PropertyDAG: Multi-objective Bayesian optimization of partially ordered, mixed-variable properties for biological sequence design
| Autor: | Park, Ji Won, Stanton, Samuel, Saremi, Saeed, Watkins, Andrew, Dwyer, Henri, Gligorijevic, Vladimir, Bonneau, Richard, Ra, Stephen, Cho, Kyunghyun |
|---|---|
| Rok vydání: | 2022 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Bayesian optimization offers a sample-efficient framework for navigating the exploration-exploitation trade-off in the vast design space of biological sequences. Whereas it is possible to optimize the various properties of interest jointly using a multi-objective acquisition function, such as the expected hypervolume improvement (EHVI), this approach does not account for objectives with a hierarchical dependency structure. We consider a common use case where some regions of the Pareto frontier are prioritized over others according to a specified $\textit{partial ordering}$ in the objectives. For instance, when designing antibodies, we would like to maximize the binding affinity to a target antigen only if it can be expressed in live cell culture -- modeling the experimental dependency in which affinity can only be measured for antibodies that can be expressed and thus produced in viable quantities. In general, we may want to confer a partial ordering to the properties such that each property is optimized conditioned on its parent properties satisfying some feasibility condition. To this end, we present PropertyDAG, a framework that operates on top of the traditional multi-objective BO to impose this desired ordering on the objectives, e.g. expression $\rightarrow$ affinity. We demonstrate its performance over multiple simulated active learning iterations on a penicillin production task, toy numerical problem, and a real-world antibody design task. Comment: 9 pages, 7 figures. Submitted to NeurIPS 2022 AI4Science Workshop |
| Databáze: | arXiv |
| Externí odkaz: |
|