期刊
SCIENCE
卷 373, 期 6558, 页码 1047-+出版社
AMER ASSOC ADVANCEMENT SCIENCE
DOI: 10.1126/science.abe5650
关键词
-
资金
- National Science Fatmdation Graduate Research Fellowships
- U.S. Department of Energy, Office of Science Graduate Student Research program
- Stanford Bio-X Bowes Fellowship
- Army Research Office Multidisciplinary University Research program
- U.S. Department of Energy, Office of Science, Scientific Discovery through Advanced Computing (SciDAC) program
- Intel
- Stanford BierX seed grant
- National Institutes of Health [R21CA219847, R35GM122579]
The study introduces a machine learning approach that can accurately identify RNA structures without assumptions about their defining characteristics, trained with only a small amount of known data. This approach outperforms previous methods and consistently produces the best results in community-wide blind RNA structure prediction challenges.
RNA molecules adopt three-dimensional structures that are critical to their function and of interest in drug discovery. Few RNA structures are known, however, and predicting them computationally has proven challenging. We introduce a machine learning approach that enables identification of accurate structural models without assumptions about their defining characteristics, despite being trained with only 18 known RNA structures. The resulting scoring function, the Atomic Rotationally Equivariant Scorer (ARES), substantially outperforms previous methods and consistently produces the best results in community-wide blind RNA structure prediction challenges. By learning effectively even from a small amount of data, our approach overcomes a major limitation of standard deep neural networks. Because it uses only atomic coordinates as inputs and incorporates no RNA-specific information, this approach is applicable to diverse problems in structural biology, chemistry, materials science, and beyond.
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