1
|
Wang G, Wang C, Zhang X, Li Z, Zhou J, Sun Z. Machine learning interatomic potential: Bridge the gap between small-scale models and realistic device-scale simulations. iScience 2024; 27:109673. [PMID: 38646181 PMCID: PMC11033164 DOI: 10.1016/j.isci.2024.109673] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/23/2024] Open
Abstract
Machine learning interatomic potential (MLIP) overcomes the challenges of high computational costs in density-functional theory and the relatively low accuracy in classical large-scale molecular dynamics, facilitating more efficient and precise simulations in materials research and design. In this review, the current state of the four essential stages of MLIP is discussed, including data generation methods, material structure descriptors, six unique machine learning algorithms, and available software. Furthermore, the applications of MLIP in various fields are investigated, notably in phase-change memory materials, structure searching, material properties predicting, and the pre-trained universal models. Eventually, the future perspectives, consisting of standard datasets, transferability, generalization, and trade-off between accuracy and complexity in MLIPs, are reported.
Collapse
Affiliation(s)
- Guanjie Wang
- School of Materials Science and Engineering, Beihang University, Beijing 100191, China
- School of Integrated Circuit Science and Engineering, Beihang University, Beijing 100191, China
| | - Changrui Wang
- School of Materials Science and Engineering, Beihang University, Beijing 100191, China
| | - Xuanguang Zhang
- School of Materials Science and Engineering, Beihang University, Beijing 100191, China
| | - Zefeng Li
- School of Materials Science and Engineering, Beihang University, Beijing 100191, China
| | - Jian Zhou
- School of Materials Science and Engineering, Beihang University, Beijing 100191, China
| | - Zhimei Sun
- School of Materials Science and Engineering, Beihang University, Beijing 100191, China
| |
Collapse
|
2
|
Yan Z, Wei D, Li X, Chung LW. Accelerating reliable multiscale quantum refinement of protein-drug systems enabled by machine learning. Nat Commun 2024; 15:4181. [PMID: 38755151 PMCID: PMC11099068 DOI: 10.1038/s41467-024-48453-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2023] [Accepted: 04/24/2024] [Indexed: 05/18/2024] Open
Abstract
Biomacromolecule structures are essential for drug development and biocatalysis. Quantum refinement (QR) methods, which employ reliable quantum mechanics (QM) methods in crystallographic refinement, showed promise in improving the structural quality or even correcting the structure of biomacromolecules. However, vast computational costs and complex quantum mechanics/molecular mechanics (QM/MM) setups limit QR applications. Here we incorporate robust machine learning potentials (MLPs) in multiscale ONIOM(QM:MM) schemes to describe the core parts (e.g., drugs/inhibitors), replacing the expensive QM method. Additionally, two levels of MLPs are combined for the first time to overcome MLP limitations. Our unique MLPs+ONIOM-based QR methods achieve QM-level accuracy with significantly higher efficiency. Furthermore, our refinements provide computational evidence for the existence of bonded and nonbonded forms of the Food and Drug Administration (FDA)-approved drug nirmatrelvir in one SARS-CoV-2 main protease structure. This study highlights that powerful MLPs accelerate QRs for reliable protein-drug complexes, promote broader QR applications and provide more atomistic insights into drug development.
Collapse
Affiliation(s)
- Zeyin Yan
- Shenzhen Grubbs Institute, Department of Chemistry and Guangdong Provincial Key Laboratory of Catalysis, Southern University of Science and Technology, Shenzhen, 518055, China
| | - Dacong Wei
- Shenzhen Grubbs Institute, Department of Chemistry and Guangdong Provincial Key Laboratory of Catalysis, Southern University of Science and Technology, Shenzhen, 518055, China
| | - Xin Li
- Shenzhen Grubbs Institute, Department of Chemistry and Guangdong Provincial Key Laboratory of Catalysis, Southern University of Science and Technology, Shenzhen, 518055, China
| | - Lung Wa Chung
- Shenzhen Grubbs Institute, Department of Chemistry and Guangdong Provincial Key Laboratory of Catalysis, Southern University of Science and Technology, Shenzhen, 518055, China.
| |
Collapse
|
3
|
Kirkland JK, Kumawat J, Shaban Tameh M, Tolman T, Lambert AC, Lief GR, Yang Q, Ess DH. Machine Learning Models for Predicting Zirconocene Properties and Barriers. J Chem Inf Model 2024; 64:775-784. [PMID: 38259142 DOI: 10.1021/acs.jcim.3c01575] [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: 01/24/2024]
Abstract
Zr metallocenes have significant potential to be highly tunable polyethylene catalysts through modification of the aromatic ligand framework. Here we report the development of multiple machine learning models using a large library (>700 systems) of DFT-calculated zirconocene properties and barriers for ethylene polymerization. We show that very accurate machine learning models are possible for HOMO-LUMO gaps of precatalysts but the performance significantly depends on the machine learning algorithm and type of featurization, such as fingerprints, Coulomb matrices, smooth overlap of atomic positions, or persistence images. Surprisingly, the description of the bonding hapticity, the number of direct connections between Zr and the ligand aromatic carbons, only has a moderate influence on the performance of most models. Despite robust models for HOMO-LUMO gaps, these types of machine learning models based on structure connectivity type features perform poorly in predicting ethylene migratory insertion barrier heights. Therefore, we developed several relatively robust and accurate machine learning models for barrier heights that are based on quantum-chemical descriptors (QCDs). The quantitative accuracy of these models depends on which potential energy surface structure QCDs were harvested from. This revealed a Hammett-type principle to naturally emerge showing that QCDs from the π-coordination complexes provide much better descriptions of the transition states than other potential-energy structures. Feature importance analysis of the QCDs provides several fundamental principles that influence zirconocene catalyst reactivity.
Collapse
Affiliation(s)
- Justin K Kirkland
- Department of Chemistry and Biochemistry, Brigham Young University, Provo, Utah 84604, United States
| | - Jugal Kumawat
- Department of Chemistry and Biochemistry, Brigham Young University, Provo, Utah 84604, United States
| | - Maliheh Shaban Tameh
- Department of Chemistry and Biochemistry, Brigham Young University, Provo, Utah 84604, United States
| | - Tyson Tolman
- Department of Chemistry and Biochemistry, Brigham Young University, Provo, Utah 84604, United States
| | - Allison C Lambert
- Department of Chemistry and Biochemistry, Brigham Young University, Provo, Utah 84604, United States
| | - Graham R Lief
- Research and Technology, Chevron Phillips Chemical Company, Highways 60 & 123, Bartlesville, Oklahoma 74003, United States
| | - Qing Yang
- Research and Technology, Chevron Phillips Chemical Company, Highways 60 & 123, Bartlesville, Oklahoma 74003, United States
| | - Daniel H Ess
- Department of Chemistry and Biochemistry, Brigham Young University, Provo, Utah 84604, United States
| |
Collapse
|
4
|
Maier JC, Wang CI, Jackson NE. Distilling coarse-grained representations of molecular electronic structure with continuously gated message passing. J Chem Phys 2024; 160:024109. [PMID: 38193551 DOI: 10.1063/5.0179253] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2023] [Accepted: 12/14/2023] [Indexed: 01/10/2024] Open
Abstract
Bottom-up methods for coarse-grained (CG) molecular modeling are critically needed to establish rigorous links between atomistic reference data and reduced molecular representations. For a target molecule, the ideal reduced CG representation is a function of both the conformational ensemble of the system and the target physical observable(s) to be reproduced at the CG resolution. However, there is an absence of algorithms for selecting CG representations of molecules from which complex properties, including molecular electronic structure, can be accurately modeled. We introduce continuously gated message passing (CGMP), a graph neural network (GNN) method for atomically decomposing molecular electronic structure sampled over conformational ensembles. CGMP integrates 3D-invariant GNNs and a novel gated message passing system to continuously reduce the atomic degrees of freedom accessible for electronic predictions, resulting in a one-shot importance ranking of atoms contributing to a target molecular property. Moreover, CGMP provides the first approach by which to quantify the degeneracy of "good" CG representations conditioned on specific prediction targets, facilitating the development of more transferable CG representations. We further show how CGMP can be used to highlight multiatom correlations, illuminating a path to developing CG electronic Hamiltonians in terms of interpretable collective variables for arbitrarily complex molecules.
