Shu Nanjiang, Zhou Tuping, Hovmöller Sven
Structural Chemistry, Arrhenius Laboratory, Stockholm University, SE-106 91 Stockholm, Sweden.
Bioinformatics. 2008 Mar 15;24(6):775-82. doi: 10.1093/bioinformatics/btm618. Epub 2008 Feb 1.
Motivated by the abundance, importance and unique functionality of zinc, both biologically and physiologically, we have developed an improved method for the prediction of zinc-binding sites in proteins from their amino acid sequences.
By combining support vector machine (SVM) and homology-based predictions, our method predicts zinc-binding Cys, His, Asp and Glu with 75% precision (86% for Cys and His only) at 50% recall according to a 5-fold cross-validation on a non-redundant set of protein chains from the Protein Data Bank (PDB) (2727 chains, 235 of which bind zinc). Consequently, our method predicts zinc-binding Cys and His with 10% higher precision at different recall levels compared to a recently published method when tested on the same dataset.
The program is available for download at www.fos.su.se/~nanjiang/zincpred/download/
受锌在生物学和生理学上的丰富性、重要性及独特功能的驱动，我们开发了一种改进方法，可根据蛋白质的氨基酸序列预测其锌结合位点。
通过结合支持向量机（SVM）和基于同源性的预测，我们的方法在对蛋白质数据银行（PDB）的一组非冗余蛋白质链（2727条链，其中235条结合锌）进行5折交叉验证时，以50%的召回率预测锌结合的半胱氨酸（Cys）、组氨酸（His）、天冬氨酸（Asp）和谷氨酸（Glu），精确率达75%（仅Cys和His时为86%）。因此，在同一数据集上测试时，与最近发表的方法相比，我们的方法在不同召回水平下预测锌结合的Cys和His时，精确率高10%。
