Timezone: »

 
PropertyDAG: Multi-objective Bayesian optimization of partially ordered, mixed-variable properties for biological sequence design
Ji Won Park · Samuel Stanton · Saeed Saremi · Andrew Watkins · Stephen Ra · Vladimir Gligorijevic · Kyunghyun Cho · Richard Bonneau

@
in AI for Science: Progress and Promises »
Event URL: https://openreview.net/forum?id=GN2jsoQFLhi »
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 hierarchical 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 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 a desired partial 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.
Keywords: Active Learning · Bayesian optimization · Multi-Objective Optimization · probabilistic graphical models

Author Information

Ji Won Park (Prescient Design, Genentech/Roche)
Samuel Stanton (Prescient Design, Genentech)

ML Scientist at Genentech Early Research and Development (gRED). Building ML systems for scientific discovery in biotech.

Saeed Saremi (NNAISENSE)
Andrew Watkins (Prescient Design, Genentech)
Stephen Ra (Prescient Design / Genentech)
Vladimir Gligorijevic (Prescient Design/Genentech)
Kyunghyun Cho (Genentech / NYU)

Kyunghyun Cho is an associate professor of computer science and data science at New York University and a research scientist at Facebook AI Research. He was a postdoctoral fellow at the Université de Montréal until summer 2015 under the supervision of Prof. Yoshua Bengio, and received PhD and MSc degrees from Aalto University early 2014 under the supervision of Prof. Juha Karhunen, Dr. Tapani Raiko and Dr. Alexander Ilin. He tries his best to find a balance among machine learning, natural language processing, and life, but almost always fails to do so.

Richard Bonneau (New York University)

More from the Same Authors