{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:53:15Z","timestamp":1778759595006,"version":"3.51.4"},"reference-count":52,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T00:00:00Z","timestamp":1730678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T00:00:00Z","timestamp":1730678400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The development of next-generation polymers necessitates optimizing several key properties simultaneously, a task that is expensive and infeasible using traditional trial-and-error experimental approaches. A promising alternative is employing a combination of machine learning and physics-based tools to rapidly screen the polymer design space and provide suggestions of new polymers that meet the critical properties required for industrial applications. In this study, we introduce a comprehensive workflow that utilizes machine learning and molecular modeling approaches to design new polymers with the focus on improving five polymer properties: (1) glass transition temperature, (2) dielectric constant, (3) refractive index, (4) stress optic coefficient, and (5) linear coefficient of thermal expansion. Using a small dataset (<jats:inline-formula>\n                     <jats:tex-math\/>\n                     <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                           <mml:mo>&lt;<\/mml:mo>\n                        <\/mml:mrow>\n                     <\/mml:math>\n                  <\/jats:inline-formula>200 unique polymers), we developed quantitative structure-property relationships (QSPRs) models to accurately predict the experimental polymer properties for both homo- and co-polymer systems. We tested several ML algorithms and identified the best models for predicting these polymer properties, achieving test set <jats:italic>R<\/jats:italic>\n                  <jats:sup>2<\/jats:sup> greater than 0.77 across all properties. We then explored new polymers by creating a library of over \u223c10\u2009000 homopolymers using R-group enumeration tools and applied the trained QSPR models to rapidly predict the five polymer properties. The predictions of QSPR models were used to create a multi-parameter optimization score, which helped downselect the large polymer space to \u223c10 promising candidates. The properties of these selected polymer candidates were subsequently validated with classical molecular dynamics simulations and density functional theory, revealing a strong correlation with the QSPR model predictions. Finally, one of the top candidates was validated by experiments, which showed good agreement against QSPR and physics-based models. Our workflow underscores the power of combining data-driven and theoretical methods in the polymer design process given a small dataset size, offering a valuable resource for experimentalists looking to leverage computer-aided strategies in materials innovation.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad88d7","type":"journal-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T22:56:51Z","timestamp":1729292211000},"page":"045031","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Designing the next generation of polymers with machine learning and physics-based models"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7051-9778","authenticated-orcid":true,"given":"Alex K","family":"Chew","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8261-2024","authenticated-orcid":false,"given":"Mohammad Atif Faiz","family":"Afzal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anand","family":"Chandrasekaran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0435-0764","authenticated-orcid":false,"given":"Jan Henk","family":"Kamps","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2207-4812","authenticated-orcid":true,"given":"Vaidya","family":"Ramakrishnan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2024,11,4]]},"reference":[{"key":"mlstad88d7bib1","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1177\/8756087917691088","article-title":"A review of filled and pristine polycarbonate blends and their applications","volume":"34","author":"Kausar","year":"2018","journal-title":"J. Plast. Film Sheeting"},{"key":"mlstad88d7bib2","volume":"vol 9","author":"Schnell","year":"1964"},{"key":"mlstad88d7bib3","first-page":"p 38","author":"Christopher","year":"1962"},{"key":"mlstad88d7bib4","author":"Bendler","year":"1999"},{"key":"mlstad88d7bib5","doi-asserted-by":"crossref","DOI":"10.1021\/bk-2005-0898.ch001","article-title":"Advances in polycarbonates: an overview","author":"Brunelle","year":"2005"},{"key":"mlstad88d7bib6","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1021\/acsapm.0c00524","article-title":"High-throughput molecular dynamics simulations and validation of thermophysical properties of polymers for various applications","volume":"3","author":"Atif Faiz Afzal","year":"2020","journal-title":"ACS Appl. Polym. Mater."},{"key":"mlstad88d7bib7","doi-asserted-by":"publisher","first-page":"4291","DOI":"10.1021\/acs.jctc.1c00302","article-title":"OPLS4: improving force field accuracy on challenging regimes of chemical space","volume":"17","author":"Chao","year":"2021","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad88d7bib8","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-43804-5","article-title":"Development of scalable and generalizable machine learned force field for polymers","volume":"13","author":"Mohanty","year":"2023","journal-title":"Sci. Rep."