Accelerating Chemical Discovery with Machine Learning: Simulated Evolution of Spin Crossover Complexes with an Artificial Neural Network

doi:10.1021/acs.jpclett.8b00170

Title: Accelerating Chemical Discovery with Machine Learning: Simulated Evolution of Spin Crossover Complexes with an Artificial Neural Network

Abstract

Machine learning (ML) has emerged as a powerful complement to simulation for materials discovery by reducing time for evaluation of energies and properties at accuracy competitive with first-principles methods. We use genetic algorithm (GA) optimization to discover unconventional spin-crossover complexes in combination with efficient scoring from an artificial neural network (ANN) that predicts spin-state splitting of inorganic complexes. We explore a compound space of over 5600 candidate materials derived from eight metal/oxidation state combinations and a 32-ligand pool. We introduce a strategy for error-aware ML-driven discovery by limiting how far the GA travels away from the nearest ANN training points while maximizing property (i.e., spin-splitting) fitness, leading to discovery of 80% of the leads from full chemical space enumeration. Over a 51-complex subset, average unsigned errors (4.5 kcal/mol) are close to the ANN’s baseline 3 kcal/mol error. By obtaining leads from the trained ANN within seconds rather than days from a DFT-driven GA, this strategy demonstrates the power of ML for accelerating inorganic material discovery.

Authors:

^[1]; Chan, Lydia ^[1];

^[1]

Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States

Publication Date:: 2018-02-15

Research Org.:: Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Basic Energy Sciences (BES)

OSTI Identifier:: 1421993

Alternate Identifier(s):: OSTI ID: 1508752

Grant/Contract Number:: SC0018096; N00014-17-1-2956; CBET-1704266; ACI-1548562

Resource Type:: Published Article

Journal Name:: Journal of Physical Chemistry Letters

Additional Journal Information:: Journal Name: Journal of Physical Chemistry Letters Journal Volume: 9 Journal Issue: 5; Journal ID: ISSN 1948-7185

Publisher:: American Chemical Society

Country of Publication:: United States

Language:: English

Subject:: 37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; 36 MATERIALS SCIENCE

Citation Formats


                    Janet, Jon Paul, Chan, Lydia, and Kulik, Heather J. Accelerating Chemical Discovery with Machine Learning: Simulated Evolution of Spin Crossover Complexes with an Artificial Neural Network.  United States: N. p., 2018. 
        Web.  doi:10.1021/acs.jpclett.8b00170.

Copy to clipboard


                    Janet, Jon Paul, Chan, Lydia, & Kulik, Heather J. Accelerating Chemical Discovery with Machine Learning: Simulated Evolution of Spin Crossover Complexes with an Artificial Neural Network.  United States.  doi:10.1021/acs.jpclett.8b00170.

Copy to clipboard


                    Janet, Jon Paul, Chan, Lydia, and Kulik, Heather J. Thu .  
        "Accelerating Chemical Discovery with Machine Learning: Simulated Evolution of Spin Crossover Complexes with an Artificial Neural Network".  United States.  doi:10.1021/acs.jpclett.8b00170.

Copy to clipboard


                    
@article{osti_1421993,

  title        = {Accelerating Chemical Discovery with Machine Learning: Simulated Evolution of Spin Crossover Complexes with an Artificial Neural Network},

  author       = {Janet, Jon Paul and Chan, Lydia and Kulik, Heather J.},

  abstractNote = {Machine learning (ML) has emerged as a powerful complement to simulation for materials discovery by reducing time for evaluation of energies and properties at accuracy competitive with first-principles methods. We use genetic algorithm (GA) optimization to discover unconventional spin-crossover complexes in combination with efficient scoring from an artificial neural network (ANN) that predicts spin-state splitting of inorganic complexes. We explore a compound space of over 5600 candidate materials derived from eight metal/oxidation state combinations and a 32-ligand pool. We introduce a strategy for error-aware ML-driven discovery by limiting how far the GA travels away from the nearest ANN training points while maximizing property (i.e., spin-splitting) fitness, leading to discovery of 80% of the leads from full chemical space enumeration. Over a 51-complex subset, average unsigned errors (4.5 kcal/mol) are close to the ANN’s baseline 3 kcal/mol error. By obtaining leads from the trained ANN within seconds rather than days from a DFT-driven GA, this strategy demonstrates the power of ML for accelerating inorganic material discovery.},

  doi          = {10.1021/acs.jpclett.8b00170},

  journal      = {Journal of Physical Chemistry Letters},

  number       = 5,

  volume       = 9,

  place        = {United States},

  year         = {2018},

  month        = {2}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Publisher's Version of Record
DOI: 10.1021/acs.jpclett.8b00170

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 20 works

Citation information provided by
Web of Science

Figures / Tables:

