期刊
2022 56TH ANNUAL CONFERENCE ON INFORMATION SCIENCES AND SYSTEMS (CISS)
卷 -, 期 -, 页码 188-193出版社
IEEE
DOI: 10.1109/CISS53076.2022.9751154
关键词
neural bandits; protein design; kernel trick
In this paper, a neural bandits algorithm is proposed for accelerating the search for optimal protein designs, and it is demonstrated to be effective through experiments.
Protein design involves searching over a large combinatorial sequence space. Evaluating the fitness of new protein sequences often requires wet-lab experiments that are costly and time consuming. In this paper we propose a neural bandits algorithm that utilizes a modified upper-confidence bound algorithm for accelerating the search for optimal designs. The algorithm makes adaptive queries as guided by the kernelized neural bandits. The algorithm is tested on two public protein fitness datasets, the GB1 and WW domain. For both datasets, our algorithm consistently identifies top-fitness protein sequences. Notably, this approach finds a diverse and rich class of high fitness proteins using substantially fewer design queries compared to a range of alternative methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据