Probing the properties of molecules and complex materials using machine learning
David A. Winkler
A B C *
+ Author Affiliations
- Author Affiliations
A Biochemistry and Chemistry, School of Agriculture, Biology and Engineering and La Trobe Institute for Molecular Science, La Trobe University, Bundoora, 3046, Australia.
B School of Medicinal Chemistry, Monash Institute of Pharmaceutical Science, Monash University, Parkville, 3154, Australia.
C School of Pharmacy, University of Nottingham, Nottingham, NG7 2QL, UK.
Australian Journal of Chemistry 75(11) 906-922 https://doi.org/10.1071/CH22138
Submitted: 16 June 2022 Accepted: 29 July 2022 Published: 13 September 2022
© 2022 The Author(s) (or their employer(s)). Published by CSIRO Publishing. This is an open access article distributed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND)
Abstract
The application of machine learning to predicting the properties of small and large discrete (single) molecules and complex materials (polymeric, extended or mixtures of molecules) has been increasing exponentially over the past few decades. Unlike physics-based and rule-based computational systems, machine learning algorithms can learn complex relationships between physicochemical and process parameters and their useful properties for an extremely diverse range of molecular entities. Both the breadth of machine learning methods and the range of physical, chemical, materials, biological, medical and many other application areas have increased markedly in the past decade. This Account summarises three decades of research into improved cheminformatics and machine learning methods and their application to drug design, regenerative medicine, biomaterials, porous and 2D materials, catalysts, biomarkers, surface science, physicochemical and phase properties, nanomaterials, electrical and optical properties, corrosion and battery research.
Keywords: artificial intelligence, batteries, Bayesian methods, biomaterials, catalysts, complex systems, computational molecular design, drug design, machine learning, nanomaterials, organic photovoltaic (OPV) devices, porous materials, quantitative structure-activity relationships (QSAR), regenerative medicine, science, 2D materials.
References
[1] T Fujita, DA Winkler, Understanding the Roles of the “Two QSARs”. J Chem Inf Model 2016, 56, 269.| Understanding the Roles of the “Two QSARs”.Crossref | GoogleScholarGoogle Scholar |
[2] Mitchell M. Complexity: a guided tour. New York: Oxford University Press; 2011.
[3] JD Halley, DA Winkler, Consistent concepts of self‐organization and self‐assembly. Complexity 2008, 14, 10.
| Consistent concepts of self‐organization and self‐assembly.Crossref | GoogleScholarGoogle Scholar |
[4] JD Halley, DA Winkler, Classification of emergence and its relation to self‐organization. Complexity 2008, 13, 10.
| Classification of emergence and its relation to self‐organization.Crossref | GoogleScholarGoogle Scholar |
[5] JD Halley, DA Winkler, Classification of self-organization and emergence in chemical and biological systems. Aust J Chem 2006, 59, 849.
| Classification of self-organization and emergence in chemical and biological systems.Crossref | GoogleScholarGoogle Scholar |
[6] T Le, VC Epa, FR Burden, DA Winkler, Quantitative structure-property relationship modeling of diverse materials properties. Chem Rev 2012, 112, 2889.
| Quantitative structure-property relationship modeling of diverse materials properties.Crossref | GoogleScholarGoogle Scholar |
[7] EN Muratov, J Bajorath, RP Sheridan, IV Tetko, D Filimonov, V Poroikov, et al. QSAR without borders. Chem Soc Rev 2020, 49, 3525.
| QSAR without borders.Crossref | GoogleScholarGoogle Scholar |
[8] FR Burden, MJ Polley, DA Winkler, Toward novel universal descriptors: charge fingerprints. J Chem Inf Model 2009, 49, 710.
| Toward novel universal descriptors: charge fingerprints.Crossref | GoogleScholarGoogle Scholar |
[9] FR Burden, A Chemically Intuitive Molecular Index Based on the Eigenvalues of a Modified Adjacency Matrix. Quant Struct-Act Relat 1997, 16, 309.