Figure 1.: (top) Representative descriptors in MCDL-25: metal properties, metal-adjacent (i.e., local ligand properties), and global ligand properties. (bottom) Representative complexes including Fe(II)(H₂O)₆ in training data and increasingly distant complexes from the training data (left to right): Fe(II)(bpy)₃, Fe(II)(H₂O)₂(furan)₄, and Fe(II)(bpy)₂(furan)₂. The closest training point and its distance is indicatedmore »

All figures and tables (4 total)

Save / Share:

Export Metadata

Save to My Library

Works referencing / citing this record:

Enumeration of de novo inorganic complexes for chemical discovery and machine learning
journal, January 2020

Gugler, Stefan; Janet, Jon Paul; Kulik, Heather J.
Molecular Systems Design & Engineering, Vol. 5, Issue 1
DOI: 10.1039/c9me00069k

Enumeration of de novo inorganic complexes for chemical discovery and machine learning
journal, January 2020

Gugler, Stefan; Janet, Jon Paul; Kulik, Heather J.
Molecular Systems Design & Engineering, Vol. 5, Issue 1
DOI: 10.1039/c9me00069k

Toward Predicting Efficiency of Organic Solar Cells via Machine Learning and Improved Descriptors
journal, July 2018

Sahu, Harikrishna; Rao, Weining; Troisi, Alessandro
Advanced Energy Materials, Vol. 8, Issue 24
DOI: 10.1002/aenm.201801032

Machine learning for heterogeneous catalyst design and discovery
journal, May 2018

Goldsmith, Bryan R.; Esterhuizen, Jacques; Liu, Jin-Xun
AIChE Journal, Vol. 64, Issue 7
DOI: 10.1002/aic.16198

Data Mining the C−C Cross‐Coupling Genome
journal, May 2019

Sawatlon, Boodsarin; Wodrich, Matthew D.; Meyer, Benjamin
ChemCatChem, Vol. 11, Issue 16
DOI: 10.1002/cctc.201900597

Methane Chemisorption on Oxide‐Supported Pt Single Atom
journal, July 2019

Fung, Victor; Hu, Guoxiang; Tao, Franklin (Feng)
ChemPhysChem, Vol. 20, Issue 17
DOI: 10.1002/cphc.201900497

Making machine learning a useful tool in the accelerated discovery of transition metal complexes
journal, July 2019

Kulik, Heather J.
WIREs Computational Molecular Science, Vol. 10, Issue 1
DOI: 10.1002/wcms.1439

Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning
journal, August 2018

Lu, Shuaihua; Zhou, Qionghua; Ouyang, Yixin
Nature Communications, Vol. 9, Issue 1
DOI: 10.1038/s41467-018-05761-w

The basis for reevaluating the reactivity of pyrite surfaces: spin states and crystal field d-orbital splitting energies of bulk, terrace, edge, and corner Fe( ii ) ions
journal, January 2019

Arumugam, Krishnamoorthy; Renock, Devon; Becker, Udo
Physical Chemistry Chemical Physics, Vol. 21, Issue 12
DOI: 10.1039/c8cp05459b

Towards operando computational modeling in heterogeneous catalysis
journal, January 2018

Grajciar, Lukáš; Heard, Christopher J.; Bondarenko, Anton A.
Chemical Society Reviews, Vol. 47, Issue 22
DOI: 10.1039/c8cs00398j

Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery
journal, January 2018

Meredig, Bryce; Antono, Erin; Church, Carena
Molecular Systems Design & Engineering, Vol. 3, Issue 5
DOI: 10.1039/c8me00012c

Machine learning meets volcano plots: computational discovery of cross-coupling catalysts
journal, January 2018

Meyer, Benjamin; Sawatlon, Boodsarin; Heinen, Stefan
Chemical Science, Vol. 9, Issue 35
DOI: 10.1039/c8sc01949e

Mapping binary copolymer property space with neural networks
journal, January 2019

Wilbraham, Liam; Sprick, Reiner Sebastian; Jelfs, Kim E.
Chemical Science, Vol. 10, Issue 19
DOI: 10.1039/c8sc05710a

Benchmarking quantum chemistry methods for spin-state energetics of iron complexes against quantitative experimental data
journal, January 2019

Radoń, Mariusz
Physical Chemistry Chemical Physics, Vol. 21, Issue 9
DOI: 10.1039/c9cp00105k

Hammett neural networks: prediction of frontier orbital energies of tungsten–benzylidyne photoredox complexes
journal, January 2019

Chang, Alexander M.; Freeze, Jessica G.; Batista, Victor S.
Chemical Science, Vol. 10, Issue 28
DOI: 10.1039/c9sc02339a

Machine learning for renewable energy materials
journal, January 2019

Gu, Geun Ho; Noh, Juhwan; Kim, Inkyung
Journal of Materials Chemistry A, Vol. 7, Issue 29
DOI: 10.1039/c9ta02356a