Collapse
Affiliation(s)
- J Charlie Maier
- Department of Physics, University of Illinois at Urbana-Champaign, Urbana, Illinois 61801, USA
| | - Chun-I Wang
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, Illinois 61801, USA
| | - Nicholas E Jackson
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, Illinois 61801, USA
| |
Collapse
|
5
|
Guzman-Pando A, Ramirez-Alonso G, Arzate-Quintana C, Camarillo-Cisneros J. Deep learning algorithms applied to computational chemistry. Mol Divers 2023:10.1007/s11030-023-10771-y. [PMID: 38151697 DOI: 10.1007/s11030-023-10771-y] [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: 09/20/2023] [Accepted: 11/14/2023] [Indexed: 12/29/2023]
Abstract
Recently, there has been a significant increase in the use of deep learning techniques in the molecular sciences, which have shown high performance on datasets and the ability to generalize across data. However, no model has achieved perfect performance in solving all problems, and the pros and cons of each approach remain unclear to those new to the field. Therefore, this paper aims to review deep learning algorithms that have been applied to solve molecular challenges in computational chemistry. We proposed a comprehensive categorization that encompasses two primary approaches; conventional deep learning and geometric deep learning models. This classification takes into account the distinct techniques employed by the algorithms within each approach. We present an up-to-date analysis of these algorithms, emphasizing their key features and open issues. This includes details of input descriptors, datasets used, open-source code availability, task solutions, and actual research applications, focusing on general applications rather than specific ones such as drug discovery. Furthermore, our report discusses trends and future directions in molecular algorithm design, including the input descriptors used for each deep learning model, GPU usage, training and forward processing time, model parameters, the most commonly used datasets, libraries, and optimization schemes. This information aids in identifying the most suitable algorithms for a given task. It also serves as a reference for the datasets and input data frequently used for each algorithm technique. In addition, it provides insights into the benefits and open issues of each technique, and supports the development of novel computational chemistry systems.
Collapse
Affiliation(s)
- Abimael Guzman-Pando
- Computational Chemistry Physics Laboratory, Facultad de Medicina y Ciencias Biomédicas, Universidad Autónoma de Chihuahua, Campus II, 31125, Chihuahua, Mexico
| | - Graciela Ramirez-Alonso
- Faculty of Engineering, Universidad Autónoma de Chihuahua, Campus II, 31125, Chihuahua, Mexico
| | - Carlos Arzate-Quintana
- Computational Chemistry Physics Laboratory, Facultad de Medicina y Ciencias Biomédicas, Universidad Autónoma de Chihuahua, Campus II, 31125, Chihuahua, Mexico
| | - Javier Camarillo-Cisneros
- Computational Chemistry Physics Laboratory, Facultad de Medicina y Ciencias Biomédicas, Universidad Autónoma de Chihuahua, Campus II, 31125, Chihuahua, Mexico.
| |
Collapse
|
6
|
Li W, Wang G, Ma J. Deep learning for complex chemical systems. Natl Sci Rev 2023; 10:nwad335. [PMID: 38274240 PMCID: PMC10808951 DOI: 10.1093/nsr/nwad335] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2023] [Revised: 10/24/2023] [Accepted: 10/31/2023] [Indexed: 01/27/2024] Open
Abstract
Deep learning forms a bridge between the local features of molecular fragments/localized orbitals and the global properties of complex systems, enabling multi-scale simulations of complex chemical systems and reaction processes.
Collapse
Affiliation(s)
- Wei Li
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering, Nanjing University, China
| | - Guoqiang Wang
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering, Nanjing University, China
| | - Jing Ma
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering, Nanjing University, China
| |
Collapse
|
7
|
Borislavov L, Nedyalkova M, Tadjer A, Aydemir O, Romanova J. Machine Learning-Based Screening for Potential Singlet Fission Chromophores: The Challenge of Imbalanced Data Sets. J Phys Chem Lett 2023; 14:10103-10112. [PMID: 37921710 PMCID: PMC10659028 DOI: 10.1021/acs.jpclett.3c02365] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2023] [Revised: 10/13/2023] [Accepted: 10/18/2023] [Indexed: 11/04/2023]
Abstract
Excitation with one photon of a singlet fission (SF) material generates two triplet excitons, thus doubling the solar cell efficiency. Therefore, the SF molecules are regarded as new generation organic photovoltaics, but it is hard to identify them. Recently, it was demonstrated that molecules of low-to-intermediate diradical character (DRC) are potential SF chromophores. This prompts a low-cost strategy for finding new SF candidates by computational high-throughput workflows. We propose a machine learning aided screening for SF entrants based on their DRC. Our data set comprises 469 784 compounds extracted from the PubChem database, structurally rich but inherently imbalanced regarding DRC values. We developed well performing classification models that can retrieve potential SF chromophores. The latter (∼4%) were analyzed by K-means clustering to reveal qualitative structure-property relationships and to extract strategies for molecular design. The developed screening procedure and data set can be easily adapted for applications of diradicaloids in photonics and spintronics.
Collapse
Affiliation(s)
- Lyuben Borislavov
- Institute
of General and Inorganic Chemistry, Bulgarian
Academy of Sciences, 11 Akad. Georgi Bonchev str., 1113 Sofia, Bulgaria
| | - Miroslava Nedyalkova
- Chemistry
Department, University of Fribourg, Chemin du Musée 9, 1700 Fribourg, Switzerland
- Faculty
of Chemistry and Pharmacy, Sofia University, 1 James Bourchier Blvd., 1164 Sofia, Bulgaria
| | - Alia Tadjer
- Faculty
of Chemistry and Pharmacy, Sofia University, 1 James Bourchier Blvd., 1164 Sofia, Bulgaria
| | - Onder Aydemir
- Faculty
of Engineering, Department of Electrical & Electronics Engineering, Karadeniz Technical University, 61080 Trabzon, Turkey
| | - Julia Romanova
- Faculty
of Chemistry and Pharmacy, Sofia University, 1 James Bourchier Blvd., 1164 Sofia, Bulgaria
| |
Collapse
|
8
|
Nandi S, Vegge T, Bhowmik A. MultiXC-QM9: Large dataset of molecular and reaction energies from multi-level quantum chemical methods. Sci Data 2023; 10:783. [PMID: 37938558 PMCID: PMC10632468 DOI: 10.1038/s41597-023-02690-2] [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: 06/27/2023] [Accepted: 10/25/2023] [Indexed: 11/09/2023] Open
Abstract
Well curated extensive datasets have helped spur intense molecular machine learning (ML) method development activities over the last few years, encouraging nonchemists to be part of the effort as well. QM9 dataset is one of the benchmark databases for small molecules with molecular energies based on B3LYP functional. G4MP2 based energies of these molecules were published later. To enable a wide variety of ML tasks like transfer learning, delta learning, multitask learning, etc. with QM9 molecules, in this article, we introduce a new dataset with QM9 molecule energies estimated with 76 different DFT functionals and three different basis sets (228 energy numbers for each molecule). We additionally enumerated all possible A ↔ B monomolecular interconversions within the QM9 dataset and provided the reaction energies based on these 76 functionals, and basis sets. Lastly, we also provide the bond changes for all the 162 million reactions with the dataset to enable structure- and bond-based reaction energy prediction tools based on ML.
Collapse
Affiliation(s)
- Surajit Nandi
- Department of Energy Conversion and Storage, Technical University of Denmark, Anker Engelunds Vej 301, 2800 Kongens Lyngby, Copenhagen, Denmark
| | - Tejs Vegge
- Department of Energy Conversion and Storage, Technical University of Denmark, Anker Engelunds Vej 301, 2800 Kongens Lyngby, Copenhagen, Denmark
| | - Arghya Bhowmik
- Department of Energy Conversion and Storage, Technical University of Denmark, Anker Engelunds Vej 301, 2800 Kongens Lyngby, Copenhagen, Denmark.
| |
Collapse
|
9
|
Hagg A, Kirschner KN. Open-Source Machine Learning in Computational Chemistry. J Chem Inf Model 2023; 63:4505-4532. [PMID: 37466636 PMCID: PMC10430767 DOI: 10.1021/acs.jcim.3c00643] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2023] [Indexed: 07/20/2023]
Abstract
The field of computational chemistry has seen a significant increase in the integration of machine learning concepts and algorithms. In this Perspective, we surveyed 179 open-source software projects, with corresponding peer-reviewed papers published within the last 5 years, to better understand the topics within the field being investigated by machine learning approaches. For each project, we provide a short description, the link to the code, the accompanying license type, and whether the training data and resulting models are made publicly available. Based on those deposited in GitHub repositories, the most popular employed Python libraries are identified. We hope that this survey will serve as a resource to learn about machine learning or specific architectures thereof by identifying accessible codes with accompanying papers on a topic basis. To this end, we also include computational chemistry open-source software for generating training data and fundamental Python libraries for machine learning. Based on our observations and considering the three pillars of collaborative machine learning work, open data, open source (code), and open models, we provide some suggestions to the community.
