PredAlgo: A New Subcellular Localization Prediction Tool Dedicated to Green Algae
PredAlgo: A New Subcellular Localization Prediction Tool Dedicated to Green Algae
复制标题
DOI：
10.1093/molbev/mss178
复制
发表时间：
2012-12-01
影响因子：
10.7
通讯作者：
Cournac, Laurent
中科院分区：
文献类型：
--
作者：
Tardif, Marianne;Atteia, Ariane;Cournac, Laurent
单细胞绿藻莱茵衣藻是破译光合细胞胞内区室中发生的过程的主要模型。细胞器特异性蛋白质组学研究已开始描绘其各种亚蛋白质组，但基于序列的预测软件对于在全基因组规模上分配蛋白质亚细胞定位是必要的。不幸的是，现有的工具是针对陆地植物的，并且往往会错误地预测核编码藻类蛋白的定位，预测许多叶绿体蛋白是线粒体的目标。因此，我们开发了一种名为 PredAlgo 的新工具，可以预测这些蛋白质在绿藻中三个细胞内区室之一的细胞内定位：线粒体、叶绿体和分泌途径。其核心是使用精心设计的莱茵衣藻蛋白质集进行训练的神经网络，将 N 端序列划分为重叠的 19 个残基窗口，并对它们属于上述细胞器之一的可切割靶向序列的概率进行评分。然后推断该蛋白质的靶向预测，并根据 N 端序列的评分函数的形状预测可能的切割位点。当对莱茵衣藻序列的独立基准集进行评估时，PredAlgo 显示出显着提高的叶绿体和线粒体定位蛋白之间的区分能力。它的预测与叶绿体蛋白质组学研究的结果非常吻合。当对其他绿藻进行测试时，它对绿藻纲和海藻纲给出了良好的结果，但往往低估了绿藻纲中的线粒体蛋白。预计大约 18% 的核编码莱茵衣藻蛋白质组将靶向叶绿体，15% 将靶向线粒体。
The unicellular green alga Chlamydomonas reinhardtii is a prime model for deciphering processes occurring in the intracellular compartments of the photosynthetic cell. Organelle-specific proteomic studies have started to delineate its various subproteomes, but sequence-based prediction software is necessary to assign proteins subcellular localizations at whole genome scale. Unfortunately, existing tools are oriented toward land plants and tend to mispredict the localization of nuclear-encoded algal proteins, predicting many chloroplast proteins as mitochondrion targeted. We thus developed a new tool called PredAlgo that predicts intracellular localization of those proteins to one of three intracellular compartments in green algae: the mitochondrion, the chloroplast, and the secretory pathway. At its core, a neural network, trained using carefully curated sets of C. reinhardtii proteins, divides the N-terminal sequence into overlapping 19-residue windows and scores the probability that they belong to a cleavable targeting sequence for one of the aforementioned organelles. A targeting prediction is then deduced for the protein, and a likely cleavage site is predicted based on the shape of the scoring function along the N-terminal sequence. When assessed on an independent benchmarking set of C. reinhardtii sequences, PredAlgo showed a highly improved discrimination capacity between chloroplast- and mitochondrion-localized proteins. Its predictions matched well the results of chloroplast proteomics studies. When tested on other green algae, it gave good results with Chlorophyceae and Trebouxiophyceae but tended to underpredict mitochondrial proteins in Prasinophyceae. Approximately 18% of the nuclear-encoded C. reinhardtii proteome was predicted to be targeted to the chloroplast and 15% to the mitochondrion.