美国斯坦福大学Ron O. Dror和Rhiju Das研究组合作对RNA结构几何进行深度学习。相关论文于2021年8月27日发表于国际顶尖学术期刊《科学》杂志上。
他们引入了一种机器学习方法,尽管仅使用 18 个已知的 RNA 结构进行训练,但它可以识别准确的结构模型,而无需对其定义特征进行假设。由此产生的评分函数、原子旋转等变评分器 (ARES),大大优于以前的方法,并且在群体范围的盲 RNA 结构预测挑战中始终如一地产生最佳结果。
通过从少量数据中有效学习,他们的方法克服了标准深度神经网络的主要限制。由于它仅使用原子坐标作为输入,并且不包含特定于 RNA 的信息,因此这种方法适用于结构生物学、化学、材料科学等领域的各种问题。
据介绍,RNA 分子形成对其功能至关重要且在药物发现中很重要的三维结构。然而,很少有 RNA 结构是已知的,并且通过计算来预测它们已被证明具有挑战性。
附:英文原文
Title: Geometric deep learning of RNA structure
Author: Raphael J. L. Townshend, Stephan Eismann, Andrew M. Watkins, Ramya Rangan, Maria Karelina, Rhiju Das, Ron O. Dror
Issue&Volume: 2021/08/27
Abstract: 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.
DOI: 10.1126/science.abe5650
Source: https://science.sciencemag.org/content/373/6558/1047