1
|
Fedorov R, Gryn’ova G. Unlocking the Potential: Predicting Redox Behavior of Organic Molecules, from Linear Fits to Neural Networks. J Chem Theory Comput 2023; 19:4796-4814. [PMID: 37463673 PMCID: PMC10414033 DOI: 10.1021/acs.jctc.3c00355] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2023] [Indexed: 07/20/2023]
Abstract
Redox-active organic molecules, i.e., molecules that can relatively easily accept and/or donate electrons, are ubiquitous in biology, chemical synthesis, and electronic and spintronic devices, such as solar cells and rechargeable batteries, etc. Choosing the best candidates from an essentially infinite chemical space for experimental testing in a target application requires efficient screening approaches. In this Review, we discuss modern in silico techniques for predicting reduction and oxidation potentials of organic molecules that go beyond conventional first-principles computations and thermodynamic cycles. Approaches ranging from simple linear fits based on molecular orbital energy approximation and energy difference approximation to advanced regression and neural network machine learning algorithms employing complex descriptors of molecular compositions, geometries, and electronic structures are examined in conjunction with relevant literature examples. We discuss the interplay between ab initio data and machine learning (ML), i.e., whether it is better to base predictions on low-level quantum-chemical results corrected with ML or to bypass first-principles computations entirely and instead rely on elaborate deep learning architectures. Finally, we list currently available data sets of redox-active organic molecules and their experimental and/or computed properties to facilitate the development of screening platforms and rational design of redox-active organic molecules.
Collapse
Affiliation(s)
- Rostislav Fedorov
- Heidelberg
Institute for Theoretical Studies (HITS gGmbH), 69118 Heidelberg, Germany
- Interdisciplinary
Center for Scientific Computing, Heidelberg
University, 69120 Heidelberg, Germany
| | - Ganna Gryn’ova
- Heidelberg
Institute for Theoretical Studies (HITS gGmbH), 69118 Heidelberg, Germany
- Interdisciplinary
Center for Scientific Computing, Heidelberg
University, 69120 Heidelberg, Germany
| |
Collapse
|
2
|
Galuzzi BG, Mirarchi A, Viganò EL, De Gioia L, Damiani C, Arrigoni F. Machine Learning for Efficient Prediction of Protein Redox Potential: The Flavoproteins Case. J Chem Inf Model 2022; 62:4748-4759. [PMID: 36126254 PMCID: PMC9554915 DOI: 10.1021/acs.jcim.2c00858] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
![]()
Determining the redox
potentials of protein cofactors
and how they
are influenced by their molecular neighborhoods is essential for basic
research and many biotechnological applications, from biosensors and
biocatalysis to bioremediation and bioelectronics. The laborious determination
of redox potential with current experimental technologies pushes forward
the need for computational approaches that can reliably predict it.
Although current computational approaches based on quantum and molecular
mechanics are accurate, their large computational costs hinder their
usage. In this work, we explored the possibility of using more efficient
QSPR models based on machine learning (ML) for the prediction of protein
redox potential, as an alternative to classical approaches. As a proof
of concept, we focused on flavoproteins, one of the most important
families of enzymes directly involved in redox processes. To train
and test different ML models, we retrieved a dataset of flavoproteins
with a known midpoint redox potential (Em) and 3D structure. The features of interest, accounting for both
short- and long-range effects of the protein matrix on the flavin
cofactor, have been automatically extracted from each protein PDB
file. Our best ML model (XGB) has a performance error below 1 kcal/mol
(∼36 mV), comparing favorably to more sophisticated computational
approaches. We also provided indications on the features that mostly
affect the Em value, and when possible,
we rationalized them on the basis of previous studies.
