Computer-aided multi-objective optimization in small molecule discovery
Molecular discovery is a multi-objective optimization problem that requires identifying a molecule or set of molecules that balance multiple, often competing, properties. Multi-objective molecular design is commonly addressed by combining properties of interest into a single objective function using...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Elsevier BV
2025
|
| Online Access: | https://hdl.handle.net/1721.1/158193 |
| _version_ | 1824458173451337728 |
|---|---|
| author | Fromer, Jenna C Coley, Connor W |
| author2 | Massachusetts Institute of Technology. Department of Chemical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Chemical Engineering Fromer, Jenna C Coley, Connor W |
| author_sort | Fromer, Jenna C |
| collection | MIT |
| description | Molecular discovery is a multi-objective optimization problem that requires identifying a molecule or set of molecules that balance multiple, often competing, properties. Multi-objective molecular design is commonly addressed by combining properties of interest into a single objective function using scalarization, which imposes assumptions about relative importance and uncovers little about the trade-offs between objectives. In contrast to scalarization, Pareto optimization does not require knowledge of relative importance and reveals the trade-offs between objectives. However, it introduces additional considerations in algorithm design. In this review, we describe pool-based and de novo generative approaches to multi-objective molecular discovery with a focus on Pareto optimization algorithms. We show how pool-based molecular discovery is a relatively direct extension of multi-objective Bayesian optimization and how the plethora of different generative models extend from single-objective to multi-objective optimization in similar ways using non-dominated sorting in the reward function (reinforcement learning) or to select molecules for retraining (distribution learning) or propagation (genetic algorithms). Finally, we discuss some remaining challenges and opportunities in the field, emphasizing the opportunity to adopt Bayesian optimization techniques into multi-objective de novo design. |
| first_indexed | 2025-02-19T04:21:41Z |
| format | Article |
| id | mit-1721.1/158193 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2025-02-19T04:21:41Z |
| publishDate | 2025 |
| publisher | Elsevier BV |
| record_format | dspace |
| spelling | mit-1721.1/1581932025-02-11T20:49:59Z Computer-aided multi-objective optimization in small molecule discovery Fromer, Jenna C Coley, Connor W Massachusetts Institute of Technology. Department of Chemical Engineering Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Molecular discovery is a multi-objective optimization problem that requires identifying a molecule or set of molecules that balance multiple, often competing, properties. Multi-objective molecular design is commonly addressed by combining properties of interest into a single objective function using scalarization, which imposes assumptions about relative importance and uncovers little about the trade-offs between objectives. In contrast to scalarization, Pareto optimization does not require knowledge of relative importance and reveals the trade-offs between objectives. However, it introduces additional considerations in algorithm design. In this review, we describe pool-based and de novo generative approaches to multi-objective molecular discovery with a focus on Pareto optimization algorithms. We show how pool-based molecular discovery is a relatively direct extension of multi-objective Bayesian optimization and how the plethora of different generative models extend from single-objective to multi-objective optimization in similar ways using non-dominated sorting in the reward function (reinforcement learning) or to select molecules for retraining (distribution learning) or propagation (genetic algorithms). Finally, we discuss some remaining challenges and opportunities in the field, emphasizing the opportunity to adopt Bayesian optimization techniques into multi-objective de novo design. 2025-02-11T20:49:58Z 2025-02-11T20:49:58Z 2023-02 2025-02-11T20:34:25Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/158193 Fromer, Jenna C and Coley, Connor W. 2023. "Computer-aided multi-objective optimization in small molecule discovery." Patterns, 4 (2). en 10.1016/j.patter.2023.100678 Patterns Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ application/pdf Elsevier BV Elsevier BV |
| spellingShingle | Fromer, Jenna C Coley, Connor W Computer-aided multi-objective optimization in small molecule discovery |
| title | Computer-aided multi-objective optimization in small molecule discovery |
| title_full | Computer-aided multi-objective optimization in small molecule discovery |
| title_fullStr | Computer-aided multi-objective optimization in small molecule discovery |
| title_full_unstemmed | Computer-aided multi-objective optimization in small molecule discovery |
| title_short | Computer-aided multi-objective optimization in small molecule discovery |
| title_sort | computer aided multi objective optimization in small molecule discovery |
| url | https://hdl.handle.net/1721.1/158193 |
| work_keys_str_mv | AT fromerjennac computeraidedmultiobjectiveoptimizationinsmallmoleculediscovery AT coleyconnorw computeraidedmultiobjectiveoptimizationinsmallmoleculediscovery |