Collapse
Affiliation(s)
- Alexander Hagg
- Institute
of Technology, Resource and Energy-Efficient Engineering (TREE), University of Applied Sciences Bonn-Rhein-Sieg, 53757 Sankt Augustin, Germany
- Department
of Electrical Engineering, Mechanical Engineering and Technical Journalism, University of Applied Sciences Bonn-Rhein-Sieg, 53757 Sankt Augustin, Germany
| | - Karl N. Kirschner
- Institute
of Technology, Resource and Energy-Efficient Engineering (TREE), University of Applied Sciences Bonn-Rhein-Sieg, 53757 Sankt Augustin, Germany
- Department
of Computer Science, University of Applied
Sciences Bonn-Rhein-Sieg, 53757 Sankt Augustin, Germany
| |
Collapse
|
10
|
Morgan JP, Paiement A, Klinke C. Domain-informed graph neural networks: A quantum chemistry case study. Neural Netw 2023; 165:938-952. [PMID: 37453397 DOI: 10.1016/j.neunet.2023.06.030] [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: 08/24/2022] [Revised: 05/05/2023] [Accepted: 06/24/2023] [Indexed: 07/18/2023]
Abstract
We explore different strategies to integrate prior domain knowledge into the design of graph neural networks (GNN). Our study is supported by a use-case of estimating the potential energy of chemical systems (molecules and crystals) represented as graphs. We integrate two elements of domain knowledge into the design of the GNN to constrain and regularise its learning, towards higher accuracy and generalisation. First, knowledge on the existence of different types of relations/graph edges (e.g. chemical bonds in our case study) between nodes of the graph is used to modulate their interactions. We formulate and compare two strategies, namely specialised message production and specialised update of internal states. Second, knowledge of the relevance of some physical quantities is used to constrain the learnt features towards a higher physical relevance using a simple multi-task learning (MTL) paradigm. We explore the potential of MTL to better capture the underlying mechanisms behind the studied phenomenon. We demonstrate the general applicability of our two knowledge integrations by applying them to three architectures that rely on different mechanisms to propagate information between nodes and to update node states. Our implementations are made publicly available. To support these experiments, we release three new datasets of out-of-equilibrium molecules and crystals of various complexities.
Collapse
Affiliation(s)
- Jay Paul Morgan
- Université de Toulon, Aix Marseille Univ, CNRS, LIS, Marseille, France; Department of Computer Science, Swansea University, Swansea, SA2 8PP, United Kingdom.
| | - Adeline Paiement
- Université de Toulon, Aix Marseille Univ, CNRS, LIS, Marseille, France; Department of Computer Science, Swansea University, Swansea, SA2 8PP, United Kingdom.
| | - Christian Klinke
- Institute of Physics, University of Rostock, Rostock, 18059, Germany; Department "Life, Light & Matter", University of Rostock, Rostock, 18059, Germany; Department of Chemistry, Swansea University, Swansea, SA2 8PP, United Kingdom.
| |
Collapse
|
11
|
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: 2] [Impact Index Per Article: 2.0] [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
|
12
|
Mou LH, Han T, Smith PES, Sharman E, Jiang J. Machine Learning Descriptors for Data-Driven Catalysis Study. ADVANCED SCIENCE (WEINHEIM, BADEN-WURTTEMBERG, GERMANY) 2023:e2301020. [PMID: 37191279 PMCID: PMC10401178 DOI: 10.1002/advs.202301020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/14/2023] [Revised: 04/07/2023] [Indexed: 05/17/2023]
Abstract
Traditional trial-and-error experiments and theoretical simulations have difficulty optimizing catalytic processes and developing new, better-performing catalysts. Machine learning (ML) provides a promising approach for accelerating catalysis research due to its powerful learning and predictive abilities. The selection of appropriate input features (descriptors) plays a decisive role in improving the predictive accuracy of ML models and uncovering the key factors that influence catalytic activity and selectivity. This review introduces tactics for the utilization and extraction of catalytic descriptors in ML-assisted experimental and theoretical research. In addition to the effectiveness and advantages of various descriptors, their limitations are also discussed. Highlighted are both 1) newly developed spectral descriptors for catalytic performance prediction and 2) a novel research paradigm combining computational and experimental ML models through suitable intermediate descriptors. Current challenges and future perspectives on the application of descriptors and ML techniques to catalysis are also presented.
Collapse
Affiliation(s)
- Li-Hui Mou
- Hefei National Research Center for Physical Sciences at the Microscale, School of Chemistry and Materials Science, University of Science and Technology of China, Hefei, Anhui, 230026, China
| | - TianTian Han
- Hefei JiShu Quantum Technology Co. Ltd., Hefei, 230026, China
| | - Pieter E S Smith
- YDS Pharmatech, ETEC, 1220 Washington Ave., Albany, NY, 12203, USA
| | - Edward Sharman
- Department of Neurology, University of California, Irvine, CA, 92697, USA
| | - Jun Jiang
- Hefei National Research Center for Physical Sciences at the Microscale, School of Chemistry and Materials Science, University of Science and Technology of China, Hefei, Anhui, 230026, China
| |
Collapse
|
13
|
Physical pooling functions in graph neural networks for molecular property prediction. Comput Chem Eng 2023. [DOI: 10.1016/j.compchemeng.2023.108202] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
|
14
|
SuHAN: Substructural hierarchical attention network for molecular representation. J Mol Graph Model 2023; 119:108401. [PMID: 36584590 DOI: 10.1016/j.jmgm.2022.108401] [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: 11/03/2022] [Revised: 12/16/2022] [Accepted: 12/23/2022] [Indexed: 12/26/2022]
Abstract
Recently, molecular representation and property exploration, with the combination of neural network, play a critical role in the field of drug design and discovery for assisting in drug related research. However, previous research in molecular representation relies heavily on artificial extraction of features based on biological experiments which may result in a manually introduced noise of molecular information with high cost in time and money. In this paper, a novel method named Substructural Hierarchical Attention Network (SuHAN) is proposed to discover inherent characteristics of molecules for representation learning. Specifically, SuHAN is composed of the cascaded layer: atom-level layer and substructure-level layer. Molecule in the SMILES format is divided into several substructural fragments by predefined partition rules, and then they are fed into atom-level layer and substructure-level layer successively to obtain feature representation from different perspective: atomic view and substructural view. In this way, the prominent structural features that may be omitted in global extraction are excavated from a fine-grained viewpoint and fused to reconstruct representative pattern in an overall view. Experiments on biophysics and physiology datasets demonstrate that our model is competitive with a significant improvement of both accuracy and stability in performance. We confirmed that the substructural segments and progressive hierarchical networks lead to an effective molecular representation for downstream tasks. These results provide a novel perspective about reconstructing overall pattern through local prominent structure.
Collapse
|
15
|
Wang G, Wu X, Xin B, Gu X, Wang G, Zhang Y, Zhao J, Cheng X, Chen C, Ma J. Machine Learning in Unmanned Systems for Chemical Synthesis. Molecules 2023; 28:2232. [PMID: 36903478 PMCID: PMC10004533 DOI: 10.3390/molecules28052232] [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: 01/15/2023] [Revised: 02/05/2023] [Accepted: 02/23/2023] [Indexed: 03/04/2023] Open
Abstract
Chemical synthesis is state-of-the-art, and, therefore, it is generally based on chemical intuition or experience of researchers. The upgraded paradigm that incorporates automation technology and machine learning (ML) algorithms has recently been merged into almost every subdiscipline of chemical science, from material discovery to catalyst/reaction design to synthetic route planning, which often takes the form of unmanned systems. The ML algorithms and their application scenarios in unmanned systems for chemical synthesis were presented. The prospects for strengthening the connection between reaction pathway exploration and the existing automatic reaction platform and solutions for improving autonomation through information extraction, robots, computer vision, and intelligent scheduling were proposed.
Collapse
Affiliation(s)
- Guoqiang Wang
- Key Laboratory of Mesoscopic Chemistry of MOE, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, China
| | - Xuefei Wu
- Department of Control Science and Intelligent Engineering, School of Management and Engineering, Nanjing University, Nanjing 210093, China
| | - Bo Xin
- Department of Control Science and Intelligent Engineering, School of Management and Engineering, Nanjing University, Nanjing 210093, China
| | - Xu Gu
- Key Laboratory of Mesoscopic Chemistry of MOE, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, China
| | - Gaobo Wang
- Key Laboratory of Mesoscopic Chemistry of MOE, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, China
| | - Yong Zhang
- Key Laboratory of Mesoscopic Chemistry of MOE, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, China
| | - Jiabao Zhao
- Department of Control Science and Intelligent Engineering, School of Management and Engineering, Nanjing University, Nanjing 210093, China
| | - Xu Cheng
- Key Laboratory of Mesoscopic Chemistry of MOE, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, China
- Jiangsu Key Laboratory of Advanced Organic Materials, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, China
| | - Chunlin Chen
- Department of Control Science and Intelligent Engineering, School of Management and Engineering, Nanjing University, Nanjing 210093, China
| | - Jing Ma
- Key Laboratory of Mesoscopic Chemistry of MOE, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, China
- Jiangsu Key Laboratory of Advanced Organic Materials, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, China
| |
Collapse
|
16
|
Zhang S, Xu L, Li S, Oliveira JCA, Li X, Ackermann L, Hong X. Bridging Chemical Knowledge and Machine Learning for Performance Prediction of Organic Synthesis. Chemistry 2023; 29:e202202834. [PMID: 36206170 PMCID: PMC10099903 DOI: 10.1002/chem.202202834] [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: 09/12/2022] [Indexed: 11/29/2022]
Abstract
Recent years have witnessed a boom of machine learning (ML) applications in chemistry, which reveals the potential of data-driven prediction of synthesis performance. Digitalization and ML modelling are the key strategies to fully exploit the unique potential within the synergistic interplay between experimental data and the robust prediction of performance and selectivity. A series of exciting studies have demonstrated the importance of chemical knowledge implementation in ML, which improves the model's capability for making predictions that are challenging and often go beyond the abilities of human beings. This Minireview summarizes the cutting-edge embedding techniques and model designs in synthetic performance prediction, elaborating how chemical knowledge can be incorporated into machine learning until June 2022. By merging organic synthesis tactics and chemical informatics, we hope this Review can provide a guide map and intrigue chemists to revisit the digitalization and computerization of organic chemistry principles.