Collapse
Affiliation(s)
- Bruno Giovanni Galuzzi
- Department of Biotechnology and Biosciences, University of Milano-Bicocca, Piazza della Scienza 2, 20126 Milan, Italy.,SYSBIO Centre of Systems Biology/ISBE.IT, Piazza della Scienza 2, 20126, Milan, Italy
| | - Antonio Mirarchi
- Department of Biotechnology and Biosciences, University of Milano-Bicocca, Piazza della Scienza 2, 20126 Milan, Italy
| | - Edoardo Luca Viganò
- Istituto di Ricerche Farmacologiche Mario Negri, Via Mario Negri 2, 20156 Milan, Italy
| | - Luca De Gioia
- Department of Biotechnology and Biosciences, University of Milano-Bicocca, Piazza della Scienza 2, 20126 Milan, Italy
| | - Chiara Damiani
- Department of Biotechnology and Biosciences, University of Milano-Bicocca, Piazza della Scienza 2, 20126 Milan, Italy.,SYSBIO Centre of Systems Biology/ISBE.IT, Piazza della Scienza 2, 20126, Milan, Italy
| | - Federica Arrigoni
- Department of Biotechnology and Biosciences, University of Milano-Bicocca, Piazza della Scienza 2, 20126 Milan, Italy
| |
Collapse
|
3
|
A study on Ti-doped Fe 3O 4 anode for Li ion battery using machine learning, electrochemical and distribution function of relaxation times (DFRTs) analyses. Sci Rep 2022; 12:4851. [PMID: 35318363 PMCID: PMC8941007 DOI: 10.1038/s41598-022-08584-4] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2022] [Accepted: 03/09/2022] [Indexed: 11/24/2022] Open
Abstract
Among many transition-metal oxides, Fe3O4 anode based lithium ion batteries (LIBs) have been well-investigated because of their high energy and high capacity. Iron is known for elemental abundance and is relatively environmentally friendly as well contains with low toxicity. However, LIBs based on Fe3O4 suffer from particle aggregation during charge–discharge processes that affects the cycling performance. This study conjectures that iron agglomeration and material performance could be affected by dopant choice, and improvements are sought with Fe3O4 nanoparticles doped with 0.2% Ti. The electrochemical measurements show a stable specific capacity of 450 mAh g−1 at 0.1 C rate for at least 100 cycles in Ti doped Fe3O4. The stability in discharge capacity for Ti doped Fe3O4 is achieved, arising from good electronic conductivity and stability in microstructure and crystal structure, which has been further confirmed by density functional theory (DFT) calculation. Detailed distribution function of relaxation times (DFRTs) analyses based on the impedance spectra reveal two different types of Li ion transport phenomena, which are closely related with the electron density difference near the two Fe-sites. Detailed analyses on EIS measurements using DFRTs for Ti doped Fe3O4 indicate that improvement in interfacial charge transfer processes between electrode and Li metal along with an intermediate lithiated phase helps to enhance the electrochemical performance.
Collapse
|
4
|
Abstract
Variations in mixture proportions of plasticizers, additives, and crosslinking agents have significant impacts on mechanical performance of starch-based foam materials. In particular, starch/ethylene-vinyl acetate (EVA) foam materials have been developed with improved mechanical strength by optimizing the formulation. There is a lack of numerical correlations that could help analyze the effects of components and provide a predictive method for future research. In this study, we develop simple and accurate predictions for tensile strength and resilience based on mixture proportions of components for starch-based/EVA foam materials. The models constructed might be used to help design mixture proportions of starch-based foam materials. By combining optimization results from the Taguchi method and machine learning approaches, it is expected that more quantitative data can be extracted from fewer experimental trials at the same time.
Collapse
Affiliation(s)
- Yun Zhang
- North Carolina State University, Raleigh, NC, USA
| | - Xiaojie Xu
- North Carolina State University, Raleigh, NC, USA
| |
Collapse
|
5
|
Hruska E, Gale A, Liu F. Bridging the Experiment-Calculation Divide: Machine Learning Corrections to Redox Potential Calculations in Implicit and Explicit Solvent Models. J Chem Theory Comput 2022; 18:1096-1108. [PMID: 34991320 DOI: 10.1021/acs.jctc.1c01040] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/01/2023]
Abstract
Prediction of redox potentials is essential for catalysis and energy storage. Although density functional theory (DFT) calculations have enabled rapid redox potential predictions for numerous compounds, prominent errors persist compared to experimental measurements. In this work, we develop machine learning (ML) models to reduce the errors of redox potential calculations in both implicit and explicit solvent models. Training and testing of the ML correction models are based on the diverse ROP313 data set with experimental redox potentials measured for organic and organometallic compounds in a variety of solvents. For the implicit solvent approach, our ML models can reduce both the systematic bias and the number of outliers. ML corrected redox potentials also demonstrate less sensitivity to DFT functional choice. For the explicit solvent approach, we significantly reduce the computational costs by embedding the microsolvated cluster in implicit bulk solvent, obtaining converged redox potential results with a smaller solvation shell. This combined implicit-explicit solvent model, together with GPU-accelerated quantum chemistry methods, enabled rapid generation of a large data set of explicit-solvent-calculated redox potentials for 165 organic compounds, allowing detailed investigation of the error sources in explicit solvent redox potential calculations.