| A Chemically Intuitive Molecular Index Based on the Eigenvalues of a Modified Adjacency Matrix.Crossref | GoogleScholarGoogle Scholar |
[10] DA Winkler, FR Burden, AJR Watkins, Atomistic topological indices applied to benzodiazepines using various regression methods. Quant Struct-Act Relat 1998, 17, 14.
| Atomistic topological indices applied to benzodiazepines using various regression methods.Crossref | GoogleScholarGoogle Scholar |
[11] R Tibshirani, Regression Shrinkage and Selection via the Lasso. J R Stat Soc Series B Stat Methodol 1996, 58, 267.
| Regression Shrinkage and Selection via the Lasso.Crossref | GoogleScholarGoogle Scholar |
[12] FR Burden, DA Winkler, Optimal sparse descriptor selection for QSAR using Bayesian methods. QSAR Comb Sci 2009, 28, 645.
| Optimal sparse descriptor selection for QSAR using Bayesian methods.Crossref | GoogleScholarGoogle Scholar |
[13] FR Burden, MG Ford, DC Whitley, DA Winkler, Use of automatic relevance determination in QSAR studies using Bayesian neural networks. J Chem Inf Comput Sci 2000, 40, 1423.
| Use of automatic relevance determination in QSAR studies using Bayesian neural networks.Crossref | GoogleScholarGoogle Scholar |
[14] FR Burden, DA Winkler, An optimal self‐pruning neural network and nonlinear descriptor selection in QSAR. QSAR Comb Sci 2009, 28, 1092.
| An optimal self‐pruning neural network and nonlinear descriptor selection in QSAR.Crossref | GoogleScholarGoogle Scholar |
[15] Burden FR, Winkler DA. Bayesian Regularization of Neural Networks, in Artificial Neural Networks: Methods and Applications, In Livingston D, editor. Methods in Molecular Biology, Vol. 458. Totowa, NJ 07512 USA: Humana Press; 2009. pp 25‐44. ISBN: 978‐1‐58829‐718‐1
[16] DA Winkler, Sparse QSAR modelling methods for therapeutic and regenerative medicine. J Comput Aided Mol Des 2018, 32, 497.
| Sparse QSAR modelling methods for therapeutic and regenerative medicine.Crossref | GoogleScholarGoogle Scholar |
[17] FR Burden, DA Winkler, Robust QSAR models using Bayesian regularized neural networks. J Med Chem 1999, 42, 3183.
| Robust QSAR models using Bayesian regularized neural networks.Crossref | GoogleScholarGoogle Scholar |
[18] FR Burden, DA Winkler, Relevance Vector Machines: Sparse Classification Methods for QSAR. J Chem Inf Model 2015, 55, 1529.
| Relevance Vector Machines: Sparse Classification Methods for QSAR.Crossref | GoogleScholarGoogle Scholar |
[19] DA Winkler, Potent antimalarial drugs with validated activities. Nat Mach Intell 2022, 4, 102.
| Potent antimalarial drugs with validated activities.Crossref | GoogleScholarGoogle Scholar |
[20] X Tong, X Liu, X Tan, X Li, J Jiang, Z Xiong, et al. Generative Models for De Novo Drug Design. J Med Chem 2021, 64, 14011.
| Generative Models for De Novo Drug Design.Crossref | GoogleScholarGoogle Scholar |
[21] DA Winkler, TC Le, Performance of Deep and Shallow Neural Networks, the Universal Approximation Theorem, Activity Cliffs, and QSAR. Mol Inform 2017, 36, 1600118.
| Performance of Deep and Shallow Neural Networks, the Universal Approximation Theorem, Activity Cliffs, and QSAR.Crossref | GoogleScholarGoogle Scholar |
[22] H Mai, TC Le, T Hisatomi, D Chen, K Domen, DA Winkler, et al. Use of Meta Models for Rapid Discovery of Narrow Bandgap Oxide Photocatalysts. iScience 2021, 24, 103068.
