Scholarlink

<p>RNA design aims to find a sequence that can fold into a target secondary structure. It can create artificial RNA molecules for specific functions, with wide applications in medicine. It is computationally challenging due to <i>two levels</i> of combinatorial explosion: the exponentially large design space and the exponentially many competing structures per design. Popular methods such as local search cannot keep up with these combinatorial explosions. We instead employ two techniques from machine learning, continuous optimization and Monte-Carlo sampling. We start from a distribution over all valid sequences, and use gradient descent to improve the expectation of an arbitrary objective function. We define novel coupled-variable distributions to model the correlation between nucleotides. We then use sampling to approximate the objective, estimate the gradient, and select the final candidate. Our work consistently outperforms state-of-the-art methods in key metrics including Boltzmann probability and ensemble defect, especially on long and hard-to-design structures.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SamplingDesign: RNA design via continuous optimization with coupled variables and Monte-Carlo sampling

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月20日

查看全文
  • Wei Yu Tang,
  • Ning Dai,
  • Tianshuo Zhou,
  • David H. Mathews,
  • Liang Huang

摘要

RNA design aims to find a sequence that can fold into a target secondary structure. It can create artificial RNA molecules for specific functions, with wide applications in medicine. It is computationally challenging due to two levels of combinatorial explosion: the exponentially large design space and the exponentially many competing structures per design. Popular methods such as local search cannot keep up with these combinatorial explosions. We instead employ two techniques from machine learning, continuous optimization and Monte-Carlo sampling. We start from a distribution over all valid sequences, and use gradient descent to improve the expectation of an arbitrary objective function. We define novel coupled-variable distributions to model the correlation between nucleotides. We then use sampling to approximate the objective, estimate the gradient, and select the final candidate. Our work consistently outperforms state-of-the-art methods in key metrics including Boltzmann probability and ensemble defect, especially on long and hard-to-design structures.