1
|
Duan C, Nandy A, Kulik HJ. Machine Learning for the Discovery, Design, and Engineering of Materials. Annu Rev Chem Biomol Eng 2022; 13:405-429. [PMID: 35320698 DOI: 10.1146/annurev-chembioeng-092320-120230] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
Machine learning (ML) has become a part of the fabric of high-throughput screening and computational discovery of materials. Despite its increasingly central role, challenges remain in fully realizing the promise of ML. This is especially true for the practical acceleration of the engineering of robust materials and the development of design strategies that surpass trial and error or high-throughput screening alone. Depending on the quantity being predicted and the experimental data available, ML can either outperform physics-based modes, be used to accelerate such models, or be integrated with them to improve their performance. We cover recent advances in algorithms and in their application that are starting to make inroads toward (a) the discovery of new materials through large-scale enumerative screening, (b) the design of materials through identification of rules and principles that govern materials properties, and (c) the engineering of practical materials by satisfying multiple objectives. We conclude with opportunities for further advancement to realize ML as a widespread tool for practical computational materials design. Expected final online publication date for the Annual Review of Chemical and Biomolecular Engineering, Volume 13 is October 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.
Collapse
Affiliation(s)
- Chenru Duan
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA; , , .,Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
| | - Aditya Nandy
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA; , , .,Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
| | - Heather J Kulik
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA; , ,
| |
Collapse
|
2
|
Nandy A, Duan C, Taylor MG, Liu F, Steeves AH, Kulik HJ. Computational Discovery of Transition-metal Complexes: From High-throughput Screening to Machine Learning. Chem Rev 2021; 121:9927-10000. [PMID: 34260198 DOI: 10.1021/acs.chemrev.1c00347] [Citation(s) in RCA: 70] [Impact Index Per Article: 23.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
Abstract
Transition-metal complexes are attractive targets for the design of catalysts and functional materials. The behavior of the metal-organic bond, while very tunable for achieving target properties, is challenging to predict and necessitates searching a wide and complex space to identify needles in haystacks for target applications. This review will focus on the techniques that make high-throughput search of transition-metal chemical space feasible for the discovery of complexes with desirable properties. The review will cover the development, promise, and limitations of "traditional" computational chemistry (i.e., force field, semiempirical, and density functional theory methods) as it pertains to data generation for inorganic molecular discovery. The review will also discuss the opportunities and limitations in leveraging experimental data sources. We will focus on how advances in statistical modeling, artificial intelligence, multiobjective optimization, and automation accelerate discovery of lead compounds and design rules. The overall objective of this review is to showcase how bringing together advances from diverse areas of computational chemistry and computer science have enabled the rapid uncovering of structure-property relationships in transition-metal chemistry. We aim to highlight how unique considerations in motifs of metal-organic bonding (e.g., variable spin and oxidation state, and bonding strength/nature) set them and their discovery apart from more commonly considered organic molecules. We will also highlight how uncertainty and relative data scarcity in transition-metal chemistry motivate specific developments in machine learning representations, model training, and in computational chemistry. Finally, we will conclude with an outlook of areas of opportunity for the accelerated discovery of transition-metal complexes.
Collapse
Affiliation(s)
- Aditya Nandy
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.,Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Chenru Duan
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States.,Department of Chemistry, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Michael G Taylor
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Fang Liu
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Adam H Steeves
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Heather J Kulik
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| |
Collapse
|
3
|
Breunig JM, Tofan D, Cummins CC. Contrastingcyclo-P3Ligand Transfer Reactivity of Valence-Isoelectronic Aryloxide Complexes [(P3)Nb(ODipp)3]-and [(P3)W(ODipp)3]. Eur J Inorg Chem 2013. [DOI: 10.1002/ejic.201301140] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
|
4
|
Examples of Different Reactions of Benzylsulfanyl‐Substituted Alkynes with Selected Complexes of Ti
II
and Co
I. Eur J Inorg Chem 2013. [DOI: 10.1002/ejic.201300312] [Citation(s) in RCA: 15] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
|
5
|
Sues PE, Lough AJ, Morris RH. Flexible Syntheses of Tripodal Phosphine Ligands 1,1,2-Tris(diarylphosphino)ethane and Their Ruthenium η5-C5Me5 Complexes. Organometallics 2012. [DOI: 10.1021/om3005959] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Peter E. Sues
- Department of Chemistry, University of Toronto, Toronto, Ontario
M5S 3H6, Canada
| | - Alan J. Lough
- Department of Chemistry, University of Toronto, Toronto, Ontario
M5S 3H6, Canada
| | - Robert H. Morris
- Department of Chemistry, University of Toronto, Toronto, Ontario
M5S 3H6, Canada
| |
Collapse
|
6
|
Landrum GA, Penzotti J, Putta S. Machine-Learning Models for Combinatorial Catalyst Discovery. ACTA ACUST UNITED AC 2011. [DOI: 10.1557/proc-804-jj11.5] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/13/2022]
Abstract
ABSTRACTStandard machine-learning algorithms were used to build models capable of predicting the molecular weights of polymers generated by a homogeneous catalyst. Using descriptors calculated from only the two-dimensional structures of the ligands, the average accuracy of the models on an external validation data set was approximately 70%. Because the models show no bias and perform significantly better than equivalent models built using randomized data, we conclude that they learned useful rules and did not overfit the data.