| Use of Meta Models for Rapid Discovery of Narrow Bandgap Oxide Photocatalysts.Crossref | GoogleScholarGoogle Scholar |
[23] M Fronzi, O Isayev, DA Winkler, JG Shapter, AV Ellis, PC Sherrell, et al. Active learning in Bayesian neural networks for bandgap predictions of novel Van der Waals heterostructures. Adv Intell Syst 2021, 3, 2100080.
| Active learning in Bayesian neural networks for bandgap predictions of novel Van der Waals heterostructures.Crossref | GoogleScholarGoogle Scholar |
[24] DLJ Alexander, A Tropsha, DA Winkler, Beware of R2: Simple, Unambiguous Assessment of the Prediction Accuracy of QSAR and QSPR Models. J Chem Inf Model 2015, 55, 1316.
| Beware of R2: Simple, Unambiguous Assessment of the Prediction Accuracy of QSAR and QSPR Models.Crossref | GoogleScholarGoogle Scholar |
[25] RD Cramer, DE Patterson, JD Bunce, Comparative molecular field analysis (CoMFA). 1. Effect of shape on binding of steroids to carrier proteins. J Am Chem Soc 1988, 110, 5959.
| Comparative molecular field analysis (CoMFA). 1. Effect of shape on binding of steroids to carrier proteins.Crossref | GoogleScholarGoogle Scholar |
[26] FR Burden, BS Rosewarne, DA Winkler, Predicting maximum bioactivity by effective inversion of neural networks using genetic algorithms. Chemometr Intell Lab Syst 1997, 38, 127.
| Predicting maximum bioactivity by effective inversion of neural networks using genetic algorithms.Crossref | GoogleScholarGoogle Scholar |
[27] P Mikulskis, MR Alexander, DA Winkler, Toward interpretable machine learning models for materials discovery. Adv Intell Syst 2019, 1, 1900045.
| Toward interpretable machine learning models for materials discovery.Crossref | GoogleScholarGoogle Scholar |
[28] T Würger, D Mei, B Vaghefinazari, DA Winkler, SV Lamaka, ML Zheludkevich, et al. Exploring structure-property relationships in magnesium dissolution modulators. npj Mater Degrad 2021, 5, 2.
| Exploring structure-property relationships in magnesium dissolution modulators.Crossref | GoogleScholarGoogle Scholar |
[29] DA Winkler, FR Burden, Robust, quantitative tools for modelling ex-vivo expansion of haematopoietic stem cells and progenitors. Mol Biosyst 2012, 8, 913.
| Robust, quantitative tools for modelling ex-vivo expansion of haematopoietic stem cells and progenitors.Crossref | GoogleScholarGoogle Scholar |
[30] AD Celiz, JGW Smith, AK Patel, AL Hook, D Rajamohan, VT George, et al. Discovery of a Novel Polymer for Human Pluripotent Stem Cell Expansion and Multilineage Differentiation. Adv Mater 2015, 27, 4006.
| Discovery of a Novel Polymer for Human Pluripotent Stem Cell Expansion and Multilineage Differentiation.Crossref | GoogleScholarGoogle Scholar |
[31] AD Celiz, JGW Smith, R Langer, DG Anderson, DA Winkler, DA Barrett, et al. Materials for stem cell factories of the future. Nat Mater 2014, 13, 570.
| Materials for stem cell factories of the future.Crossref | GoogleScholarGoogle Scholar |
[32] S Rasi Ghaemi, B Delalat, S Gronthos, MR Alexander, DA Winkler, AL Hook, et al. High-Throughput Assessment and Modeling of a Polymer Library Regulating Human Dental Pulp-Derived Stem Cell Behavior. ACS Appl Mater Interfaces 2018, 10, 38739.
| High-Throughput Assessment and Modeling of a Polymer Library Regulating Human Dental Pulp-Derived Stem Cell Behavior.Crossref | GoogleScholarGoogle Scholar |
[33] VC Epa, J Yang, Y Mei, AL Hook, R Langer, DG Anderson, et al. Modelling human embryoid body cell adhesion to a combinatorial library of polymer surfaces. J Mater Chem 2012, 22, 20902.
