English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Directed Evolution (DE), a landmark wet-lab method originated in 1960s,enables discovery of novel protein designs via evolving a population ofcandidate sequences. Recent advances in biotechnology has made it possible tocollect high-throughput data, allowing the use of machine learning to map out aprotein's sequence-to-function relation. There is a growing interest in machinelearning-assisted DE for accelerating protein optimization. Yet the theoreticalunderstanding of DE, as well as the use of machine learning in DE, remainslimited. In this paper, we connect DE with the bandit learning theory and makea first attempt to study regret minimization in DE. We propose a ThompsonSampling-guided Directed Evolution (TS-DE) framework for sequence optimization,where the sequence-to-function mapping is unknown and querying a single valueis subject to costly and noisy measurements. TS-DE updates a posterior of thefunction based on collected measurements. It uses a posterior-sampled functionestimate to guide the crossover recombination and mutation steps in DE. In thecase of a linear model, we show that TS-DE enjoys a Bayesian regret of order$\tilde O(d^{2}\sqrt{MT})$, where $d$ is feature dimension, $M$ is populationsize and $T$ is number of rounds. This regret bound is nearly optimal,confirming that bandit learning can provably accelerate DE. It may haveimplications for more general sequence optimization and evolutionaryalgorithms.

Bandit Theory and Thompson Sampling-Guided Directed Evolution for Sequence Optimization