Collapse
Affiliation(s)
- Shuo‐Qing Zhang
- Center of Chemistry for Frontier TechnologiesDepartment of ChemistryState Key Laboratory of Clean Energy UtilizationZhejiang University38 Zheda RoadHangzhou310027P. R. China
| | - Li‐Cheng Xu
- Center of Chemistry for Frontier TechnologiesDepartment of ChemistryState Key Laboratory of Clean Energy UtilizationZhejiang University38 Zheda RoadHangzhou310027P. R. China
| | - Shu‐Wen Li
- Center of Chemistry for Frontier TechnologiesDepartment of ChemistryState Key Laboratory of Clean Energy UtilizationZhejiang University38 Zheda RoadHangzhou310027P. R. China
| | - João C. A. Oliveira
- Institut für Organische und Biomolekulare ChemieWöhler Research Institute for Sustainable Chemistry (WISCh)Georg-August-UniversitätTammannstraße 237077GöttingenGermany
| | - Xin Li
- Center of Chemistry for Frontier TechnologiesDepartment of ChemistryState Key Laboratory of Clean Energy UtilizationZhejiang University38 Zheda RoadHangzhou310027P. R. China
| | - Lutz Ackermann
- Institut für Organische und Biomolekulare ChemieWöhler Research Institute for Sustainable Chemistry (WISCh)Georg-August-UniversitätTammannstraße 237077GöttingenGermany
| | - Xin Hong
- Center of Chemistry for Frontier TechnologiesDepartment of ChemistryState Key Laboratory of Clean Energy UtilizationZhejiang University38 Zheda RoadHangzhou310027P. R. China
- Beijing National Laboratory for Molecular SciencesZhongguancun North First Street No. 2Beijing100190P. R. China
- Key Laboratory of Precise Synthesis ofFunctional Molecules of Zhejiang ProvinceSchool of ScienceWestlake University18 Shilongshan RoadHangzhou310024Zhejiang ProvinceP. R. China
| |
Collapse
|
17
|
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
|
18
|
Jia Q, Ni Y, Liu Z, Gu X, Cui Z, Fan M, Zhu Q, Wang Y, Ma J. Fast Prediction of Lipophilicity of Organofluorine Molecules: Deep Learning-Derived Polarity Characters and Experimental Tests. J Chem Inf Model 2022; 62:4928-4936. [PMID: 36223527 DOI: 10.1021/acs.jcim.2c01201] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Abstract
Fast and accurate estimation of lipophilicity for organofluorine molecules is in great demand for accelerating drug and materials discovery. A lipophilicity data set of organofluorine molecules (OFL data set), containing 1907 samples, is constructed through density functional theory (DFT) calculations and experimental measurements. An efficient and interpretable model, called PoLogP, is developed to predict the n-octanol/water partition coefficient, log Po/w, of organofluorine molecules on the basis of the descriptors of polarization, which is a combination of polarity descriptors, including the molecular polarity index and molecular polarizability (α), and hydrogen bond (HBs) index, consisting of the number of donors (NHBD) and acceptors (NHBA and NHB-FA). The present PoLogP with a combination of polarity descriptors is demonstrated to perform better than the dipole moment (μ) alone for the F-contained molecules. With the aid of a multilevel attention graph convolutional neural network model, the fast generation of polarity descriptors of organofluorine molecules could be achieved with the DFT accuracy based only on a topological molecular graph structure. The performance of PoLogP is further validated on synthesized organofluorine molecules and 2626 non-fluorinated molecules with satisfactory accuracy, highlighting the potential usage of PoLogP in high-throughput screening of the functional molecules with the desired solubility in various solvent media.
Collapse
Affiliation(s)
- Qingqing Jia
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, P. R. China
| | - Yifan Ni
- Jiangsu Key Laboratory of Advanced Organic Materials, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, P. R. China
| | - Ziteng Liu
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, P. R. China
| | - Xu Gu
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, P. R. China
| | - Ziyi Cui
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, P. R. China
| | - Mengting Fan
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, P. R. China
| | - Qiang Zhu
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, P. R. China
| | - Yi Wang
- Jiangsu Key Laboratory of Advanced Organic Materials, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, P. R. China
| | - Jing Ma
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, P. R. China.,Jiangsu Key Laboratory of Advanced Organic Materials, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing 210023, P. R. China
| |
Collapse
|
19
|
Deep learning methods for molecular representation and property prediction. Drug Discov Today 2022; 27:103373. [PMID: 36167282 DOI: 10.1016/j.drudis.2022.103373] [Citation(s) in RCA: 35] [Impact Index Per Article: 17.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2022] [Revised: 08/22/2022] [Accepted: 09/21/2022] [Indexed: 01/11/2023]
Abstract
With advances in artificial intelligence (AI) methods, computer-aided drug design (CADD) has developed rapidly in recent years. Effective molecular representation and accurate property prediction are crucial tasks in CADD workflows. In this review, we summarize contemporary applications of deep learning (DL) methods for molecular representation and property prediction. We categorize DL methods according to the format of molecular data (1D, 2D, and 3D). In addition, we discuss some common DL models, such as ensemble learning and transfer learning, and analyze the interpretability methods for these models. We also highlight the challenges and opportunities of DL methods for molecular representation and property prediction.
Collapse
|
20
|
Shmilovich K, Willmott D, Batalov I, Kornbluth M, Mailoa J, Kolter JZ. Orbital Mixer: Using Atomic Orbital Features for Basis-Dependent Prediction of Molecular Wavefunctions. J Chem Theory Comput 2022; 18:6021-6030. [PMID: 36122312 DOI: 10.1021/acs.jctc.2c00555] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
Leveraging ab initio data at scale has enabled the development of machine learning models capable of extremely accurate and fast molecular property prediction. A central paradigm of many previous studies focuses on generating predictions for only a fixed set of properties. Recent lines of research instead aim to explicitly learn the electronic structure via molecular wavefunctions, from which other quantum chemical properties can be directly derived. While previous methods generate predictions as a function of only the atomic configuration, in this work we present an alternate approach that directly purposes basis-dependent information to predict molecular electronic structure. Our model, Orbital Mixer, is composed entirely of multi-layer perceptrons (MLPs) using MLP-Mixer layers within a simple, intuitive, and scalable architecture that achieves competitive Hamiltonian and molecular orbital energy and coefficient prediction accuracies compared to the state-of-the-art.
Collapse
Affiliation(s)
- Kirill Shmilovich
- Pritzker School of Molecular Engineering, University of Chicago, Chicago, Illinois 60637, United States
| | - Devin Willmott
- Bosch Center for Artificial Intelligence, Pittsburgh, Pennsylvania 15222, United States
| | - Ivan Batalov
- Bosch Center for Artificial Intelligence, Pittsburgh, Pennsylvania 15222, United States
| | - Mordechai Kornbluth
- Bosch Research and Technology Center, Cambridge, Massachusetts 02139, United States
| | - Jonathan Mailoa
- Tencent Quantum Laboratory, Shenzhen, Guangdong 518057, China
| | - J Zico Kolter
- Bosch Center for Artificial Intelligence, Pittsburgh, Pennsylvania 15222, United States.,Carnegie Mellon University, Pittsburgh, Pennsylvania 15222, United States
| |
Collapse
|
21
|
Qiao Z, Christensen AS, Welborn M, Manby FR, Anandkumar A, Miller TF. Informing geometric deep learning with electronic interactions to accelerate quantum chemistry. Proc Natl Acad Sci U S A 2022; 119:e2205221119. [PMID: 35901215 PMCID: PMC9351474 DOI: 10.1073/pnas.2205221119] [Citation(s) in RCA: 23] [Impact Index Per Article: 11.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2022] [Accepted: 06/06/2022] [Indexed: 01/30/2023] Open
Abstract
Predicting electronic energies, densities, and related chemical properties can facilitate the discovery of novel catalysts, medicines, and battery materials. However, existing machine learning techniques are challenged by the scarcity of training data when exploring unknown chemical spaces. We overcome this barrier by systematically incorporating knowledge of molecular electronic structure into deep learning. By developing a physics-inspired equivariant neural network, we introduce a method to learn molecular representations based on the electronic interactions among atomic orbitals. Our method, OrbNet-Equi, leverages efficient tight-binding simulations and learned mappings to recover high-fidelity physical quantities. OrbNet-Equi accurately models a wide spectrum of target properties while being several orders of magnitude faster than density functional theory. Despite only using training samples collected from readily available small-molecule libraries, OrbNet-Equi outperforms traditional semiempirical and machine learning-based methods on comprehensive downstream benchmarks that encompass diverse main-group chemical processes. Our method also describes interactions in challenging charge-transfer complexes and open-shell systems. We anticipate that the strategy presented here will help to expand opportunities for studies in chemistry and materials science, where the acquisition of experimental or reference training data is costly.