| Modelling human embryoid body cell adhesion to a combinatorial library of polymer surfaces.Crossref | GoogleScholarGoogle Scholar |
[34] H Autefage, E Gentleman, E Littmann, MAB Hedegaard, T Von Erlach, M O’Donnell, et al. Sparse feature selection methods identify unexpected global cellular response to strontium-containing materials. Proc Natl Acad Sci U S A 2015, 112, 4280.
| Sparse feature selection methods identify unexpected global cellular response to strontium-containing materials.Crossref | GoogleScholarGoogle Scholar |
[35] YH Huh, M Noh, FR Burden, JC Chen, DA Winkler, JL Sherley, Sparse feature selection identifies H2A.Z as a novel, pattern-specific biomarker for asymmetrically self-renewing distributed stem cells. Stem Cell Res 2015, 14, 144.
| Sparse feature selection identifies H2A.Z as a novel, pattern-specific biomarker for asymmetrically self-renewing distributed stem cells.Crossref | GoogleScholarGoogle Scholar |
[36] TC Le, M Ballard, P Casey, MS Liu, DA Winkler, Illuminating Flash Point: Comprehensive Prediction Models. Mol Inform 2015, 34, 18.
| Illuminating Flash Point: Comprehensive Prediction Models.Crossref | GoogleScholarGoogle Scholar |
[37] M Salahinejad, TC Le, DA Winkler, Capturing the crystal: prediction of enthalpy of sublimation, crystal lattice energy, and melting points of organic compounds. J Chem Inf Model 2013, 53, 223.
| Capturing the crystal: prediction of enthalpy of sublimation, crystal lattice energy, and melting points of organic compounds.Crossref | GoogleScholarGoogle Scholar |
[38] M Salahinejad, TC Le, DA Winkler, Aqueous solubility prediction: do crystal lattice interactions help? Mol Pharm 2013, 10, 2757.
| Aqueous solubility prediction: do crystal lattice interactions help?Crossref | GoogleScholarGoogle Scholar |
[39] II Baskin, D Winkler, IV Tetko, A renaissance of neural networks in drug discovery. Expert Opin Drug Discov 2016, 11, 785.
| A renaissance of neural networks in drug discovery.Crossref | GoogleScholarGoogle Scholar |
[40] TC Le, X Mulet, FR Burden, DA Winkler, Predicting the complex phase behavior of self-assembling drug delivery nanoparticles. Mol Pharm 2013, 10, 1368.
| Predicting the complex phase behavior of self-assembling drug delivery nanoparticles.Crossref | GoogleScholarGoogle Scholar |
[41] BTC Le, N Tran, X Mulet, DA Winkler, Modeling the Influence of Fatty Acid Incorporation on Mesophase Formation in Amphiphilic Therapeutic Delivery Systems. Mol Pharm 2016, 13, 996.
| Modeling the Influence of Fatty Acid Incorporation on Mesophase Formation in Amphiphilic Therapeutic Delivery Systems.Crossref | GoogleScholarGoogle Scholar |
[42] TC Le, CE Conn, FR Burden, DA Winkler, Computational modeling and prediction of the complex time-dependent phase behavior of lyotropic liquid crystals under in meso crystallization conditions. Crystal Growth Des 2013, 13, 1267.
| Computational modeling and prediction of the complex time-dependent phase behavior of lyotropic liquid crystals under in meso crystallization conditions.Crossref | GoogleScholarGoogle Scholar |
[43] MJ Polley, FR Burden, DA Winkler, Predictive human intestinal absorption QSAR models using Bayesian regularized neural networks. Aust J Chem 2005, 58, 859.
| Predictive human intestinal absorption QSAR models using Bayesian regularized neural networks.Crossref | GoogleScholarGoogle Scholar |
[44] DA Winkler, FR Burden, Modelling blood-brain barrier partitioning using Bayesian neural nets. J Mol Graph Model 2004, 22, 499.
| Modelling blood-brain barrier partitioning using Bayesian neural nets.Crossref | GoogleScholarGoogle Scholar |
[45] MJ Sorich, P Smith, D Winkler, FR Burden, R McKinnon, J Miners, In Silico Prediction of Chemical Metabolism by Human Udp-Glucuronosyltransferase Isoforms: Evaluation of Classification Algorithms. Drug Metab Rev 2003, 35, 167.
