ECDomainMiner

Many entries in the protein data bank (PDB) are annotated to show their component protein domains according to the Pfam classification, as well as their biological function through the enzyme commission (EC) numbering scheme. However, despite the fact that the biological activity of many proteins often arises from specific domain-domain and domain-ligand interactions, current on-line resources rarely provide a direct mapping from structure to function at the domain level. Since the PDB now contains many tens of thousands of protein chains, and since protein sequence databases can dwarf such numbers by orders of magnitude, there is a pressing need to develop automatic structure-function annotation tools which can operate at the domain level. This article presents ECDomainMiner, a novel content-based filtering approach to automatically infer associations between EC numbers and Pfam domains. ECDomainMiner finds a total of 20,728 non-redundant EC-Pfam associations with a F- measure of 0.95 with respect to a "Gold Standard" test set extracted from InterPro. Compared to the 1,515 manually curated EC-Pfam associations in InterPro, ECDomainMiner infers a 13-fold increase in the number of EC-Pfam associations. These EC-Pfam associations could be used to annotate some 68,152 protein chains in the PDB which currently lack any EC annotation蛋白质数据库（PDB）中的大量条目均已完成注释：其组分蛋白质结构域依照Pfam分类体系标注，生物学功能则通过酶委员会（EC）编号体系予以标注。然而，尽管多数蛋白质的生物学活性往往源自特定的结构域-结构域与结构域-配体相互作用，但当前的在线资源极少能提供结构域层面上从结构到功能的直接映射关系。鉴于当前PDB已收录数万条蛋白质链，而蛋白质序列数据库的规模更是远超该数量级，因此迫切需要开发可在结构域层面运行的自动化结构-功能注释工具。本文提出了ECDomainMiner——一种用于自动推导EC编号与Pfam结构域之间关联的新型基于内容的过滤方法。相较于从InterPro中提取的"Gold Standard"测试集，ECDomainMiner共找到了20,728条非冗余的EC-Pfam关联，其F测度达到0.95。与InterPro中1,515条经人工审定的EC-Pfam关联相比，ECDomainMiner推导出的EC-Pfam关联数量增长了13倍。这些EC-Pfam关联可用于为PDB中目前尚无任何EC注释的约68,152条蛋白质链完成注释。

搜集汇总

背景与挑战

背景概述

ECDomainMiner是一个基于内容过滤的自动工具，用于推断酶分类号（EC）和Pfam蛋白结构域之间的关联。该数据集提供了20,728个非冗余关联，准确度达0.95，相比现有手动整理数据增加了13倍，可用于注释蛋白质数据银行中大量未标注的蛋白质链。