Collapse
Affiliation(s)
- Zhuoran Qiao
- Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, CA 91125
| | | | | | | | - Anima Anandkumar
- Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA 91125
- Nvidia Corporation, Santa Clara, CA 95051
| | - Thomas F. Miller
- Division of Chemistry and Chemical Engineering, California Institute of Technology, Pasadena, CA 91125
- Entos, Inc., Los Angeles, CA 90027
| |
Collapse
|
22
|
Liao K, Dong S, Cheng Z, Li W, Li S. Combined fragment-based machine learning force field with classical force field and its application in the NMR calculations of macromolecules in solutions. Phys Chem Chem Phys 2022; 24:18559-18567. [PMID: 35916054 DOI: 10.1039/d2cp02192g] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
We have developed a combined fragment-based machine learning (ML) force field and molecular mechanics (MM) force field for simulating the structures of macromolecules in solutions, and then compute its NMR chemical shifts with the generalized energy-based fragmentation (GEBF) approach at the level of density functional theory (DFT). In this work, we first construct Gaussian approximation potential based on GEBF subsystems of macromolecules for MD simulations and then a GEBF-based neural network (GEBF-NN) with deep potential model for the studied macromolecule. Then, we develop a GEBF-NN/MM force field for macromolecules in solutions by combining the GEBF-NN force field for the solute molecule and ff14SB force field for solvent molecules. Using the GEBF-NN/MM MD simulation to generate snapshot structures of solute/solvent clusters, we then perform the NMR calculations with the GEBF approach at the DFT level to calculate NMR chemical shifts of the solute molecule. Taking a heptamer of oligopyridine-dicarboxamides in chloroform solution as an example, our results show that the GEBF-NN force field is quite accurate for this heptamer by comparing with the reference DFT results. For this heptamer in chloroform solution, both the GEBF-NN/MM and classical MD simulations could lead to helical structures from the same initial extended structure. The GEBF-DFT NMR results indicate that the GEBF-NN/MM force field could lead to more accurate NMR chemical shifts on hydrogen atoms by comparing with the experimental NMR results. Therefore, the GEBF-NN/MM force field could be employed for predicting more accurate dynamical behaviors than the classical force field for complex systems in solutions.
Collapse
Affiliation(s)
- Kang Liao
- School of Chemistry and Chemical Engineering, Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, Nanjing University, Nanjing, 210023, P. R. China.
| | - Shiyu Dong
- School of Chemistry and Chemical Engineering, Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, Nanjing University, Nanjing, 210023, P. R. China.
| | - Zheng Cheng
- School of Chemistry and Chemical Engineering, Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, Nanjing University, Nanjing, 210023, P. R. China.
| | - Wei Li
- School of Chemistry and Chemical Engineering, Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, Nanjing University, Nanjing, 210023, P. R. China.
| | - Shuhua Li
- School of Chemistry and Chemical Engineering, Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, Nanjing University, Nanjing, 210023, P. R. China.
| |
Collapse
|
23
|
When machine learning meets molecular synthesis. TRENDS IN CHEMISTRY 2022. [DOI: 10.1016/j.trechm.2022.07.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
|
24
|
Roseiro P, Robert V. Environmental effects on the singlet fission phenomenon: a model Hamiltonian-based study. Phys Chem Chem Phys 2022; 24:15945-15950. [PMID: 35730339 DOI: 10.1039/d2cp01632j] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
In the screening of compounds for singlet fission, the relative energies of the constitutive units are decisive to fulfil the thermodynamic rules. From a model Hamiltonian constructed on the local spin states of an active chromophore and its environment, it is suggested that embedding greatly influences the energy differences of the active monomer spin states. Even in the absence of charge transfer, the field generated by a singlet environment produces an increase of the [E(S1) - E(S0)]/[E(T1) - E(S0)] critical ratio by up to 6% as compared to the one of a free chromophore. Besides, variations are observed when the intimate electronic structure of the singlet environment is modified. This propensity towards singlet fission is even more pronounced (10%) when the environment is switched to the triplet state. Finally, the embedding is likely to reverse the spin state ordering in the limit of vanishing atomic orbital overlaps. Despite its simplicity, the model stresses the importance of the environment spin nature in the quest for singlet fission candidates, and more generally in spectroscopy analysis.
Collapse
Affiliation(s)
- Pablo Roseiro
- Laboratoire de Chimie Quantique, UMR 7177 Université de Strasbourg CNRS, 4 rue Blaise Pascal, 67000, Strasbourg, France.
| | - Vincent Robert
- Laboratoire de Chimie Quantique, UMR 7177 Université de Strasbourg CNRS, 4 rue Blaise Pascal, 67000, Strasbourg, France.
| |
Collapse
|
25
|
Kim H, Park M, Lee I, Nam H. BayeshERG: a robust, reliable and interpretable deep learning model for predicting hERG channel blockers. Brief Bioinform 2022; 23:6609519. [PMID: 35709752 DOI: 10.1093/bib/bbac211] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2022] [Revised: 04/19/2022] [Accepted: 05/06/2022] [Indexed: 11/13/2022] Open
Abstract
Unintended inhibition of the human ether-à-go-go-related gene (hERG) ion channel by small molecules leads to severe cardiotoxicity. Thus, hERG channel blockage is a significant concern in the development of new drugs. Several computational models have been developed to predict hERG channel blockage, including deep learning models; however, they lack robustness, reliability and interpretability. Here, we developed a graph-based Bayesian deep learning model for hERG channel blocker prediction, named BayeshERG, which has robust predictive power, high reliability and high resolution of interpretability. First, we applied transfer learning with 300 000 large data in initial pre-training to increase the predictive performance. Second, we implemented a Bayesian neural network with Monte Carlo dropout to calibrate the uncertainty of the prediction. Third, we utilized global multihead attentive pooling to augment the high resolution of structural interpretability for the hERG channel blockers and nonblockers. We conducted both internal and external validations for stringent evaluation; in particular, we benchmarked most of the publicly available hERG channel blocker prediction models. We showed that our proposed model outperformed predictive performance and uncertainty calibration performance. Furthermore, we found that our model learned to focus on the essential substructures of hERG channel blockers via an attention mechanism. Finally, we validated the prediction results of our model by conducting in vitro experiments and confirmed its high validity. In summary, BayeshERG could serve as a versatile tool for discovering hERG channel blockers and helping maximize the possibility of successful drug discovery. The data and source code are available at our GitHub repository (https://github.com/GIST-CSBL/BayeshERG).
Collapse
Affiliation(s)
- Hyunho Kim
- School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Buk-gu, Gwangju, 61005, Republic of Korea
| | - Minsu Park
- School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Buk-gu, Gwangju, 61005, Republic of Korea
| | - Ingoo Lee
- School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Buk-gu, Gwangju, 61005, Republic of Korea
| | - Hojung Nam
- School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology (GIST), Buk-gu, Gwangju, 61005, Republic of Korea
| |
Collapse
|
26
|
Zhang D, Xia S, Zhang Y. Accurate Prediction of Aqueous Free Solvation Energies Using 3D Atomic Feature-Based Graph Neural Network with Transfer Learning. J Chem Inf Model 2022; 62:1840-1848. [PMID: 35422122 PMCID: PMC9038704 DOI: 10.1021/acs.jcim.2c00260] [Citation(s) in RCA: 20] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Abstract
Graph neural network (GNN)-based deep learning (DL) models have been widely implemented to predict the experimental aqueous solvation free energy, while its prediction accuracy has reached a plateau partly due to the scarcity of available experimental data. In order to tackle this challenge, we first build a large and diverse calculated data set Frag20-Aqsol-100K of aqueous solvation free energy with reasonable computational cost and accuracy via electronic structure calculations with continuum solvent models. Then, we develop a novel 3D atomic feature-based GNN model with the principal neighborhood aggregation (PNAConv) and demonstrate that 3D atomic features obtained from molecular mechanics-optimized geometries can significantly improve the learning power of GNN models in predicting calculated solvation free energies. Finally, we employ a transfer learning strategy by pre-training our DL model on Frag20-Aqsol-100K and fine-tuning it on the small experimental data set, and the fine-tuned model A3D-PNAConv-FT achieves the state-of-the-art prediction on the FreeSolv data set with a root-mean-squared error of 0.719 kcal/mol and a mean-absolute error of 0.417 kcal/mol using random data splits. These results indicate that integrating molecular modeling and DL would be a promising strategy to develop robust prediction models in molecular science. The source code and data are accessible at: https://yzhang.hpc.nyu.edu/IMA.