[46] MJ Sorich, JO Miners, RA McKinnon, DA Winkler, FR Burden, PA Smith, Comparison of linear and nonlinear classification algorithms for the prediction of drug and chemical metabolism by human UDP-glucuronosyltransferase isoforms. J Chem Inf Comput Sci 2003, 43, 2019.
| Comparison of linear and nonlinear classification algorithms for the prediction of drug and chemical metabolism by human UDP-glucuronosyltransferase isoforms.Crossref | GoogleScholarGoogle Scholar |
[47] MJ Sorich, RA McKinnon, JO Miners, DA Winkler, PA Smith, Rapid prediction of chemical metabolism by human UDP-glucuronosyltransferase isoforms using quantum chemical descriptors derived with the electronegativity equalization method. J Med Chem 2004, 47, 5311.
| Rapid prediction of chemical metabolism by human UDP-glucuronosyltransferase isoforms using quantum chemical descriptors derived with the electronegativity equalization method.Crossref | GoogleScholarGoogle Scholar |
[48] MJ Polley, DA Winkler, FR Burden, Broad-based quantitative structure-activity relationship modeling of potency and selectivity of farnesyltransferase inhibitors using a Bayesian regularized neural network. J Med Chem 2004, 47, 6230.
| Broad-based quantitative structure-activity relationship modeling of potency and selectivity of farnesyltransferase inhibitors using a Bayesian regularized neural network.Crossref | GoogleScholarGoogle Scholar |
[49] FR Burden, DA Winkler, A quantitative structure–activity relationships model for the acute toxicity of substituted benzenes to Tetrahymena pyriformis using Bayesian-regularized neural networks. Chem Res Toxicol 2000, 13, 436.
| A quantitative structure–activity relationships model for the acute toxicity of substituted benzenes to Tetrahymena pyriformis using Bayesian-regularized neural networks.Crossref | GoogleScholarGoogle Scholar |
[50] DA Winkler, FR Burden, Bayesian neural nets for modeling in drug discovery. Drug Discov Today: BIOSILICO 2004, 2, 104.
| Bayesian neural nets for modeling in drug discovery.Crossref | GoogleScholarGoogle Scholar |
[51] DA Winkler, Neural networks as robust tools in drug lead discovery and development. Mol Biotechnol 2004, 27, 139.
| Neural networks as robust tools in drug lead discovery and development.Crossref | GoogleScholarGoogle Scholar |
[52] DA Winkler, Neural networks in ADME and toxicity prediction. Drugs Future 2004, 29, 1043.
| Neural networks in ADME and toxicity prediction.Crossref | GoogleScholarGoogle Scholar |
[53] DA Winkler, Use of Artificial Intelligence and Machine Learning for Discovery of Drugs for Neglected Tropical Diseases. Front Chem 2021, 9, 614073.
| Use of Artificial Intelligence and Machine Learning for Discovery of Drugs for Neglected Tropical Diseases.Crossref | GoogleScholarGoogle Scholar |
[54] VC Epa, AL Hook, C Chang, J Yang, R Langer, DG Anderson, et al. Modelling and prediction of bacterial attachment to polymers. Adv Funct Mater 2014, 24, 2085.
| Modelling and prediction of bacterial attachment to polymers.Crossref | GoogleScholarGoogle Scholar |
[55] P Mikulskis, A Hook, AA Dundas, D Irvine, O Sanni, D Anderson, et al. Prediction of Broad-Spectrum Pathogen Attachment to Coating Materials for Biomedical Devices. ACS Appl Mater Interfaces 2018, 10, 139.