Designing promising molecules for organic solar cells via machine learning assisted virtual screening
journal, January 2019

Sahu, Harikrishna; Yang, Feng; Ye, Xiaobo
Journal of Materials Chemistry A, Vol. 7, Issue 29
DOI: 10.1039/c9ta04097h

In silico high throughput screening of bimetallic and single atom alloys using machine learning and ab initio microkinetic modelling
journal, January 2020

Saxena, Shivam; Khan, Tuhin Suvra; Jalid, Fatima
Journal of Materials Chemistry A, Vol. 8, Issue 1
DOI: 10.1039/c9ta07651d

Calculating spin crossover temperatures by a first-principles LDA+ U scheme with parameter U evaluated from GW
journal, October 2019

Zhang, Yachao
The Journal of Chemical Physics, Vol. 151, Issue 13
DOI: 10.1063/1.5124239

Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network
journal, August 2019

Zubatyuk, Roman; Smith, Justin S.; Leszczynski, Jerzy
Science Advances, Vol. 5, Issue 8
DOI: 10.1126/sciadv.aav6490

Figures / Tables found in this record:

Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.

Similar Records in DOE PAGES and OSTI.GOV collections:

Machine Learning Accelerates the Discovery of Design Rules and Exceptions in Stable Metal–Oxo Intermediate Formation

Journal Article Nandy, Aditya ; Zhu, Jiazhou ; Janet, Jon Paul ; ... - ACS Catalysis

Metal–oxo moieties are important catalytic intermediates in the selective partial oxidation of hydrocarbons and in water splitting. Stable metal–oxo species have reactive properties that vary depending on the spin state of the metal, complicating the development of structure–property relationships. To overcome these challenges, we train machine-learning (ML) models capable of predicting metal–oxo formation energies across a range of first-row metals, oxidation states, and spin states. Using connectivity-only features tailored for inorganic chemistry as inputs to kernel ridge regression or artificial neural network (ANN) ML models, we achieve good mean absolute errors (4–5 kcal/mol) on set-aside test data across a rangemore »« less
Cited by 10
DOI: 10.1021/acscatal.9b02165

Full Text Available
Large-scale comparison of 3d and 4d transition metal complexes illuminates the reduced effect of exchange on second-row spin-state energetics

Journal Article Nandy, Aditya ; Chu, Daniel K. ; Harper, Daniel R. ; ... - Physical Chemistry Chemical Physics. PCCP (Print)

Density functional theory (DFT) is widely used in transition-metal chemistry, yet essential properties such as spin-state energetics in transition-metal complexes (TMCs) are well known to be sensitive to the choice of the exchange–correlation functional. Increasing the amount of exchange in a functional typically shifts the preferred ground state in first-row TMCs from low-spin to high-spin by penalizing delocalization error, but the effect on properties of second-row complexes is less well known. We compare the exchange sensitivity of adiabatic spin-splitting energies in pairs of mononuclear 3d and 4d mid-row octahedral transition-metal complexes. We analyze hundreds of complexes assembled from four metalsmore »« less
DOI: 10.1039/D0CP02977G
Designing in the Face of Uncertainty: Exploiting Electronic Structure and Machine Learning Models for Discovery in Inorganic Chemistry

Journal Article Janet, Jon Paul ; Liu, Fang ; Nandy, Aditya ; ... - Inorganic Chemistry

Recent transformative advances in computing power and algorithms have made computational chemistry central to the discovery and design of new molecules and materials. First-principles simulations are increasingly accurate and applicable to large systems with the speed needed for high-throughput computational screening. Despite these strides, the combinatorial challenges associated with the vastness of chemical space mean that more than just fast and accurate computational tools are needed for accelerated chemical discovery. In transition-metal chemistry and catalysis, unique challenges arise. The variable spin, oxidation state, and coordination environments favored by elements with well-localized d or f electrons provide great opportunity for tailoringmore »« less
Cited by 14
DOI: 10.1021/acs.inorgchem.9b00109
Seeing Is Believing: Experimental Spin States from Machine Learning Model Structure Predictions

Journal Article Taylor, Michael G. ; Yang, Tzuhsiung ; Lin, Sean ; ... - Journal of Physical Chemistry. A, Molecules, Spectroscopy, Kinetics, Environment, and General Theory

Determination of ground-state spins of open-shell transition-metal complexes is critical to understanding catalytic and materials properties but also challenging with approximate electronic structure methods. As an alternative approach, we demonstrate how structure alone can be used to guide assignment of ground-state spin from experimentally determined crystal structures of transition-metal complexes. We first identify the limits of distance-based heuristics from distributions of metal-ligand bond lengths of over 2000 unique mononuclear Fe(II)/Fe(III) transition-metal complexes. To overcome these limits, we employ artificial neural networks (ANNs) to predict spin-state-dependent metal-ligand bond lengths and classify experimental ground-state spins based on agreement of experimental structures withmore »« less
DOI: 10.1021/acs.jpca.0c01458
Accurate Multiobjective Design in a Space of Millions of Transition Metal Complexes with Neural-Network-Driven Efficient Global Optimization

