Rapid design of top-performing metal-organic frameworks with qualitative representations of building blocks
Abstract Data-driven materials design often encounters challenges where systems possess qualitative (categorical) information. Specifically, representing Metal-organic frameworks (MOFs) through different building blocks poses a challenge for designers to incorporate qualitative information into desi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-09-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-023-01125-1 |
| _version_ | 1827633694316167168 |
|---|---|
| author | Yigitcan Comlek Thang Duc Pham Randall Q. Snurr Wei Chen |
| author_facet | Yigitcan Comlek Thang Duc Pham Randall Q. Snurr Wei Chen |
| author_sort | Yigitcan Comlek |
| collection | DOAJ |
| description | Abstract Data-driven materials design often encounters challenges where systems possess qualitative (categorical) information. Specifically, representing Metal-organic frameworks (MOFs) through different building blocks poses a challenge for designers to incorporate qualitative information into design optimization, and leads to a combinatorial challenge, with large number of MOFs that could be explored. In this work, we integrated Latent Variable Gaussian Process (LVGP) and Multi-Objective Batch-Bayesian Optimization (MOBBO) to identify top-performing MOFs adaptively, autonomously, and efficiently. We showcased that our method (i) requires no specific physical descriptors and only uses building blocks that construct the MOFs for global optimization through qualitative representations, (ii) is application and property independent, and (iii) provides an interpretable model of building blocks with physical justification. By searching only ~1% of the design space, LVGP-MOBBO identified all MOFs on the Pareto front and 97% of the 50 top-performing designs for the CO2 working capacity and CO2/N2 selectivity properties. |
| first_indexed | 2024-03-09T15:04:07Z |
| format | Article |
| id | doaj.art-8b1ab520a4d3453a8775fcacaba5f94c |
| institution | Directory Open Access Journal |
| issn | 2057-3960 |
| language | English |
| last_indexed | 2024-03-09T15:04:07Z |
| publishDate | 2023-09-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj.art-8b1ab520a4d3453a8775fcacaba5f94c2023-11-26T13:46:59ZengNature Portfolionpj Computational Materials2057-39602023-09-019111410.1038/s41524-023-01125-1Rapid design of top-performing metal-organic frameworks with qualitative representations of building blocksYigitcan Comlek0Thang Duc Pham1Randall Q. Snurr2Wei Chen3Department of Mechanical Engineering, Northwestern UniversityDepartment of Chemical and Biological Engineering, Northwestern UniversityDepartment of Chemical and Biological Engineering, Northwestern UniversityDepartment of Mechanical Engineering, Northwestern UniversityAbstract Data-driven materials design often encounters challenges where systems possess qualitative (categorical) information. Specifically, representing Metal-organic frameworks (MOFs) through different building blocks poses a challenge for designers to incorporate qualitative information into design optimization, and leads to a combinatorial challenge, with large number of MOFs that could be explored. In this work, we integrated Latent Variable Gaussian Process (LVGP) and Multi-Objective Batch-Bayesian Optimization (MOBBO) to identify top-performing MOFs adaptively, autonomously, and efficiently. We showcased that our method (i) requires no specific physical descriptors and only uses building blocks that construct the MOFs for global optimization through qualitative representations, (ii) is application and property independent, and (iii) provides an interpretable model of building blocks with physical justification. By searching only ~1% of the design space, LVGP-MOBBO identified all MOFs on the Pareto front and 97% of the 50 top-performing designs for the CO2 working capacity and CO2/N2 selectivity properties.https://doi.org/10.1038/s41524-023-01125-1 |
| spellingShingle | Yigitcan Comlek Thang Duc Pham Randall Q. Snurr Wei Chen Rapid design of top-performing metal-organic frameworks with qualitative representations of building blocks npj Computational Materials |
| title | Rapid design of top-performing metal-organic frameworks with qualitative representations of building blocks |
| title_full | Rapid design of top-performing metal-organic frameworks with qualitative representations of building blocks |
| title_fullStr | Rapid design of top-performing metal-organic frameworks with qualitative representations of building blocks |
| title_full_unstemmed | Rapid design of top-performing metal-organic frameworks with qualitative representations of building blocks |
| title_short | Rapid design of top-performing metal-organic frameworks with qualitative representations of building blocks |
| title_sort | rapid design of top performing metal organic frameworks with qualitative representations of building blocks |
| url | https://doi.org/10.1038/s41524-023-01125-1 |
| work_keys_str_mv | AT yigitcancomlek rapiddesignoftopperformingmetalorganicframeworkswithqualitativerepresentationsofbuildingblocks AT thangducpham rapiddesignoftopperformingmetalorganicframeworkswithqualitativerepresentationsofbuildingblocks AT randallqsnurr rapiddesignoftopperformingmetalorganicframeworkswithqualitativerepresentationsofbuildingblocks AT weichen rapiddesignoftopperformingmetalorganicframeworkswithqualitativerepresentationsofbuildingblocks |