| Prediction of Broad-Spectrum Pathogen Attachment to Coating Materials for Biomedical Devices.Crossref | GoogleScholarGoogle Scholar |
[56] TC Le, M Penna, DA Winkler, I Yarovsky, Quantitative design rules for protein-resistant surface coatings using machine learning. Sci Rep 2019, 9, 265.
| Quantitative design rules for protein-resistant surface coatings using machine learning.Crossref | GoogleScholarGoogle Scholar |
[57] L Burroughs, MH Amer, M Vassey, B Koch, GP Figueredo, B Mukonoweshuro, et al. Discovery of synergistic material-topography combinations to achieve immunomodulatory osteoinductive biomaterials using a novel in vitro screening method: The ChemoTopoChip. Biomaterials 2021, 271, 120740.
| Discovery of synergistic material-topography combinations to achieve immunomodulatory osteoinductive biomaterials using a novel in vitro screening method: The ChemoTopoChip.Crossref | GoogleScholarGoogle Scholar |
[58] MJ Vassey, GP Figueredo, DJ Scurr, AS Vasilevich, S Vermeulen, A Carlier, et al. Immune Modulation by Design: Using Topography to Control Human Monocyte Attachment and Macrophage Differentiation. Adv Sci (Weinh) 2020, 7, 1903392.
| Immune Modulation by Design: Using Topography to Control Human Monocyte Attachment and Macrophage Differentiation.Crossref | GoogleScholarGoogle Scholar |
[59] A Vasilevich, A Carlier, DA Winkler, S Singh, J de Boer, Evolutionary design of optimal surface topographies for biomaterials. Sci Rep 2020, 10, 22160.
| Evolutionary design of optimal surface topographies for biomaterials.Crossref | GoogleScholarGoogle Scholar |
[60] C Feiler, D Mei, SV Lamaka, T Würger, RH Meißner, DA Winkler, BJC Luthringer-Feyerabend, et al. In silico Screening of Modulators of Magnesium Dissolution. Corros Sci 2019, 163, 108245.
| In silico Screening of Modulators of Magnesium Dissolution.Crossref | GoogleScholarGoogle Scholar |
[61] DA Winkler, M Breedon, AE Hughes, FR Burden, AS Barnard, TG Harvey, et al. Towards chromate-free corrosion inhibitors: structure–property models for organic alternatives. Green Chem 2014, 16, 3349.
| Towards chromate-free corrosion inhibitors: structure–property models for organic alternatives.Crossref | GoogleScholarGoogle Scholar |
[62] DA Winkler, M Breedon, P White, AE Hughes, ED Sapper, I Cole, Using high throughput experimental data and in silico models to discover alternatives to toxic chromate corrosion inhibitors. Corros Sci 2016, 106, 229.
| Using high throughput experimental data and in silico models to discover alternatives to toxic chromate corrosion inhibitors.Crossref | GoogleScholarGoogle Scholar |
[63] SA Tawfik, O Isayev, C Stampfl, J Shapter, DA Winkler, MJ Ford, Efficient Prediction of Structural and Electronic Properties of Hybrid 2D Materials Using Complementary DFT and Machine Learning Approaches. Adv Theor Simul 2019, 2, 1800128.
| Efficient Prediction of Structural and Electronic Properties of Hybrid 2D Materials Using Complementary DFT and Machine Learning Approaches.Crossref | GoogleScholarGoogle Scholar |
[64] SA Tawfik, O Isayev, DA Winkler, M Spencer, Predicting thermal properties of crystals using machine learning. Adv Theor Simul 2019, 3, 1900208.
| Predicting thermal properties of crystals using machine learning.Crossref | GoogleScholarGoogle Scholar |
[65] M Fronzi, SA Tawfik, MA Ghazaleh, O Isayev, DA Winkler, J Shapter, MJ Ford, High Throughput Screening of Millions of van der Waals Heterostructures for Superlubricant Applications. Adv Theor Simul 2020, 3, 2000029.