Journal Article Janet, Jon Paul ; Ramesh, Sahasrajit ; Duan, Chenru ; ... - ACS Central Science

The accelerated discovery of materials for real world applications requires the achievement of multiple design objectives. The multidimensional nature of the search necessitates exploration of multimillion compound libraries over which even density functional theory (DFT) screening is intractable. Machine learning (e.g., artificial neural network, ANN, or Gaussian process, GP) models for this task are limited by training data availability and predictive uncertainty quantification (UQ). We overcome such limitations by using efficient global optimization (EGO) with the multidimensional expected improvement (EI) criterion. EGO balances exploitation of a trained model with acquisition of new DFT data at the Pareto front, the regionmore »« less
Cited by 5
DOI: 10.1021/acscentsci.0c00026

Similar Records

Title: Accelerating Chemical Discovery with Machine Learning: Simulated Evolution of Spin Crossover Complexes with an Artificial Neural Network

Abstract

Citation Formats

Figures / Tables:

Enumeration of de novo inorganic complexes for chemical discovery and machine learning journal, January 2020

Enumeration of de novo inorganic complexes for chemical discovery and machine learning journal, January 2020

Toward Predicting Efficiency of Organic Solar Cells via Machine Learning and Improved Descriptors journal, July 2018

Machine learning for heterogeneous catalyst design and discovery journal, May 2018

Data Mining the C−C Cross‐Coupling Genome journal, May 2019

Methane Chemisorption on Oxide‐Supported Pt Single Atom journal, July 2019

Making machine learning a useful tool in the accelerated discovery of transition metal complexes journal, July 2019

Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning journal, August 2018

The basis for reevaluating the reactivity of pyrite surfaces: spin states and crystal field d-orbital splitting energies of bulk, terrace, edge, and corner Fe( ii ) ions journal, January 2019

Towards operando computational modeling in heterogeneous catalysis journal, January 2018

Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery journal, January 2018

Machine learning meets volcano plots: computational discovery of cross-coupling catalysts journal, January 2018

Mapping binary copolymer property space with neural networks journal, January 2019

Benchmarking quantum chemistry methods for spin-state energetics of iron complexes against quantitative experimental data journal, January 2019

Hammett neural networks: prediction of frontier orbital energies of tungsten–benzylidyne photoredox complexes journal, January 2019

Machine learning for renewable energy materials journal, January 2019

Designing promising molecules for organic solar cells via machine learning assisted virtual screening journal, January 2019

In silico high throughput screening of bimetallic and single atom alloys using machine learning and ab initio microkinetic modelling journal, January 2020

Calculating spin crossover temperatures by a first-principles LDA+ U scheme with parameter U evaluated from GW journal, October 2019

Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network journal, August 2019

Enumeration of de novo inorganic complexes for chemical discovery and machine learning
journal, January 2020

Enumeration of de novo inorganic complexes for chemical discovery and machine learning
journal, January 2020

Toward Predicting Efficiency of Organic Solar Cells via Machine Learning and Improved Descriptors
journal, July 2018

Machine learning for heterogeneous catalyst design and discovery
journal, May 2018

Data Mining the C−C Cross‐Coupling Genome
journal, May 2019

Methane Chemisorption on Oxide‐Supported Pt Single Atom
journal, July 2019

Making machine learning a useful tool in the accelerated discovery of transition metal complexes
journal, July 2019

Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning
journal, August 2018

The basis for reevaluating the reactivity of pyrite surfaces: spin states and crystal field d-orbital splitting energies of bulk, terrace, edge, and corner Fe( ii ) ions
journal, January 2019

Towards operando computational modeling in heterogeneous catalysis
journal, January 2018

Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery
journal, January 2018

Machine learning meets volcano plots: computational discovery of cross-coupling catalysts
journal, January 2018

Mapping binary copolymer property space with neural networks
journal, January 2019

Benchmarking quantum chemistry methods for spin-state energetics of iron complexes against quantitative experimental data
journal, January 2019

Hammett neural networks: prediction of frontier orbital energies of tungsten–benzylidyne photoredox complexes
journal, January 2019

Machine learning for renewable energy materials
journal, January 2019

Designing promising molecules for organic solar cells via machine learning assisted virtual screening
journal, January 2019

In silico high throughput screening of bimetallic and single atom alloys using machine learning and ab initio microkinetic modelling
journal, January 2020

Calculating spin crossover temperatures by a first-principles LDA+ U scheme with parameter U evaluated from GW
journal, October 2019

Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network
journal, August 2019