},{"key":"mlstad88d7bib9","doi-asserted-by":"publisher","first-page":"14610","DOI":"10.1021\/acs.jpcc.9b01147","article-title":"Accelerated discovery of high-refractive-index polyimides via first-principles molecular modeling, virtual high-throughput screening and data mining","volume":"123","author":"Atif Faiz Afzal","year":"2019","journal-title":"J. Phys. Chem. C"},{"key":"mlstad88d7bib10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2021.100238","article-title":"Polymer informatics with multi-task learning","volume":"2","author":"Kuenneth","year":"2021","journal-title":"Patterns"},{"key":"mlstad88d7bib11","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1021\/acs.chemmater.2c02991","article-title":"Polymer informatics at scale with multitask graph neural networks","volume":"35","author":"Gurnani","year":"2023","journal-title":"Chem. Mater."},{"key":"mlstad88d7bib12","first-page":"pp 22","article-title":"Polyinfo: Polymer database for polymeric materials design","author":"Otsuka","year":"2011"},{"key":"mlstad88d7bib13","doi-asserted-by":"publisher","first-page":"17575","DOI":"10.1021\/acs.jpcc.8b02913","article-title":"Polymer genome: a data-powered polymer informatics platform for property predictions","volume":"122","author":"Kim","year":"2018","journal-title":"J. Phys. Chem. C"},{"key":"mlstad88d7bib14","doi-asserted-by":"publisher","first-page":"3021","DOI":"10.21105\/joss.03021","article-title":"Seaborn: statistical data visualization","volume":"6","author":"Waskom","year":"2021","journal-title":"J. Open Source Softw."},{"key":"mlstad88d7bib15","article-title":"Rdkit: Open-source cheminformatics","author":"Landrum"},{"key":"mlstad88d7bib16","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"mlstad88d7bib17","article-title":"LightGBM: a highly efficient gradient boosting decision tree","volume":"vol 30","author":"Guolin","year":"2017"},{"key":"mlstad88d7bib18","first-page":"pp 785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen","year":"2016"},{"key":"mlstad88d7bib19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-020-00479-8","article-title":"Could graph neural networks learn better molecular representation for drug discovery? a comparison study of descriptor-based and graph-based models","volume":"13","author":"Jiang","year":"2021","journal-title":"J. Cheminf."},{"key":"mlstad88d7bib20","doi-asserted-by":"publisher","first-page":"1825","DOI":"10.4155\/fmc-2016-0093","article-title":"Autoqsar: an automated machine learning tool for best-practice quantitative structure\u2013activity relationship modeling","volume":"8","author":"Dixon","year":"2016","journal-title":"Future Med. Chem."},{"key":"mlstad88d7bib21","article-title":"Version 2021-3 materials science suite","year":"2021"},{"key":"mlstad88d7bib22","article-title":"LiveDesign Release","year":"2021"},{"key":"mlstad88d7bib23","doi-asserted-by":"publisher","DOI":"10.3389\/fchem.2021.800370","article-title":"Design of organic electronic materials with a goal-directed generative model powered by deep neural networks and high-throughput molecular simulations","volume":"9","author":"Shaun Kwak","year":"2022","journal-title":"Front. Chem."},{"key":"mlstad88d7bib24","doi-asserted-by":"publisher","DOI":"10.3389\/fchem.2021.800371","article-title":"Active learning accelerates design and optimization of hole-transporting materials for organic electronics","volume":"9","author":"Abroshan","year":"2022","journal-title":"Front. Chem."},{"key":"mlstad88d7bib25","doi-asserted-by":"crossref","first-page":"5059","DOI":"10.1021\/acs.chemmater.3c00561","article-title":"High-throughput screening of hole transport materials for quantum dot light-emitting diodes","volume":"35","author":"Abroshan","year":"2023","journal-title":"Chem. Mater."},{"key":"mlstad88d7bib26","article-title":"Version 2022-1 materials science suite","year":"2022"},{"key":"mlstad88d7bib27","doi-asserted-by":"publisher","first-page":"6987","DOI":"10.1021\/acs.chemmater.3c00561","article-title":"Correlation between glass transition temperature and molecular mass in non\u2013polymeric and polymer glass formers","volume":"54","author":"Novikov","year":"2013","journal-title":"Polymer"},{"key":"mlstad88d7bib28","author":"Murray","year":"1997"},{"key":"mlstad88d7bib29","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1021\/acs.jctc.5b00864","article-title":"OPLS3: a force field providing broad coverage of drug-like small molecules and proteins","volume":"12","author":"Harder","year":"2016","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad88d7bib30","doi-asserted-by":"publisher","first-page":"1863","DOI":"10.1021\/acs.jctc.8b01026","article-title":"OPLS3: extending force field coverage for drug-like small molecules","volume":"15","author":"Roos","year":"2019","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad88d7bib31","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.1021\/ct900587b","article-title":"Prediction of absolute solvation free energies using molecular dynamics free energy perturbation and the opls force field","volume":"6","author":"Shivakumar","year":"2010","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad88d7bib32","doi-asserted-by":"publisher","first-page":"11225","DOI":"10.1021\/ja9621760","article-title":"Development and testing of the opls all-atom force field on conformational energetics and properties of organic liquids","volume":"118","author":"Jorgensen","year":"1996","journal-title":"J. Am. Chem. Soc."},{"key":"mlstad88d7bib33","doi-asserted-by":"publisher","first-page":"1657","DOI":"10.1021\/ja00214a001","article-title":"The opls [optimized potentials for liquid simulations] potential functions for proteins, energy minimizations for crystals of cyclic peptides and crambin","volume":"110","author":"Jorgensen","year":"1988","journal-title":"J. Am. Chem. Soc."