arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.08751q-bio.BMcs.AIcs.LG
收藏

面向RNA设计的耦合变量基于采样的连续优化方法

Sampling-based Continuous Optimization with Coupled Variables for RNA Design

School of EECS(电子工程与计算机科学学院);University of Southern California(南加州大学);University of Rochester Medical Center(罗切斯特大学医学中心);Oregon State University(俄勒冈州立大学)

Wei Yu Tang, Ning Dai, Tianshuo Zhou, David H. Mathews, Liang Huang

AI总结:

针对RNA设计离散问题计算难度高、长序列结构设计表现差的问题,提出基于耦合变量分布的连续优化框架,通过采样近似目标与梯度,在Eterna100基准关键指标上超越现有最优方法。

摘要:

给定目标结构的RNA设计任务旨在找到一条能够折叠为该结构的序列。这是一个计算难度极高的问题,其部分变体已被证明属于NP难问题。因此,局部搜索等启发式方法在该任务中被广泛使用,但这类方法仅探索固定数量的候选解,无法应对设计空间的指数级增长,在处理更长、更难设计的结构时往往表现不佳。\n我们转而将这类离散问题建模为连续优化问题:该方法从所有可能候选序列的分布出发,利用梯度下降提升目标函数的期望值。我们基于耦合变量定义了新型分布,用于排除不符合目标结构的无效序列,并对核苷酸之间的相关性进行建模。为使该方法可普遍适用于任意目标函数,我们采用采样来近似期望目标函数、估计梯度,并选择最终候选序列。\n与现有最优方法相比,我们的工作在Boltzmann概率、集合缺陷、能隙等关键指标上始终表现更优,尤其是在Eterna100基准中的长序列、高难度设计谜题上优势更明显。我们的代码可在以下地址获取:http://github.com/weiyutang1010/ncrna_design。

英文摘要:

The task of RNA design given a target structure aims to find a sequence that can fold into that structure. It is a computationally hard problem where some version(s) have been proven to be NP-hard. As a result, heuristic methods such as local search have been popular for this task, but by only exploring a fixed number of candidates. They can not keep up with the exponential growth of the design space, and often perform poorly on longer and harder-to-design structures. We instead formulate these discrete problems as continuous optimization, which starts with a distribution over all possible candidate sequences, and uses gradient descent to improve the expectation of an objective function. We define novel distributions based on coupled variables to rule out invalid sequences given the target structure and to model the correlation between nucleotides. To make it universally applicable to any objective function, we use sampling to approximate the expected objective function, to estimate the gradient, and to select the final candidate. Compared to the state-of-the-art methods, our work consistently outperforms them in key metrics such as Boltzmann probability, ensemble defect, and energy gap, especially on long and hard-to-design puzzles in the Eterna100 benchmark. Our code is available at: http://github.com/weiyutang1010/ncrna_design.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