Robustness under parameter and problem domain alterations of Bayesian optimization methods for chemical reactions
Abstract The related problems of chemical reaction optimization and reaction scope search concern the discovery of reaction pathways and conditions that provide the best percentage yield of a target product. The space of possible reaction pathways or conditions is too large to search in full, so ide...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-09-01
|
| Series: | Journal of Cheminformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13321-022-00641-4 |
| _version_ | 1798032466604195840 |
|---|---|
| author | Rubaiyat Mohammad Khondaker Stephen Gow Samantha Kanza Jeremy G Frey Mahesan Niranjan |
| author_facet | Rubaiyat Mohammad Khondaker Stephen Gow Samantha Kanza Jeremy G Frey Mahesan Niranjan |
| author_sort | Rubaiyat Mohammad Khondaker |
| collection | DOAJ |
| description | Abstract The related problems of chemical reaction optimization and reaction scope search concern the discovery of reaction pathways and conditions that provide the best percentage yield of a target product. The space of possible reaction pathways or conditions is too large to search in full, so identifying a globally optimal set of conditions must instead draw on mathematical methods to identify areas of the space that should be investigated. An intriguing contribution to this area of research is the recent development of the Experimental Design for Bayesian optimization (EDBO) optimizer [1]. Bayesian optimization works by building an approximation to the true function to be optimized based on a small set of simulations, and selecting the next point (or points) to be tested based on an acquisition function reflecting the value of different points within the input space. In this work, we evaluated the robustness of the EDBO optimizer under several changes to its specification. We investigated the effect on the performance of the optimizer of altering the acquisition function and batch size, applied the method to other existing reaction yield data sets, and considered its performance in the new problem domain of molecular power conversion efficiency in photovoltaic cells. Our results indicated that the EDBO optimizer broadly performs well under these changes; of particular note is the competitive performance of the computationally cheaper acquisition function Thompson Sampling when compared to the original Expected Improvement function, and some concerns around the method’s performance for “incomplete” input domains. |
| first_indexed | 2024-04-11T20:14:24Z |
| format | Article |
| id | doaj.art-10014ceffb114d269c1bbbd9e26efe84 |
| institution | Directory Open Access Journal |
| issn | 1758-2946 |
| language | English |
| last_indexed | 2024-04-11T20:14:24Z |
| publishDate | 2022-09-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Cheminformatics |
| spelling | doaj.art-10014ceffb114d269c1bbbd9e26efe842022-12-22T04:05:01ZengBMCJournal of Cheminformatics1758-29462022-09-0114111010.1186/s13321-022-00641-4Robustness under parameter and problem domain alterations of Bayesian optimization methods for chemical reactionsRubaiyat Mohammad Khondaker0Stephen Gow1Samantha Kanza2Jeremy G Frey3Mahesan Niranjan4Department of Mathematics, University of CambridgeDepartment of Chemistry, University of SouthamptonDepartment of Chemistry, University of SouthamptonDepartment of Chemistry, University of SouthamptonDepartment of Electronics and Computer Science, University of SouthamptonAbstract The related problems of chemical reaction optimization and reaction scope search concern the discovery of reaction pathways and conditions that provide the best percentage yield of a target product. The space of possible reaction pathways or conditions is too large to search in full, so identifying a globally optimal set of conditions must instead draw on mathematical methods to identify areas of the space that should be investigated. An intriguing contribution to this area of research is the recent development of the Experimental Design for Bayesian optimization (EDBO) optimizer [1]. Bayesian optimization works by building an approximation to the true function to be optimized based on a small set of simulations, and selecting the next point (or points) to be tested based on an acquisition function reflecting the value of different points within the input space. In this work, we evaluated the robustness of the EDBO optimizer under several changes to its specification. We investigated the effect on the performance of the optimizer of altering the acquisition function and batch size, applied the method to other existing reaction yield data sets, and considered its performance in the new problem domain of molecular power conversion efficiency in photovoltaic cells. Our results indicated that the EDBO optimizer broadly performs well under these changes; of particular note is the competitive performance of the computationally cheaper acquisition function Thompson Sampling when compared to the original Expected Improvement function, and some concerns around the method’s performance for “incomplete” input domains.https://doi.org/10.1186/s13321-022-00641-4Bayesian optimizationReaction optimization |
| spellingShingle | Rubaiyat Mohammad Khondaker Stephen Gow Samantha Kanza Jeremy G Frey Mahesan Niranjan Robustness under parameter and problem domain alterations of Bayesian optimization methods for chemical reactions Journal of Cheminformatics Bayesian optimization Reaction optimization |
| title | Robustness under parameter and problem domain alterations of Bayesian optimization methods for chemical reactions |
| title_full | Robustness under parameter and problem domain alterations of Bayesian optimization methods for chemical reactions |
| title_fullStr | Robustness under parameter and problem domain alterations of Bayesian optimization methods for chemical reactions |
| title_full_unstemmed | Robustness under parameter and problem domain alterations of Bayesian optimization methods for chemical reactions |
| title_short | Robustness under parameter and problem domain alterations of Bayesian optimization methods for chemical reactions |
| title_sort | robustness under parameter and problem domain alterations of bayesian optimization methods for chemical reactions |
| topic | Bayesian optimization Reaction optimization |
| url | https://doi.org/10.1186/s13321-022-00641-4 |
| work_keys_str_mv | AT rubaiyatmohammadkhondaker robustnessunderparameterandproblemdomainalterationsofbayesianoptimizationmethodsforchemicalreactions AT stephengow robustnessunderparameterandproblemdomainalterationsofbayesianoptimizationmethodsforchemicalreactions AT samanthakanza robustnessunderparameterandproblemdomainalterationsofbayesianoptimizationmethodsforchemicalreactions AT jeremygfrey robustnessunderparameterandproblemdomainalterationsofbayesianoptimizationmethodsforchemicalreactions AT mahesanniranjan robustnessunderparameterandproblemdomainalterationsofbayesianoptimizationmethodsforchemicalreactions |