Collapse
Affiliation(s)
- Eugen Hruska
- Department of Chemistry, Emory University, Atlanta, Georgia 30322, United States
| | - Ariel Gale
- Department of Chemistry, Emory University, Atlanta, Georgia 30322, United States
| | - Fang Liu
- Department of Chemistry, Emory University, Atlanta, Georgia 30322, United States
| |
Collapse
|
6
|
Jin L, Ji Y, Wang H, Ding L, Li Y. First-principles materials simulation and design for alkali and alkaline metal ion batteries accelerated by machine learning. Phys Chem Chem Phys 2021; 23:21470-21483. [PMID: 34570138 DOI: 10.1039/d1cp02963k] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
The challenge of regeneration of batteries requires a performance improvement in the alkali/alkaline metal ion battery (AMIB) materials, whereas the traditional research paradigm fully based on experiments and theoretical simulations needs massive research and development investment. During the last decade, machine learning (ML) has made breakthroughs in many complex disciplines, which testifies to their high processing speed and ability to capture relationships. Inspired by these achievements, ML has also been introduced to bring a new paradigm for shortening the development of AMIB materials. In this Perspective, the focus will be on how this new ML technology solves the key problems of redox potentials, ionic conductivity and stability parameters in first-principles materials' simulation and design for AMIBs. It is found that ML not only accelerates the property prediction, but also gives physicochemical insights into AMIB materials' design. In addition, the final part of this paper summarizes current achievements and looks forward to the progress of a novel paradigm in direct/inverse design with the increasing number of databases, skills, and ML technologies for AMIBs.
Collapse
Affiliation(s)
- Lujie Jin
- Institute of Functional Nano & Soft Materials (FUNSOM), Jiangsu Key Laboratory for Carbon-Based Functional Materials & Devices, Soochow University, Suzhou, Jiangsu 215123, China.
| | - Yujin Ji
- Institute of Functional Nano & Soft Materials (FUNSOM), Jiangsu Key Laboratory for Carbon-Based Functional Materials & Devices, Soochow University, Suzhou, Jiangsu 215123, China.
| | - Hongshuai Wang
- Institute of Functional Nano & Soft Materials (FUNSOM), Jiangsu Key Laboratory for Carbon-Based Functional Materials & Devices, Soochow University, Suzhou, Jiangsu 215123, China.
| | - Lifeng Ding
- Department of Chemistry, Xi'an JiaoTong-Liverpool University, 111 Ren'ai Road, Suzhou Dushu Lake, Higher Education Town, Jiangsu Province 215123, China
| | - Youyong Li
- Institute of Functional Nano & Soft Materials (FUNSOM), Jiangsu Key Laboratory for Carbon-Based Functional Materials & Devices, Soochow University, Suzhou, Jiangsu 215123, China. .,Macao Institute of Materials Science and Engineering, Macau University of Science and Technology, Taipa, Macau SAR 999078, China
| |
Collapse
|
7
|
Hu J, Qian X, Cheng H, Tan C, Liu X. Remaining useful life prediction for aircraft engines based on phase space reconstruction and hybrid VNS-SVR model. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2021. [DOI: 10.3233/jifs-210740] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Based on phase space reconstruction (PSR) and hybrid VNS-SVR model, a remaining useful life (RUL) prediction method for aircraft engines is proposed. The proposed hybrid model combines support vector regression (SVR), which has been successfully adopted for regression problems, with the variable neighborhood search (VNS). First, the phase space reconstruction is used to transform the selected one-dimensional performance sequences of aircraft engines into matrix forms, which increases the data information and improve the learning efficiency of the model effectively. Then, SVR is used to construct the prediction model. Meanwhile, a VNS algorithm is proposed to optimize the kernel parameters. Finally, the hybrid model is used to RUL prediction of the aircraft engines. The experimental results show that the method has a good prediction performance.