| High Throughput Screening of Millions of van der Waals Heterostructures for Superlubricant Applications.Crossref | GoogleScholarGoogle Scholar |
[66] TC Le, H Yin, R Chen, Y Chen, L Zhao, PS Casey, et al. An Experimental and Computational Approach to the Development of ZnO Nanoparticles that are Safe by Design. Small 2016, 12, 3568.
| An Experimental and Computational Approach to the Development of ZnO Nanoparticles that are Safe by Design.Crossref | GoogleScholarGoogle Scholar |
[67] DA Winkler, Role of Artificial Intelligence and Machine Learning in Nanosafety. Small 2020, 16, e2001883.
| Role of Artificial Intelligence and Machine Learning in Nanosafety.Crossref | GoogleScholarGoogle Scholar |
[68] VC Epa, FR Burden, C Tassa, R Weissleder, S Shaw, DA Winkler, Modeling biological activities of nanoparticles. Nano Lett 2012, 12, 5808.
| Modeling biological activities of nanoparticles.Crossref | GoogleScholarGoogle Scholar |
[69] DA Winkler, Recent advances, and unresolved issues, in the application of computational modelling to the prediction of the biological effects of nanomaterials. Toxicol Appl Pharmacol 2016, 299, 96.
| Recent advances, and unresolved issues, in the application of computational modelling to the prediction of the biological effects of nanomaterials.Crossref | GoogleScholarGoogle Scholar |
[70] DA Winkler, E Mombelli, A Pietroiusti, L Tran, A Worth, B Fadeel, et al. Applying quantitative structure-activity relationship approaches to nanotoxicology: current status and future potential. Toxicology 2013, 313, 15.
| Applying quantitative structure-activity relationship approaches to nanotoxicology: current status and future potential.Crossref | GoogleScholarGoogle Scholar |
[71] W Gardner, R Maliki, SM Cutts, BW Muir, D Ballabio, DA Winkler, et al. Self-Organizing Map and Relational Perspective Mapping for the accurate visualization of high-dimensional hyperspectral data. Anal Chem 2020, 92, 10450.
| Self-Organizing Map and Relational Perspective Mapping for the accurate visualization of high-dimensional hyperspectral data.Crossref | GoogleScholarGoogle Scholar |
[72] W Gardner, DA Winkler, SM Cutts, SA Torney, GA Pietersz, BW Muir, PJ Pigram, Two-Dimensional and Three-Dimensional Time-of-Flight Secondary Ion Mass Spectrometry Image Feature Extraction Using a Spatially Aware Convolutional Autoencoder. Anal Chem 2022, 94, 7804.
| Two-Dimensional and Three-Dimensional Time-of-Flight Secondary Ion Mass Spectrometry Image Feature Extraction Using a Spatially Aware Convolutional Autoencoder.Crossref | GoogleScholarGoogle Scholar |
[73] W Gardner, DA Winkler, D Ballabio, BW Muir, PJ Pigram, Analyzing 3D hyperspectral TOF-SIMS depth profile data using self-organizing map-relational perspective mapping. Biointerphases 2020, 15, 061004.
| Analyzing 3D hyperspectral TOF-SIMS depth profile data using self-organizing map-relational perspective mapping.Crossref | GoogleScholarGoogle Scholar |
[74] W Gardner, DA Winkler, SM Cutts, SA Torney, GA Pietersz, BW Muir, et al. Two-Dimensional and Three-Dimensional Time-of-Flight Secondary Ion Mass Spectrometry Image Feature Extraction Using a Spatially Aware Convolutional Autoencoder. Anal Chem 2022, 94, 7804.
| Two-Dimensional and Three-Dimensional Time-of-Flight Secondary Ion Mass Spectrometry Image Feature Extraction Using a Spatially Aware Convolutional Autoencoder.Crossref | GoogleScholarGoogle Scholar |
[75] W Gardner, DA Winkler, BW Muir, PJ Pigram, Applications of multivariate analysis and unsupervised machine learning to ToF-SIMS images of organic, bioorganic, and biological systems. Biointerphases 2022, 17, 020802.