Collapse
Affiliation(s)
- Dongdong Zhang
- Department of Chemistry, New York University, New York, New York 10003, United States
| | - Song Xia
- Department of Chemistry, New York University, New York, New York 10003, United States
| | - Yingkai Zhang
- Department of Chemistry, New York University, New York, New York 10003, United States
- NYU-ECNU Center for Computational Chemistry at NYU Shanghai, Shanghai 200062, China
| |
Collapse
|
27
|
Karandashev K, von Lilienfeld OA. An orbital-based representation for accurate quantum machine learning. J Chem Phys 2022; 156:114101. [DOI: 10.1063/5.0083301] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Abstract
We introduce an electronic structure based representation for quantum machine learning (QML) of electronic properties throughout chemical compound space. The representation is constructed using computationally inexpensive ab initio calculations and explicitly accounts for changes in the electronic structure. We demonstrate the accuracy and flexibility of resulting QML models when applied to property labels, such as total potential energy, HOMO and LUMO energies, ionization potential, and electron affinity, using as datasets for training and testing entries from the QM7b, QM7b-T, QM9, and LIBE libraries. For the latter, we also demonstrate the ability of this approach to account for molecular species of different charge and spin multiplicity, resulting in QML models that infer total potential energies based on geometry, charge, and spin as input.
Collapse
Affiliation(s)
| | - O. Anatole von Lilienfeld
- Faculty of Physics, University of Vienna, Kolingasse 14-16, AT-1090 Wien, Austria
- Department of Chemistry, Institute of Physical Chemistry and National Center for Computational Design and Discovery of Novel Materials (MARVEL), University of Basel, Klingelbergstrasse 80, CH-4056 Basel, Switzerland
| |
Collapse
|
28
|
Yang Z, Zhong W, Lv Q, Chen CYC. Multitask deep learning with dynamic task balancing for quantum mechanical properties prediction. Phys Chem Chem Phys 2022; 24:5383-5393. [PMID: 35169821 DOI: 10.1039/d1cp05172e] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/04/2023]
Abstract
Predicting quantum mechanical properties (QMPs) is very important for the innovation of material and chemistry science. Multitask deep learning models have been widely used in QMPs prediction. However, existing multitask learning models often train multiple QMPs prediction tasks simultaneously without considering the internal relationships and differences between tasks, which may cause the model to overfit easy tasks. In this study, we first proposed a multiscale dynamic attention graph neural network (MDGNN) for molecular representation learning. The MDGNN was designed in a multitask learning fashion that can solve multiple learning tasks at the same time. We then introduced a dynamic task balancing (DTB) strategy combining task differences and difficulties to reduce overfitting across multiple tasks. Finally, we adopted gradient-weighted class activation mapping (Grad-CAM) to analyze a deep learning model for frontier molecular orbital, highest occupied molecular orbital (HOMO) and lowest unoccupied molecular orbital (LUMO) energy level predictions. We evaluated our approach using two large QMPs datasets and compared the proposed method to the state-of-the-art multitask learning models. The MDGNN outperforms other multitask learning approaches on two datasets. The DTB strategy can further improve the performance of MDGNN significantly. Moreover, we show that Grad-CAM creates explanations that are consistent with the molecular orbitals theory. These advantages demonstrate that the proposed method improves the generalization and interpretation capability of QMPs prediction modeling.
Collapse
Affiliation(s)
- Ziduo Yang
- Artificial Intelligence Medical Center, School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, 510275, China.
| | - Weihe Zhong
- Artificial Intelligence Medical Center, School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, 510275, China.
| | - Qiujie Lv
- Artificial Intelligence Medical Center, School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, 510275, China.
| | - Calvin Yu-Chian Chen
- Artificial Intelligence Medical Center, School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, 510275, China. .,Department of Medical Research, China Medical University Hospital, Taichung 40447, Taiwan.,Department of Bioinformatics and Medical Engineering, Asia University, Taichung, 41354, Taiwan
| |
Collapse
|
29
|
Stuyver T, Coley CW. Quantum chemistry-augmented neural networks for reactivity prediction: Performance, generalizability, and explainability. J Chem Phys 2022; 156:084104. [DOI: 10.1063/5.0079574] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/07/2023] Open
Abstract
There is a perceived dichotomy between structure-based and descriptor-based molecular representations used for predictive chemistry tasks. Here, we study the performance, generalizability, and explainability of the quantum mechanics-augmented graph neural network (ml-QM-GNN) architecture as applied to the prediction of regioselectivity (classification) and of activation energies (regression). In our hybrid QM-augmented model architecture, structure-based representations are first used to predict a set of atom- and bond-level reactivity descriptors derived from density functional theory calculations. These estimated reactivity descriptors are combined with the original structure-based representation to make the final reactivity prediction. We demonstrate that our model architecture leads to significant improvements over structure-based GNNs in not only overall accuracy but also in generalization to unseen compounds. Even when provided training sets of only a couple hundred labeled data points, the ml-QM-GNN outperforms other state-of-the-art structure-based architectures that have been applied to these tasks as well as descriptor-based (linear) regressions. As a primary contribution of this work, we demonstrate a bridge between data-driven predictions and conceptual frameworks commonly used to gain qualitative insights into reactivity phenomena, taking advantage of the fact that our models are grounded in (but not restricted to) QM descriptors. This effort results in a productive synergy between theory and data science, wherein QM-augmented models provide a data-driven confirmation of previous qualitative analyses, and these analyses in turn facilitate insights into the decision-making process occurring within ml-QM-GNNs.
Collapse
Affiliation(s)
- Thijs Stuyver
- Department of Chemical Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, Massachusetts 02139, USA
| | - Connor W. Coley
- Department of Chemical Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, Massachusetts 02139, USA
- Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, Massachusetts 02139, USA
| |
Collapse
|
30
|
Gupta AK, Raghavachari K. Three-Dimensional Convolutional Neural Networks Utilizing Molecular Topological Features for Accurate Atomization Energy Predictions. J Chem Theory Comput 2022; 18:2132-2143. [PMID: 35226496 DOI: 10.1021/acs.jctc.1c00504] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
Deep learning methods provide a novel way to establish a correlation between two quantities. In this context, computer vision techniques such as three-dimensional (3D)-convolutional neural networks become a natural choice to associate a molecular property with its structure due to the inherent 3D nature of a molecule. However, traditional 3D input data structures are intrinsically sparse in nature, which tend to induce instabilities during the learning process, which in turn may lead to underfitted results. To address this deficiency, in this project, we propose to use quantum-chemically derived molecular topological features, namely, localized orbital locator and electron localization function, as molecular descriptors, which provide a relatively denser input representation in a 3D space. Such topological features provide a detailed picture of the atomic and electronic configuration and interatomic interactions in the molecule and hence are ideal for predicting properties that are highly dependent on the physical or electronic structure of the molecule. Herein, we demonstrate the efficacy of our proposed model by applying it to the task of predicting atomization energies for the QM9-G4MP2 data set, which contains ∼134k molecules. Furthermore, we incorporated the Δ-machine learning approach into our model, which enabled us to reach beyond benchmark accuracy levels (∼1.0 kJ mol-1). As a result, we consistently obtain impressive mean absolute errors of the order 0.1 kcal mol-1 (∼0.42 kJ mol-1) versus the G4(MP2) theory using relatively modest models, which could potentially be improved further in a systematic manner using additional compute resources.
Collapse
Affiliation(s)
- Ankur Kumar Gupta
- Department of Chemistry, Indiana University, Bloomington, Indiana 47405, United States
| | - Krishnan Raghavachari
- Department of Chemistry, Indiana University, Bloomington, Indiana 47405, United States
| |
Collapse
|
31
|
Harper DR, Nandy A, Arunachalam N, Duan C, Janet JP, Kulik HJ. Representations and strategies for transferable machine learning Improve model performance in chemical discovery. J Chem Phys 2022; 156:074101. [DOI: 10.1063/5.0082964] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Affiliation(s)
- Daniel R Harper
- Massachusetts Institute of Technology, United States of America
| | - Aditya Nandy
- Massachusetts Institute of Technology, United States of America
| | | | - Chenru Duan
- Massachusetts Institute of Technology, United States of America
| | | | - Heather J. Kulik
- Dept of Chemical Engineering, Massachusetts Institute of Technology, United States of America
| |
Collapse
|
32
|
Jiang D, Sun H, Wang J, Hsieh CY, Li Y, Wu Z, Cao D, Wu J, Hou T. Out-of-the-box deep learning prediction of quantum-mechanical partial charges by graph representation and transfer learning. Brief Bioinform 2022; 23:6513729. [DOI: 10.1093/bib/bbab597] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2021] [Revised: 12/14/2021] [Accepted: 12/23/2021] [Indexed: 11/14/2022] Open
Abstract
Abstract
Accurate prediction of atomic partial charges with high-level quantum mechanics (QM) methods suffers from high computational cost. Numerous feature-engineered machine learning (ML)-based predictors with favorable computability and reliability have been developed as alternatives. However, extensive expertise effort was needed for feature engineering of atom chemical environment, which may consequently introduce domain bias. In this study, SuperAtomicCharge, a data-driven deep graph learning framework, was proposed to predict three important types of partial charges (i.e. RESP, DDEC4 and DDEC78) derived from high-level QM calculations based on the structures of molecules. SuperAtomicCharge was designed to simultaneously exploit the 2D and 3D structural information of molecules, which was proved to be an effective way to improve the prediction accuracy of the model. Moreover, a simple transfer learning strategy and a multitask learning strategy based on self-supervised descriptors were also employed to further improve the prediction accuracy of the proposed model. Compared with the latest baselines, including one GNN-based predictor and two ML-based predictors, SuperAtomicCharge showed better performance on all the three external test sets and had better usability and portability. Furthermore, the QM partial charges of new molecules predicted by SuperAtomicCharge can be efficiently used in drug design applications such as structure-based virtual screening, where the predicted RESP and DDEC4 charges of new molecules showed more robust scoring and screening power than the commonly used partial charges. Finally, two tools including an online server (http://cadd.zju.edu.cn/deepchargepredictor) and the source code command lines (https://github.com/zjujdj/SuperAtomicCharge) were developed for the easy access of the SuperAtomicCharge services.