},{"key":"mlstad88d7bib34","doi-asserted-by":"crossref","DOI":"10.1109\/SC.2006.54","article-title":"Scalable algorithms for molecular dynamics simulations on commodity clusters","author":"Bowers","year":"2006"},{"key":"mlstad88d7bib35","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1063\/1.447334","article-title":"A unified formulation of the constant temperature molecular dynamics methods","volume":"81","author":"Nos\u00e9","year":"1984","journal-title":"J. Chem. Phys."},{"key":"mlstad88d7bib36","doi-asserted-by":"publisher","first-page":"1695","DOI":"10.1103\/PhysRevA.31.1695","article-title":"Canonical dynamics: equilibrium phase-space distributions","volume":"31","author":"Hoover","year":"1985","journal-title":"Phys. Rev. A"},{"key":"mlstad88d7bib37","doi-asserted-by":"publisher","first-page":"4177","DOI":"10.1063\/1.467468","article-title":"Constant pressure molecular dynamics algorithms","volume":"101","author":"Martyna","year":"1994","journal-title":"J. Chem. Phys."},{"key":"mlstad88d7bib38","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1016\/j.polymer.2016.01.074","article-title":"Uncertainty quantification in molecular dynamics studies of the glass transition temperature","volume":"87","author":"Patrone","year":"2016","journal-title":"Polymer"},{"key":"mlstad88d7bib39","doi-asserted-by":"publisher","first-page":"5648","DOI":"10.1063\/1.464913","article-title":"Density-functional thermochemistry. III. The role of exact exchange","volume":"98","author":"Beck","year":"1993","journal-title":"J. Chem. Phys"},{"key":"mlstad88d7bib40","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1039\/C4CP04286G","article-title":"Development of new auxiliary basis functions of the karlsruhe segmented contracted basis sets including diffuse basis functions (def2-SVPD, def2-TZVPPD and def2-QVPPD) for RI-MP2 and RI-CC calculations","volume":"17","author":"Hellweg","year":"2015","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstad88d7bib41","doi-asserted-by":"publisher","first-page":"2110","DOI":"10.1002\/qua.24481","article-title":"Jaguar: a high-performance quantum chemistry software program with strengths in life and materials sciences","volume":"113","author":"Bochevarov","year":"2013","journal-title":"Int. J. Quantum Chem."},{"key":"mlstad88d7bib42","doi-asserted-by":"publisher","DOI":"10.1063\/1.5007873","article-title":"Combining first-principles and data modeling for the accurate prediction of the refractive index of organic polymers","volume":"148","author":"Atif Faiz Afzal","year":"2018","journal-title":"J. Chem. Phys."},{"key":"mlstad88d7bib43","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"mlstad88d7bib44","doi-asserted-by":"publisher","first-page":"6622","DOI":"10.1039\/C9GC02619C","article-title":"Regioselective synthesis, isomerisation, in vitro oestrogenic activity and copolymerisation of bisguaiacol f (BGF) isomers","volume":"21","author":"Koelewijn","year":"2019","journal-title":"Green Chem."},{"key":"mlstad88d7bib45","article-title":"Polycarbonates having superior dielectric properties suitable for energy dense capacitors","author":"Boyles","year":"2019"},{"key":"mlstad88d7bib46","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1016\/j.eurpolymj.2012.02.001","article-title":"Electrical properties of a novel fluorinated polycarbonate","volume":"48","author":"Bendler","year":"2012","journal-title":"Eur. Polym. J."},{"key":"mlstad88d7bib47","doi-asserted-by":"publisher","DOI":"10.1002\/slct.202204829","article-title":"Study on the preparation and optical properties of co-polycarbonates based on binaphthalene and cardo structures","volume":"8","author":"Chen","year":"2023","journal-title":"ChemistrySelect"},{"key":"mlstad88d7bib48","article-title":"Polycarbonates suitable for use in optical articles, 670 December 14 1999","author":"Charles Davis","year":"1999"},{"key":"mlstad88d7bib49","article-title":"Polycarbonate having improved thermal and mechanical properties and reduced coefficients of thermal expansion, June 13 2017","author":"Heuer"},{"key":"mlstad88d7bib50","article-title":"chemprop, and deeppurpose on the admet subset of the therapeutic data commons","author":"Benchmark study of deepautoqsar","year":"2022"},{"key":"mlstad88d7bib51","article-title":"Leveraging high-throughput molecular simulations and machine learning for formulation design","author":"Chew","year":"2024"},{"key":"mlstad88d7bib52","doi-asserted-by":"publisher","first-page":"5837","DOI":"10.1021\/acs.jpca.2c04221","article-title":"De novo design of molecules with low hole reorganization energy based on a quarter-million molecule dft screen: part 2","volume":"126","author":"Staker","year":"2022","journal-title":"J. Phys. Chem. A"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad88d7","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad88d7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad88d7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad88d7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad88d7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad88d7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad88d7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad88d7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T12:04:02Z","timestamp":1730721842000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad88d7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,4]]},"references-count":52,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,11,4]]},"published-print":{"date-parts":[[2024,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad88d7","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,4]]},"assertion":[{"value":"Designing the next generation of polymers with machine learning and physics-based models","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-07-18","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-10-18","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-11-04","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}