Collapse
Affiliation(s)
- Junying Hu
- School of Management, Hefei University of Technology, Hefei, PR. China
- Key Laboratory of Process Optimization and Intelligent Decision-making of the Ministry of Education, Hefei, PR. China
| | - Xiaofei Qian
- School of Management, Hefei University of Technology, Hefei, PR. China
- Key Laboratory of Process Optimization and Intelligent Decision-making of the Ministry of Education, Hefei, PR. China
- Ministry of Education Engineering Research Center for Intelligent Decision-Making & Information System Technologies, Hefei, PR. China
| | - Hao Cheng
- School of Management, Hefei University of Technology, Hefei, PR. China
- Key Laboratory of Process Optimization and Intelligent Decision-making of the Ministry of Education, Hefei, PR. China
| | - Changchun Tan
- School of Economics, Hefei University of Technology, Hefei, PR. China
| | - Xinbao Liu
- School of Management, Hefei University of Technology, Hefei, PR. China
- Key Laboratory of Process Optimization and Intelligent Decision-making of the Ministry of Education, Hefei, PR. China
| |
Collapse
|
8
|
Bang K, Yeo BC, Kim D, Han SS, Lee HM. Accelerated mapping of electronic density of states patterns of metallic nanoparticles via machine-learning. Sci Rep 2021; 11:11604. [PMID: 34078997 PMCID: PMC8173009 DOI: 10.1038/s41598-021-91068-8] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2021] [Accepted: 05/20/2021] [Indexed: 11/21/2022] Open
Abstract
Within first-principles density functional theory (DFT) frameworks, it is challenging to predict the electronic structures of nanoparticles (NPs) accurately but fast. Herein, a machine-learning architecture is proposed to rapidly but reasonably predict electronic density of states (DOS) patterns of metallic NPs via a combination of principal component analysis (PCA) and the crystal graph convolutional neural network (CGCNN). With the PCA, a mathematically high-dimensional DOS image can be converted to a low-dimensional vector. The CGCNN plays a key role in reflecting the effects of local atomic structures on the DOS patterns of NPs with only a few of material features that are easily extracted from a periodic table. The PCA-CGCNN model is applicable for all pure and bimetallic NPs, in which a handful DOS training sets that are easily obtained with the typical DFT method are considered. The PCA-CGCNN model predicts the R2 value to be 0.85 or higher for Au pure NPs and 0.77 or higher for Au@Pt core@shell bimetallic NPs, respectively, in which the values are for the test sets. Although the PCA-CGCNN method showed a small loss of accuracy when compared with DFT calculations, the prediction time takes just ~ 160 s irrespective of the NP size in contrast to DFT method, for example, 13,000 times faster than the DFT method for Pt147. Our approach not only can be immediately applied to predict electronic structures of actual nanometer scaled NPs to be experimentally synthesized, but also be used to explore correlations between atomic structures and other spectrum image data of the materials (e.g., X-ray diffraction, X-ray photoelectron spectroscopy, and Raman spectroscopy).
Collapse
Affiliation(s)
- Kihoon Bang
- Department of Materials Science and Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea
| | - Byung Chul Yeo
- Computational Science Research Center, Korea Institute of Science and Technology (KIST), 5 Hwarang-ro 14-gil, Seongbuk-gu, Seoul, 02792, Republic of Korea
| | - Donghun Kim
- Computational Science Research Center, Korea Institute of Science and Technology (KIST), 5 Hwarang-ro 14-gil, Seongbuk-gu, Seoul, 02792, Republic of Korea
| | - Sang Soo Han
- Computational Science Research Center, Korea Institute of Science and Technology (KIST), 5 Hwarang-ro 14-gil, Seongbuk-gu, Seoul, 02792, Republic of Korea.
| | - Hyuck Mo Lee
- Department of Materials Science and Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea.
| |
Collapse
|
9
|
Zhang Y, Xu X. Machine learning glass transition temperature of polyacrylamides using quantum chemical descriptors. Polym Chem 2021. [DOI: 10.1039/d0py01581d] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
Abstract
Polyacrylamides glass transition temperature predictions from different models, where the GPR model is from the current study. The GPR model based on quantum chemical descriptors shows a high degree of accuracy.
Collapse
Affiliation(s)
- Yun Zhang
- North Carolina State University
- Raleigh
- USA
| | - Xiaojie Xu
- North Carolina State University
- Raleigh
- USA
| |
Collapse
|