Predicting small ligand binding sites in proteins using backbone structure.
Predicting small ligand binding sites in proteins using backbone structure.
复制标题
DOI：
10.1093/bioinformatics/btn543
复制
发表时间：
2008-12-15
期刊：
影响因子：
5.8
通讯作者：
Bordner, Andrew J.
中科院分区：
文献类型：
--
作者：
Bordner, Andrew J.
动机：金属离子与配体（如核苷酸和辅因子）的特异性非共价结合对许多蛋白质的功能至关重要。在缺乏实验信息的情况下，计算方法对于预测这些结合位点的位置是有用的。使用结构信息的方法尤其有前途，因为它们可以潜在地识别仅使用氨基酸序列无法找到的非连续结合基序。此外，可以利用低分辨率模型的预测方法是有利的，因为高分辨率结构仅适用于相对较小部分的蛋白质。结果：SitePredict是一种基于机器学习的方法，用于预测特定金属离子或小分子在蛋白质结构中的结合位点。该方法使用随机森林分类器训练各种基于残留物的站点属性，包括残留物类型的空间聚类和进化保护。SitePredict在一组非冗余蛋白质-配体复合物结构中的六种不同金属离子和五种不同小分子的已知结合位点上进行交叉验证。所考虑的所有配体的预测性能都很好，AUC值至少为0.8。此外，对非束缚结构进行的更现实的测试表明，精度仅略有下降。对每个配体的预测精度贡献最大的性质也进行了检查。最后，讨论了同源模型和未表征蛋白中预测结合位点的例子。可用性：所有PDB蛋白结构和人类蛋白同源性模型的结合位点预测结果可在http://sitepredict.org/上获得。补充信息：补充数据可在Bioinformatics在线获取。
Motivation: Specific non-covalent binding of metal ions and ligands, such as nucleotides and cofactors, is essential for the function of many proteins. Computational methods are useful for predicting the location of such binding sites when experimental information is lacking. Methods that use structural information, when available, are particularly promising since they can potentially identify non-contiguous binding motifs that cannot be found using only the amino acid sequence. Furthermore, a prediction method that can utilize low-resolution models is advantageous because high-resolution structures are available for only a relatively small fraction of proteins. Results: SitePredict is a machine learning-based method for predicting binding sites in protein structures for specific metal ions or small molecules. The method uses Random Forest classifiers trained on diverse residue-based site properties including spatial clustering of residue types and evolutionary conservation. SitePredict was tested by cross-validation on a set of known binding sites for six different metal ions and five different small molecules in a non-redundant set of protein–ligand complex structures. The prediction performance was good for all ligands considered, as reflected by AUC values of at least 0.8. Furthermore, a more realistic test on unbound structures showed only a slight decrease in the accuracy. The properties that contribute the most to the prediction accuracy of each ligand were also examined. Finally, examples of predicted binding sites in homology models and uncharacterized proteins are discussed. Availability: Binding site prediction results for all PDB protein structures and human protein homology models are available at http://sitepredict.org/. Contact: bordner.andrew@mayo.edu Supplementary information: Supplementary data are available at Bioinformatics online.
登录
查看更多内容
Pfam：氏族、网络工具和服务。
影响因子：
14.9
作者：
Finn, Robert D.;Mistry, Jaina;Schuster-Bockler, Benjamin;Griffiths-Jones, Sam;Hollich, Volker;Lassmann, Timo;Moxon, Simon;Marshall, Mhairi;Khanna, Ajay;Durbin, Richard;Eddy, Sean R.;Sonnhammer, Erik L. L.;Bateman, Alex
通讯作者：
Bateman, Alex
影响因子：
--
作者：
Huang B;Schroeder M
通讯作者：
Schroeder M
影响因子：
5.8
作者：
Laurie, ATR;Jackson, RM
通讯作者：
Jackson, RM
影响因子：
5.6
作者：
BAKER, PJ;BRITTON, KL;STILLMAN, TJ
通讯作者：
STILLMAN, TJ
影响因子：
2.4
作者：
Guo, T;Shi, YX;Sun, ZR
通讯作者：
Sun, ZR