Collapse
|
7
|
Mautz J, Heinze K, Wadepohl H, Huttner G. Reductive Activation oftripod Metal Compounds: Identification of Intermediates and Preparative Application. Eur J Inorg Chem 2008. [DOI: 10.1002/ejic.200700873] [Citation(s) in RCA: 24] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
|
8
|
Mautz J, Huttner G. Reductive Activation oftripod Metal Compounds: Preparative Application. Eur J Inorg Chem 2008. [DOI: 10.1002/ejic.200700874] [Citation(s) in RCA: 13] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
|
9
|
Büchner M, Huttner G, Winterhalter U, Frick A. Diastereoselectivity in the Reaction of RCH
2
C[CH
2
P (Ar)(Lr)]
3
with Electrophiles: Enhancement of Diastereoselective Control by η
3
‐Coordination in {RCH
2
C[CH
2
P(Ar)(Li)
3
}Mo(Co)
3. ACTA ACUST UNITED AC 2006. [DOI: 10.1002/cber.19971301006] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Affiliation(s)
- Michael Büchner
- Anorganisch‐Chemisches Institut, Universität Heidelberg Im Neuenheimer Feld 270, D‐69120 Heidelberg, Germany
| | - Gottfried Huttner
- Anorganisch‐Chemisches Institut, Universität Heidelberg Im Neuenheimer Feld 270, D‐69120 Heidelberg, Germany
| | - Ute Winterhalter
- Anorganisch‐Chemisches Institut, Universität Heidelberg Im Neuenheimer Feld 270, D‐69120 Heidelberg, Germany
| | - Axel Frick
- Anorganisch‐Chemisches Institut, Universität Heidelberg Im Neuenheimer Feld 270, D‐69120 Heidelberg, Germany
| |
Collapse
|
10
|
Hierso JC, Amardeil R, Bentabet E, Broussier R, Gautheron B, Meunier P, Kalck P. Structural diversity in coordination chemistry of tridentate and tetradentate polyphosphines of Group 6 to 10 transition metal complexes. Coord Chem Rev 2003. [DOI: 10.1016/s0010-8545(02)00221-7] [Citation(s) in RCA: 115] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
11
|
Rupp R, Huttner G, Kircher P, Soltek R, Büchner M. Coordination Compounds oftripodCoII andtripodCoI − Selective Substitution and Redox Behaviour. Eur J Inorg Chem 2000. [DOI: 10.1002/1099-0682(200008)2000:8<1745::aid-ejic1745>3.0.co;2-7] [Citation(s) in RCA: 18] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
|
12
|
Reichling S, Huttner G. How to Find Correlations Between Molecular Shape and Packing in a Molecular Crystal: Application of a Novel Strategy to Recognizen-Point Polyhedra in Three-Dimensional Space. Eur J Inorg Chem 2000. [DOI: 10.1002/(sici)1099-0682(200005)2000:5%3c857::aid-ejic857%3e3.0.co;2-7] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
|
13
|
Reichling S, Huttner G. How to Find Correlations Between Molecular Shape and Packing in a Molecular Crystal: Application of a Novel Strategy to Recognizen-Point Polyhedra in Three-Dimensional Space. Eur J Inorg Chem 2000. [DOI: 10.1002/(sici)1099-0682(200005)2000:5<857::aid-ejic857>3.0.co;2-7] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
|
14
|
Beyreuther S, Frick A, Hunger J, Huttner G, Antelmann B, Schober P, Soltek R. How to Predict Activation Barriers – Conformational Transformations of Compounds CH3C(CH2PPh2)3–n[CH2P(oTol)2]nMo(CO)3 (n = 1–3): Force Field Calculations versus NMR Data. Eur J Inorg Chem 2000. [DOI: 10.1002/(sici)1099-0682(200004)2000:4<597::aid-ejic597>3.0.co;2-7] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
|
15
|
|
16
|
Karas J, Huttner G, Heinze K, Rutsch P, Zsolnai L. Preparation of Enantiomerically Pure Chelate Ligands L2 = XCH2CH(OH)CH2Y from Epichlorohydrin – Conformation of Their L2Rh(COD)+ Derivatives and Enantioselective Hydrogenation by L2Rh(COD)+. Eur J Inorg Chem 1999. [DOI: 10.1002/(sici)1099-0682(199903)1999:3<405::aid-ejic405>3.0.co;2-t] [Citation(s) in RCA: 14] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
|
17
|
Hunger J, Huttner G. Optimization and analysis of force field parameters by combination of genetic algorithms and neural networks. J Comput Chem 1999. [DOI: 10.1002/(sici)1096-987x(199903)20:4<455::aid-jcc6>3.0.co;2-1] [Citation(s) in RCA: 81] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