Collapse
|
33
|
Gupta A, Chakraborty S, Ghosh D, Ramakrishnan R. Data-driven modeling of S 0 → S 1 excitation energy in the BODIPY chemical space: High-throughput computation, quantum machine learning, and inverse design. J Chem Phys 2021; 155:244102. [PMID: 34972385 DOI: 10.1063/5.0076787] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022] Open
Abstract
Derivatives of BODIPY are popular fluorophores due to their synthetic feasibility, structural rigidity, high quantum yield, and tunable spectroscopic properties. While the characteristic absorption maximum of BODIPY is at 2.5 eV, combinations of functional groups and substitution sites can shift the peak position by ±1 eV. Time-dependent long-range corrected hybrid density functional methods can model the lowest excitation energies offering a semi-quantitative precision of ±0.3 eV. Alas, the chemical space of BODIPYs stemming from combinatorial introduction of-even a few dozen-substituents is too large for brute-force high-throughput modeling. To navigate this vast space, we select 77 412 molecules and train a kernel-based quantum machine learning model providing <2% hold-out error. Further reuse of the results presented here to navigate the entire BODIPY universe comprising over 253 giga (253 × 109) molecules is demonstrated by inverse-designing candidates with desired target excitation energies.
Collapse
Affiliation(s)
- Amit Gupta
- Centre for Interdisciplinary Sciences, Tata Institute of Fundamental Research, Hyderabad 500107, India
| | - Sabyasachi Chakraborty
- Centre for Interdisciplinary Sciences, Tata Institute of Fundamental Research, Hyderabad 500107, India
| | - Debashree Ghosh
- Indian Association for the Cultivation of Science, Kolkata 700032, India
| | - Raghunathan Ramakrishnan
- Centre for Interdisciplinary Sciences, Tata Institute of Fundamental Research, Hyderabad 500107, India
| |
Collapse
|
34
|
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
|
35
|
Brian D, Sun X. Charge-Transfer Landscape Manifesting the Structure-Rate Relationship in the Condensed Phase Via Machine Learning. J Phys Chem B 2021; 125:13267-13278. [PMID: 34825563 DOI: 10.1021/acs.jpcb.1c08260] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
In this work, we develop a machine learning (ML) strategy to map the molecular structure to condensed phase charge-transfer (CT) properties including CT rate constants, energy levels, electronic couplings, energy gaps, reorganization energies, and reaction free energies which are called CT fingerprints. The CT fingerprints of selected landmark structures covering the conformation space of an organic photovoltaic molecule dissolved in an explicit solvent are computed and used to train ML models using kernel ridge regression. The ML models show high predictive power with R2 > 0.97 and both mean absolute error and root-mean-square error within chemical accuracy. The CT landscape for millions of molecular dynamics sampled structures is thus constructed, which allows for instant prediction of CT rate properties, given any conformation of the molecule. We demonstrate some immediate utilities of the CT landscape such as calculating the ensemble-averaged CT rate constant and interpreting the effects of molecular structural features on the CT rate. The unprecedented CT landscape will be useful for investigating real-time CT dynamics in nanoscale- and mesoscale-condensed phase systems and for the optimal fabrication design for homogeneous and heterogeneous optoelectronic devices.
Collapse
Affiliation(s)
- Dominikus Brian
- Division of Arts and Sciences, NYU Shanghai, 1555 Century Avenue, Shanghai 200122, China.,NYU-ECNU Center for Computational Chemistry at NYU Shanghai, 3663 Zhongshan Road North, Shanghai 200062, China.,Department of Chemistry, New York University, New York, New York 10003, United States
| | - Xiang Sun
- Division of Arts and Sciences, NYU Shanghai, 1555 Century Avenue, Shanghai 200122, China.,NYU-ECNU Center for Computational Chemistry at NYU Shanghai, 3663 Zhongshan Road North, Shanghai 200062, China.,Department of Chemistry, New York University, New York, New York 10003, United States.,State Key Laboratory of Precision Spectroscopy, East China Normal University, Shanghai 200241, China
| |
Collapse
|
36
|
Li W, Ma H, Li S, Ma J. Computational and data driven molecular material design assisted by low scaling quantum mechanics calculations and machine learning. Chem Sci 2021; 12:14987-15006. [PMID: 34909141 PMCID: PMC8612375 DOI: 10.1039/d1sc02574k] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2021] [Accepted: 10/12/2021] [Indexed: 12/11/2022] Open
Abstract
Electronic structure methods based on quantum mechanics (QM) are widely employed in the computational predictions of the molecular properties and optoelectronic properties of molecular materials. The computational costs of these QM methods, ranging from density functional theory (DFT) or time-dependent DFT (TDDFT) to wave-function theory (WFT), usually increase sharply with the system size, causing the curse of dimensionality and hindering the QM calculations for large sized systems such as long polymer oligomers and complex molecular aggregates. In such cases, in recent years low scaling QM methods and machine learning (ML) techniques have been adopted to reduce the computational costs and thus assist computational and data driven molecular material design. In this review, we illustrated low scaling ground-state and excited-state QM approaches and their applications to long oligomers, self-assembled supramolecular complexes, stimuli-responsive materials, mechanically interlocked molecules, and excited state processes in molecular aggregates. Variable electrostatic parameters were also introduced in the modified force fields with the polarization model. On the basis of QM computational or experimental datasets, several ML algorithms, including explainable models, deep learning, and on-line learning methods, have been employed to predict the molecular energies, forces, electronic structure properties, and optical or electrical properties of materials. It can be conceived that low scaling algorithms with periodic boundary conditions are expected to be further applicable to functional materials, perhaps in combination with machine learning to fast predict the lattice energy, crystal structures, and spectroscopic properties of periodic functional materials.
Collapse
Affiliation(s)
- Wei Li
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering, Nanjing University Nanjing 210023 China
| | - Haibo Ma
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering, Nanjing University Nanjing 210023 China
- Jiangsu Key Laboratory of Advanced Organic Materials, Jiangsu Key Laboratory of Vehicle Emissions Control, Nanjing University Nanjing 210023 China
| | - Shuhua Li
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering, Nanjing University Nanjing 210023 China
| | - Jing Ma
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering, Nanjing University Nanjing 210023 China
- Jiangsu Key Laboratory of Advanced Organic Materials, Jiangsu Key Laboratory of Vehicle Emissions Control, Nanjing University Nanjing 210023 China
| |
Collapse
|
37
|
Xiang Y, Tang YH, Lin G, Sun H. A Comparative Study of Marginalized Graph Kernel and Message-Passing Neural Network. J Chem Inf Model 2021; 61:5414-5424. [PMID: 34723539 DOI: 10.1021/acs.jcim.1c01118] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
This work proposes a state-of-the-art hybrid kernel to calculate molecular similarity. Combined with Gaussian process models, the performance of the hybrid kernel in predicting molecular properties is comparable to that of the directed message-passing neural network (D-MPNN). The hybrid kernel consists of a marginalized graph kernel (MGK) and a radial basis function (RBF) kernel that operate on molecular graphs and global molecular features, respectively. Bayesian optimization was used to obtain the optimal hyperparameters for both models. The comparisons are performed on 11 publicly available data sets. Our results show that their performances are similar, their prediction errors are correlated, and the ensemble predictions of the two models perform better than either of them. Through principal component analysis, we found that the molecular embeddings of the hybrid kernel and the D-MPNN are also similar. The advantage of D-MPNN lies in the computational efficiency and scalability of large-scale data, while the advantage of the graph kernel models lies in the accurate uncertainty quantification.
Collapse
Affiliation(s)
- Yan Xiang
- School of Chemistry and Chemical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Yu-Hang Tang
- Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, California 94720, United States
| | - Guang Lin
- Department of Mathematics & School of Mechanical Engineering, Purdue University, West Lafayette, Indiana 47907, United States
| | - Huai Sun
- School of Chemistry and Chemical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
| |
Collapse
|
38
|
Cheng Z, Du J, Zhang L, Ma J, Li W, Li S. Building quantum mechanics quality force fields of proteins with the generalized energy-based fragmentation approach and machine learning. Phys Chem Chem Phys 2021; 24:1326-1337. [PMID: 34718360 DOI: 10.1039/d1cp03934b] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Abstract
We combined our generalized energy-based fragmentation (GEBF) approach and machine learning (ML) technique to construct quantum mechanics (QM) quality force fields for proteins. In our scheme, the training sets for a protein are only constructed from its small subsystems, which capture all short-range interactions in the target system. The energy of a given protein is expressed as the summation of atomic contributions from QM calculations of various subsystems, corrected by long-range Coulomb and van der Waals interactions. With the Gaussian approximation potential (GAP) method, our protocol can automatically generate training sets with high efficiency. To facilitate the construction of training sets for proteins, we store all trained subsystem data in a library. If subsystems in the library are detected in a new protein, corresponding datasets can be directly reused as a part of the training set on this new protein. With two polypeptides, 4ZNN and 1XQ8 segment, as examples, the energies and forces predicted by GEBF-GAP are in good agreement with those from conventional QM calculations, and dihedral angle distributions from GEBF-GAP molecular dynamics (MD) simulations can also well reproduce those from ab initio MD simulations. In addition, with the training set generated from GEBF-GAP, we also demonstrate that GEBF-ML force fields constructed by neural network (NN) methods can also show QM quality. Therefore, the present work provides an efficient and systematic way to build QM quality force fields for biological systems.
