From evolutionary interference, function annotation to structural prediction, protein sequence comparison has provided crucial biological insights. While many sequence alignment algorithms have been developed, existing approaches often cannot detect hidden structural relationships in the “twilight zone” of low sequence identity. To address this critical problem, we introduce a computational algorithm that performs protein Sequence Alignments from deep-Learning of Structural Alignments (SAdLSA, silent “d”). The key idea is to implicitly learn the protein folding code from many thousands of structural alignments using experimentally determined protein structures.

中文翻译：

---

一种基于蛋白质折叠代码深度学习的新型序列比对算法。

从进化干扰、功能注释到结构预测，蛋白质序列比较提供了重要的生物学见解。虽然已经开发了许多序列比对算法，但现有方法通常无法检测到低序列同一性“模糊地带”中隐藏的结构关系。为了解决这个关键问题，我们引入了一种计算算法，该算法通过结构比对的深度学习（SAdLSA ，无声“d”）执行蛋白质序列比对。关键思想是使用实验确定的蛋白质结构从数千个结构比对中隐式学习蛋白质折叠代码。