|
18
|
Schober P, Huttner G, Zsolnai L, Jacobi A. Synthesis, coordination chemistry and polymerfixation of the tripod-ligand HOC6H4CH2C(CH2PPh2)3. J Organomet Chem 1998. [DOI: 10.1016/s0022-328x(98)00883-3] [Citation(s) in RCA: 14] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
19
|
Jacobi A, Huttner G, Winterhalter U. Rhodium COD complexes of mixed donor set tripod ligands: coordination chemistry and catalysis. J Organomet Chem 1998. [DOI: 10.1016/s0022-328x(98)00882-1] [Citation(s) in RCA: 13] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
20
|
Beyreuther S, Hunger J, Cunskis S, Diercks T, Frick A, Planker E, Huttner G. How to Predict Conformations Accessible to a Molecule in Solution: Validation of a Force Field-Based Prediction of NOE Distances by Comparison with the Experimental Data for the Series of Compounds CH3C[CH2P(Bzl)R]3Mo(CO)3 (R = Ph,m-Xyl). Eur J Inorg Chem 1998. [DOI: 10.1002/(sici)1099-0682(199811)1998:11<1641::aid-ejic1641>3.0.co;2-x] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
|
21
|
Jacobi A, Huttner G, Winterhalter U, Cunskis S. Pyrazole as a Donor Function in Neopentane-Based Tripod Ligands RCH2C(CH2pyrazol-1-yl)3–n(CH2PR2)n – Synthesis and Coordination Chemistry. Eur J Inorg Chem 1998. [DOI: 10.1002/(sici)1099-0682(199806)1998:6<675::aid-ejic675>3.0.co;2-m] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
|
22
|
Hunger J, Beyreuther S, Huttner G, Allinger K, Radelof U, Zsolnai L. How to Derive Force Field Parameters by Genetic Algorithms: Modellingtripod-Mo(CO)3 Compounds as an Example. Eur J Inorg Chem 1998. [DOI: 10.1002/(sici)1099-0682(199806)1998:6<693::aid-ejic693>3.0.co;2-m] [Citation(s) in RCA: 27] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
|
23
|
Heinze K, Huttner G, Schober P. Magnetic Interaction in Dinuclear Triphos−Cobalt Complexes with Co···Co Separations of 8 and 10 Å. Eur J Inorg Chem 1998. [DOI: 10.1002/(sici)1099-0682(199802)1998:2<183::aid-ejic183>3.0.co;2-p] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
|
24
|
Kless A, Holz J, Reinke H, Börner A. Studies on the formation of uniform η3-coordinated triphos-Mo(0)-complexes. J Organomet Chem 1998. [DOI: 10.1016/s0022-328x(97)00326-4] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
25
|
Braga AP, Braga JP, Belchior JC. Artificial neural network applied for predicting rainbow trajectories in atomic and molecular classical collisions. J Chem Phys 1997. [DOI: 10.1063/1.475298] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
|
26
|
Antelmann B, Huttner G, Vogelgesang J, Walter O, Winterhalter U. Tripod-Liganden mit cyclopentadienyl-donorgruppe: Synthese und reaktivität von komplexen des typs CH3C(CH2-η5-C5H4)(CH2PR2)(CH2PR′2)FeCl. J Organomet Chem 1997. [DOI: 10.1016/s0022-328x(97)00502-0] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
|
27
|
Heinze K, Huttner G, Zsolnai L, Schober P. Complexes of Cobalt(II) Chloride with the Tripodal Trisphosphane triphos: Solution Dynamics, Spin-Crossover, Reactivity, and Redox Activity. Inorg Chem 1997. [DOI: 10.1021/ic9705352] [Citation(s) in RCA: 50] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Affiliation(s)
- Katja Heinze
- Department of Inorganic Chemistry, University of Heidelberg, Im Neuenheimer Feld 270, D-69120 Heidelberg, Germany
| | - Gottfried Huttner
- Department of Inorganic Chemistry, University of Heidelberg, Im Neuenheimer Feld 270, D-69120 Heidelberg, Germany
| | - Laszlo Zsolnai
- Department of Inorganic Chemistry, University of Heidelberg, Im Neuenheimer Feld 270, D-69120 Heidelberg, Germany
| | - Peter Schober
- Department of Inorganic Chemistry, University of Heidelberg, Im Neuenheimer Feld 270, D-69120 Heidelberg, Germany
| |
Collapse
|