Collapse
Affiliation(s)
- Zheng Cheng
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, School of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing, 210023, P. R. China.
| | - Jiahui Du
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, School of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing, 210023, P. R. China.
| | - Lei Zhang
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, School of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing, 210023, P. R. China.
| | - Jing Ma
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, School of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing, 210023, P. R. China.
| | - Wei Li
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, School of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing, 210023, P. R. China.
| | - Shuhua Li
- Key Laboratory of Mesoscopic Chemistry of Ministry of Education, Institute of Theoretical and Computational Chemistry, School of Theoretical and Computational Chemistry, School of Chemistry and Chemical Engineering, Nanjing University, Nanjing, 210023, P. R. China.
| |
Collapse
|
39
|
Ye S, Liang J, Zhu X. Catalyst deep neural networks (Cat-DNNs) in singlet fission property prediction. Phys Chem Chem Phys 2021; 23:20835-20840. [PMID: 34505584 DOI: 10.1039/d1cp03594k] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
Many current deep neural network (DNN) models only focus on straightforward optimization over the given database. However, most numerical fitting procedures depart from physical laws. By introducing the concept of "catalysis" from physical chemistry, we propose that the physical correlations among molecular properties could spontaneously act as a catalyst in the DNNs, which increases the accuracy, and more importantly, guides the DNNs in the right way. These Catalysis-DNNs (Cat-DNNs) could precisely predict both the ground and excited-state properties, especially the molecules' screening with singlet fission character. We show that traditional machine learning metrics are not suitable for evaluating model accuracy in physical-chemical tasks and issue new physical errors. We believe that the agile transfer of fundamental physics or chemistry domain knowledge, like the catalyst, could significantly benefit both the architecture and application of artificial intelligence technology in the future.
Collapse
Affiliation(s)
- Shuqian Ye
- School of Science and Engineering (SSE), Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS), The Chinese University of Hong Kong, Shenzhen(CUHK-Shenzhen), 14-15F, Tower G2, Xinghe World, Rd Yabao, Longgang District, Shenzhen, Guangdong, 518172, China.
| | - Jiechun Liang
- School of Science and Engineering (SSE), Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS), The Chinese University of Hong Kong, Shenzhen(CUHK-Shenzhen), 14-15F, Tower G2, Xinghe World, Rd Yabao, Longgang District, Shenzhen, Guangdong, 518172, China.
| | - Xi Zhu
- School of Science and Engineering (SSE), Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS), The Chinese University of Hong Kong, Shenzhen(CUHK-Shenzhen), 14-15F, Tower G2, Xinghe World, Rd Yabao, Longgang District, Shenzhen, Guangdong, 518172, China.
| |
Collapse
|
40
|
Çaylak O, Baumeier B. Machine Learning of Quasiparticle Energies in Molecules and Clusters. J Chem Theory Comput 2021; 17:4891-4900. [PMID: 34314186 PMCID: PMC8359011 DOI: 10.1021/acs.jctc.1c00520] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2021] [Indexed: 11/30/2022]
Abstract
We present a Δ-machine learning approach for the prediction of GW quasiparticle energies (ΔMLQP) and photoelectron spectra of molecules and clusters, using orbital-sensitive representations (OSRs) based on molecular Cartesian coordinates in kernel ridge regression-based supervised learning. Coulomb matrix, bag-of-bond, and bond-angle-torsion representations are made orbital-sensitive by augmenting them with atom-centered orbital charges and Kohn-Sham orbital energies, both of which are readily available from baseline calculations at the level of density functional theory (DFT). We first illustrate the effects of different constructions of the OSRs on the prediction of frontier orbital energies of 22k molecules of the QM8 data set and show that it is possible to predict the full photoelectron spectrum of molecules within the data set using a single model with a mean absolute error below 0.1 eV. We further demonstrate that the OSR-based ΔMLQP captures the effects of intra- and intermolecular conformations in application to water monomers and dimers. Finally, we show that the approach can be embedded in multiscale simulation workflows, by studying the solvatochromic shifts of quasiparticle and electron-hole excitation energies of solvated acetone in a setup combining molecular dynamics, DFT, the GW approximation, and the Bethe-Salpeter equation. Our findings suggest that the ΔMLQP model allows us to predict quasiparticle energies and photoelectron spectra of molecules and clusters with GW accuracy at DFT cost.
Collapse
Affiliation(s)
- Onur Çaylak
- Department of Mathematics
and Computer Science, Eindhoven University
of Technology, P.O. Box 513, 5600MB Eindhoven, The Netherlands
- Institute for Complex Molecular
Systems, Eindhoven University of Technology, P.O. Box 513, 5600MB Eindhoven, The Netherlands
| | | |
Collapse
|
41
|
Liu R, Zhu X. Essentiality of the Basis Function in Deep Learning Physical Chemistry Properties. J Phys Chem Lett 2021; 12:6330-6335. [PMID: 34228463 DOI: 10.1021/acs.jpclett.1c01880] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/13/2023]
Abstract
The deep learning (DL) method sometimes suffers from poor transferability due to the wrong structure, i.e., basis functions used as the kernel for dimension elevation. Thus, for solving specific problems, a broad and robust set of basis functions should be elaborated. The choice of basis is similar to the procedure in variational principles in quantum physical chemistry applications. This work applies the associated Laguerre and the spherical harmonic for feature generation of molecules and atomic interactions, showing better performance in both the real-space and momenta-space and significantly enhancing the transferability and interpretability to unfamiliar elements and structures over the previous models. Moreover, with the symmetry manifested by the angular part from the spherical harmonics, both the energy and distribution of excited state orbitals can be calculated. Besides, the special functions can also be used in other applications such as image classification.
Collapse
Affiliation(s)
- Rulin Liu
- Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS), The Chinese University of Hong Kong, Shenzhen Shenzhen, Guangdong 518172, China
| | - Xi Zhu
- Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS), The Chinese University of Hong Kong, Shenzhen Shenzhen, Guangdong 518172, China
| |
Collapse
|
42
|
Xiang Y, Tang YH, Liu H, Lin G, Sun H. Predicting Single-Substance Phase Diagrams: A Kernel Approach on Graph Representations of Molecules. J Phys Chem A 2021; 125:4488-4497. [PMID: 33999627 DOI: 10.1021/acs.jpca.1c02391] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/28/2023]
Abstract
This work presents a Gaussian process regression (GPR) model on top of a novel graph representation of chemical molecules that predicts thermodynamic properties of pure substances in single, double, and triple phases. A transferable molecular graph representation is proposed as the input for a marginalized graph kernel, which is the major component of the covariance function in our GPR models. Radial basis function kernels of temperature and pressure are also incorporated into the covariance function when necessary. We predicted three types of representative properties of pure substances in single, double, and triple phases, i.e., critical temperature, vapor-liquid equilibrium (VLE) density, and pressure-temperature density. The accuracy of the models is nearly identical to the precision of the experimental measurements. Moreover, the reliability of our predictions can be quantified on a per-sample basis using the posterior uncertainty of the GPR model. We compare our model against Morgan fingerprints and a graph neural network to further demonstrate the advantage of the proposed method.
Collapse
Affiliation(s)
- Yan Xiang
- School of Chemistry and Chemical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Yu-Hang Tang
- Lawrence Berkeley National Laboratory, Berkeley, California 94720, United States
| | - Hongyi Liu
- School of Chemistry and Chemical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
| | - Guang Lin
- Department of Mathematics & School of Mechanical Engineering, Purdue University, West Lafayette, Indiana 47907, United States
| | - Huai Sun
- School of Chemistry and Chemical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
| |
Collapse
|
43
|
Abstract
Theoretical simulations of electronic excitations and associated processes in molecules are indispensable for fundamental research and technological innovations. However, such simulations are notoriously challenging to perform with quantum mechanical methods. Advances in machine learning open many new avenues for assisting molecular excited-state simulations. In this Review, we track such progress, assess the current state of the art and highlight the critical issues to solve in the future. We overview a broad range of machine learning applications in excited-state research, which include the prediction of molecular properties, improvements of quantum mechanical methods for the calculations of excited-state properties and the search for new materials. Machine learning approaches can help us understand hidden factors that influence photo-processes, leading to a better control of such processes and new rules for the design of materials for optoelectronic applications.
Collapse
|