| Applications of multivariate analysis and unsupervised machine learning to ToF-SIMS images of organic, bioorganic, and biological systems.Crossref | GoogleScholarGoogle Scholar |
[76] H Mai, TC Le, D Chen, DA Winkler, RA Caruso, Machine Learning for Electrocatalyst and Photocatalyst Design and Discovery. Chem Rev 2022, 16, 13478.
| Machine Learning for Electrocatalyst and Photocatalyst Design and Discovery.Crossref | GoogleScholarGoogle Scholar |
[77] AW Thornton, DA Winkler, MS Liu, M Haranczyk, DF Kennedy, Towards computational design of zeolite catalysts for CO2 reduction. RSC Adv 2015, 5, 44361.
| Towards computational design of zeolite catalysts for CO2 reduction.Crossref | GoogleScholarGoogle Scholar |
[78] AW Thornton, CM Simon, J Kim, O Kwon, KS Deeg, K Konstas, et al. Materials Genome in Action: Identifying the Performance Limits of Physical Hydrogen Storage. Chem Mater 2017, 29, 2844.
| Materials Genome in Action: Identifying the Performance Limits of Physical Hydrogen Storage.Crossref | GoogleScholarGoogle Scholar |
[79] Y Bao, Y Ye, N Meftahi, I Lyskov, T Tian, S Kumar, et al. Machine Learning-assisted Exploration of a Universal Polymer Platform with Charge Transfer-dependent Full-color Emission. 2022,
| Machine Learning-assisted Exploration of a Universal Polymer Platform with Charge Transfer-dependent Full-color Emission.Crossref | GoogleScholarGoogle Scholar |
[80] N Meftahi, M Klymenko, AJ Christofferson, U Bach, DA Winkler, SP Russo, Machine Learning Property Prediction for Organic Photovoltaic Devices. npj Comput Mater 2020, 6, 166.
| Machine Learning Property Prediction for Organic Photovoltaic Devices.Crossref | GoogleScholarGoogle Scholar |
[81] Y Shen, JE Borowski, MA Hardy, R Sarpong, AG Doyle, T Cernak, Automation and computer-assisted planning for chemical synthesis. Nat Rev Methods Primers 2021, 1, 23.
| Automation and computer-assisted planning for chemical synthesis.Crossref | GoogleScholarGoogle Scholar |
[82] JS Smith, BT Nebgen, R Zubatyuk, N Lubbers, C Devereux, K Barros, et al. Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning. Nat Commun 2019, 10, 2903.
| Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning.Crossref | GoogleScholarGoogle Scholar |
[83] TC Le, DA Winkler, A Bright Future for Evolutionary Methods in Drug Design. ChemMedChem 2015, 10, 1296.
| A Bright Future for Evolutionary Methods in Drug Design.Crossref | GoogleScholarGoogle Scholar |
[84] DA Winkler, Biomimetic molecular design tools that learn, evolve, and adapt. Beilstein J Org Chem 2017, 13, 1288.
| Biomimetic molecular design tools that learn, evolve, and adapt.Crossref | GoogleScholarGoogle Scholar |
[85] TC Le, DA Winkler, Discovery and Optimization of Materials Using Evolutionary Approaches. Chem Rev 2016, 116, 6107.
| Discovery and Optimization of Materials Using Evolutionary Approaches.Crossref | GoogleScholarGoogle Scholar |
[86] V Dragone, V Sans, AB Henson, JM Granda, L Cronin, An autonomous organic reaction search engine for chemical reactivity. Nat Commun 2017, 8, 15733.
| An autonomous organic reaction search engine for chemical reactivity.Crossref | GoogleScholarGoogle Scholar |
[87] G Pilania, Machine learning in materials science: From explainable predictions to autonomous design. Comput Mater Sci 2021, 193, 110360.
| Machine learning in materials science: From explainable predictions to autonomous design.Crossref | GoogleScholarGoogle Scholar |
