Advancing material property prediction: using physics-informed machine learning models for viscosity
Abstract In materials science, accurately computing properties like viscosity, melting point, and glass transition temperatures solely through physics-based models is challenging. Data-driven machine learning (ML) also poses challenges in constructing ML models, especially in the material science do...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-03-01
|
| Series: | Journal of Cheminformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13321-024-00820-5 |
| _version_ | 1797259106862497792 |
|---|---|
| author | Alex K. Chew Matthew Sender Zachary Kaplan Anand Chandrasekaran Jackson Chief Elk Andrea R. Browning H. Shaun Kwak Mathew D. Halls Mohammad Atif Faiz Afzal |
| author_facet | Alex K. Chew Matthew Sender Zachary Kaplan Anand Chandrasekaran Jackson Chief Elk Andrea R. Browning H. Shaun Kwak Mathew D. Halls Mohammad Atif Faiz Afzal |
| author_sort | Alex K. Chew |
| collection | DOAJ |
| description | Abstract In materials science, accurately computing properties like viscosity, melting point, and glass transition temperatures solely through physics-based models is challenging. Data-driven machine learning (ML) also poses challenges in constructing ML models, especially in the material science domain where data is limited. To address this, we integrate physics-informed descriptors from molecular dynamics (MD) simulations to enhance the accuracy and interpretability of ML models. Our current study focuses on accurately predicting viscosity in liquid systems using MD descriptors. In this work, we curated a comprehensive dataset of over 4000 small organic molecules’ viscosities from scientific literature, publications, and online databases. This dataset enabled us to develop quantitative structure–property relationships (QSPR) consisting of descriptor-based and graph neural network models to predict temperature-dependent viscosities for a wide range of viscosities. The QSPR models reveal that including MD descriptors improves the prediction of experimental viscosities, particularly at the small data set scale of fewer than a thousand data points. Furthermore, feature importance tools reveal that intermolecular interactions captured by MD descriptors are most important for viscosity predictions. Finally, the QSPR models can accurately capture the inverse relationship between viscosity and temperature for six battery-relevant solvents, some of which were not included in the original data set. Our research highlights the effectiveness of incorporating MD descriptors into QSPR models, which leads to improved accuracy for properties that are difficult to predict when using physics-based models alone or when limited data is available. Graphical Abstract |
| first_indexed | 2024-04-24T23:04:10Z |
| format | Article |
| id | doaj.art-d431eabc630d4e9b849181689578969e |
| institution | Directory Open Access Journal |
| issn | 1758-2946 |
| language | English |
| last_indexed | 2024-04-24T23:04:10Z |
| publishDate | 2024-03-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Cheminformatics |
| spelling | doaj.art-d431eabc630d4e9b849181689578969e2024-03-17T12:36:32ZengBMCJournal of Cheminformatics1758-29462024-03-0116111410.1186/s13321-024-00820-5Advancing material property prediction: using physics-informed machine learning models for viscosityAlex K. Chew0Matthew Sender1Zachary Kaplan2Anand Chandrasekaran3Jackson Chief Elk4Andrea R. Browning5H. Shaun Kwak6Mathew D. Halls7Mohammad Atif Faiz Afzal8Schrödinger, Inc.Schrödinger, Inc.Schrödinger, Inc.Schrödinger, Inc.Schrödinger, Inc.Schrödinger, Inc.Schrödinger, Inc.Schrödinger, Inc.Schrödinger, Inc.Abstract In materials science, accurately computing properties like viscosity, melting point, and glass transition temperatures solely through physics-based models is challenging. Data-driven machine learning (ML) also poses challenges in constructing ML models, especially in the material science domain where data is limited. To address this, we integrate physics-informed descriptors from molecular dynamics (MD) simulations to enhance the accuracy and interpretability of ML models. Our current study focuses on accurately predicting viscosity in liquid systems using MD descriptors. In this work, we curated a comprehensive dataset of over 4000 small organic molecules’ viscosities from scientific literature, publications, and online databases. This dataset enabled us to develop quantitative structure–property relationships (QSPR) consisting of descriptor-based and graph neural network models to predict temperature-dependent viscosities for a wide range of viscosities. The QSPR models reveal that including MD descriptors improves the prediction of experimental viscosities, particularly at the small data set scale of fewer than a thousand data points. Furthermore, feature importance tools reveal that intermolecular interactions captured by MD descriptors are most important for viscosity predictions. Finally, the QSPR models can accurately capture the inverse relationship between viscosity and temperature for six battery-relevant solvents, some of which were not included in the original data set. Our research highlights the effectiveness of incorporating MD descriptors into QSPR models, which leads to improved accuracy for properties that are difficult to predict when using physics-based models alone or when limited data is available. Graphical Abstracthttps://doi.org/10.1186/s13321-024-00820-5Classical molecular dynamics simulationsOrganic moleculesPhysical propertiesViscosityQuantitative structure–property relationshipsMachine learning |
| spellingShingle | Alex K. Chew Matthew Sender Zachary Kaplan Anand Chandrasekaran Jackson Chief Elk Andrea R. Browning H. Shaun Kwak Mathew D. Halls Mohammad Atif Faiz Afzal Advancing material property prediction: using physics-informed machine learning models for viscosity Journal of Cheminformatics Classical molecular dynamics simulations Organic molecules Physical properties Viscosity Quantitative structure–property relationships Machine learning |
| title | Advancing material property prediction: using physics-informed machine learning models for viscosity |
| title_full | Advancing material property prediction: using physics-informed machine learning models for viscosity |
| title_fullStr | Advancing material property prediction: using physics-informed machine learning models for viscosity |
| title_full_unstemmed | Advancing material property prediction: using physics-informed machine learning models for viscosity |
| title_short | Advancing material property prediction: using physics-informed machine learning models for viscosity |
| title_sort | advancing material property prediction using physics informed machine learning models for viscosity |
| topic | Classical molecular dynamics simulations Organic molecules Physical properties Viscosity Quantitative structure–property relationships Machine learning |
| url | https://doi.org/10.1186/s13321-024-00820-5 |
| work_keys_str_mv | AT alexkchew advancingmaterialpropertypredictionusingphysicsinformedmachinelearningmodelsforviscosity AT matthewsender advancingmaterialpropertypredictionusingphysicsinformedmachinelearningmodelsforviscosity AT zacharykaplan advancingmaterialpropertypredictionusingphysicsinformedmachinelearningmodelsforviscosity AT anandchandrasekaran advancingmaterialpropertypredictionusingphysicsinformedmachinelearningmodelsforviscosity AT jacksonchiefelk advancingmaterialpropertypredictionusingphysicsinformedmachinelearningmodelsforviscosity AT andrearbrowning advancingmaterialpropertypredictionusingphysicsinformedmachinelearningmodelsforviscosity AT hshaunkwak advancingmaterialpropertypredictionusingphysicsinformedmachinelearningmodelsforviscosity AT mathewdhalls advancingmaterialpropertypredictionusingphysicsinformedmachinelearningmodelsforviscosity AT mohammadatiffaizafzal advancingmaterialpropertypredictionusingphysicsinformedmachinelearningmodelsforviscosity |