of molecular properties in the pharmaceutical industry with increasingly more success. In this study, we propose two novel models for aqueous solubility predictions, based on the Multilevel Graph Convolutional Network (MGCN) and SchNet architectures, respectively. The advantage of the MGCN lies in the fact that it could extract the graph features of the target molecules directly from the (3D) structural information; therefore, it doesn't need to rely on a lot of intra-molecular descriptors to learn the features, which are of significance for accurate predictions of the molecular properties. The SchNet performs well in modelling the interatomic interactions inside a molecule, and such a deep learning architecture is also capable of extracting structural information and further predicting the related properties. The actual accuracy of these two novel approaches was systematically benchmarked with four different independent datasets. We found that both the MGCN and SchNet models performed well for aqueous solubility predictions. In the future, we believe such promising predictive models will be applicable to enhancing the efficiency of the screening, crystallization and delivery of drug molecules, essentially as a useful tool to promote the development of molecular pharmaceutics.
Collapse
Affiliation(s)
- Peng Gao
- School of Chemistry and Molecular Bioscience, University of Wollongong, NSW 2500, Australia
| | | | | | | |
Collapse
|
12
|
Christiansen MPV, Mortensen HL, Meldgaard SA, Hammer B. Gaussian representation for image recognition and reinforcement learning of atomistic structure. J Chem Phys 2020; 153:044107. [DOI: 10.1063/5.0015571] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Affiliation(s)
| | | | - Søren Ager Meldgaard
- Department of Physics and Astronomy, Aarhus University, DK-8000 Aarhus C, Denmark
| | - Bjørk Hammer
- Department of Physics and Astronomy, Aarhus University, DK-8000 Aarhus C, Denmark
| |
Collapse
|
13
|
Meldgaard SA, Mortensen HL, Jørgensen MS, Hammer B. Structure prediction of surface reconstructions by deep reinforcement learning. JOURNAL OF PHYSICS. CONDENSED MATTER : AN INSTITUTE OF PHYSICS JOURNAL 2020; 32:404005. [PMID: 32434171 DOI: 10.1088/1361-648x/ab94f2] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/17/2020] [Accepted: 05/20/2020] [Indexed: 06/11/2023]
Abstract
We demonstrate how image recognition and reinforcement learning combined may be used to determine the atomistic structure of reconstructed crystalline surfaces. A deep neural network represents a reinforcement learning agent that obtains training rewards by interacting with an environment. The environment contains a quantum mechanical potential energy evaluator in the form of a density functional theory program. The agent handles the 3D atomistic structure as a series of stacked 2D images and outputs the next atom type to place and the atomic site to occupy. Agents are seen to require 1000-10 000 single point density functional theory evaluations, to learn by themselves how to build the optimal surface reconstructions of anatase TiO2(001)-(1 × 4) and rutile SnO2(110)-(4 × 1).
Collapse
Affiliation(s)
- Søren A Meldgaard
- Department of Physics and Astronomy, Aarhus University, DK-8000 Aarhus C, Denmark
| | - Henrik L Mortensen
- Department of Physics and Astronomy, Aarhus University, DK-8000 Aarhus C, Denmark
| | - Mathias S Jørgensen
- Department of Physics and Astronomy, Aarhus University, DK-8000 Aarhus C, Denmark
| | - Bjørk Hammer
- Department of Physics and Astronomy, Aarhus University, DK-8000 Aarhus C, Denmark
| |
Collapse
|
14
|
Gao P, Zhang J, Peng Q, Zhang J, Glezakou VA. General Protocol for the Accurate Prediction of Molecular 13C/1H NMR Chemical Shifts via Machine Learning Augmented DFT. J Chem Inf Model 2020; 60:3746-3754. [DOI: 10.1021/acs.jcim.0c00388] [Citation(s) in RCA: 25] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Peng Gao
- School of Chemistry and Molecular Bioscience, University of Wollongong, Wollongong, NSW 2500, Australia
| | - Jun Zhang
- Physical Sciences Division, Pacific Northwest National Laboratory (PNNL), Richland, Washington 99352, United States
| | - Qian Peng
- State Key Laboratory of Elemento-Organic Chemistry, College of Chemistry, Nankai University, Tianjin 300071, China
| | - Jie Zhang
- Centre of Chemistry and Chemical Biology, Guangzhou Regenerative Medicine and Health-Guangdong Laboratory, Science Park, Guangzhou 510530, China
| | - Vassiliki-Alexandra Glezakou
- Physical Sciences Division, Pacific Northwest National Laboratory (PNNL), Richland, Washington 99352, United States
| |
Collapse
|
15
|
Meldgaard SA, Kolsbjerg EL, Hammer B. Machine learning enhanced global optimization by clustering local environments to enable bundled atomic energies. J Chem Phys 2018; 149:134104. [DOI: 10.1063/1.5048290] [Citation(s) in RCA: 30] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Affiliation(s)
- Søren A. Meldgaard
- Department of Physics and Astronomy and Interdisciplinary Nanoscience Center (iNANO), Aarhus University, 8000 Aarhus, Denmark
| | - Esben L. Kolsbjerg
- Department of Physics and Astronomy and Interdisciplinary Nanoscience Center (iNANO), Aarhus University, 8000 Aarhus, Denmark
| | - Bjørk Hammer
- Department of Physics and Astronomy and Interdisciplinary Nanoscience Center (iNANO), Aarhus University, 8000 Aarhus, Denmark
| |
Collapse
|
16
|
Rupp M, von Lilienfeld OA, Burke K. Guest Editorial: Special Topic on Data-Enabled Theoretical Chemistry. J Chem Phys 2018; 148:241401. [DOI: 10.1063/1.5043213] [Citation(s) in RCA: 62] [Impact Index Per Article: 10.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/17/2023] Open
Affiliation(s)
- Matthias Rupp
- Fritz Haber Institute of the Max Planck Society, Faradayweg 4-6, 14195 Berlin, Germany
| | - O. Anatole von Lilienfeld
- Department of Chemistry, Institute of Physical Chemistry and National Center for Computational Design and Discovery of Novel Materials, University of Basel, 4056 Basel, Switzerland
| | - Kieron Burke
- Departments of Chemistry and Physics, University of California, Irvine, California 92697, USA
| |
Collapse
|