iSEE: Interface structure, evolution, and energy-based machine learning predictor of binding affinity changes upon mutations.

iSEE: Interface structure, evolution, and energy-based machine learning predictor of binding affinity changes upon mutations.
复制标题

DOI:
10.1002/prot.25630
复制
发表时间:
2019-03
期刊:
影响因子:
2.9
通讯作者:
Bonvin AMJJ
Bonvin AMJJ
中科院分区:
生物学4区
文献类型:
--
作者:
Geng C;Vangone A;Folkers GE;Xue LC;Bonvin AMJJ

文献摘要

参考文献

被引文献

相似文献

定量评价突变后结合亲和力的变化对于蛋白质工程和药物设计至关重要。基于机器学习的方法在这一领域正获得越来越大的发展势头。由于实验数据数量有限,使用少量敏感的预测特征对于此类机器学习方法的泛化性和鲁棒性至关重要。在这里,我们介绍了一个快速和可靠的预测结合亲和力的变化后,单点突变,基于随机森林的方法。我们的方法iSEE使用有限数量的界面结构、演化和基于能量的特征进行预测。iSEE仅使用31个特征,在由57种蛋白质-蛋白质复合物中的1102个突变组成的多样化训练数据集上实现了高预测性能,Pearson相关系数(PCC)为0.80,均方根误差为1.41 kcal/mol。它在两个盲法测试数据集上与现有的最先进方法竞争。对来自最近发表的SKEMPI 2.0数据库的56种蛋白质复合物中487个突变的新数据集的预测表明,目前的方法都没有表现良好(PCC < 0.42),尽管它们的组合确实改善了预测。iSEE的特征分析强调了进化保守性对于定量预测突变效应的重要性。作为应用实例,我们对MDM 2-p53复合物中的界面残基进行全突变扫描。
Quantitative evaluation of binding affinity changes upon mutations is crucial for protein engineering and drug design. Machine learning‐based methods are gaining increasing momentum in this field. Due to the limited number of experimental data, using a small number of sensitive predictive features is vital to the generalization and robustness of such machine learning methods. Here we introduce a fast and reliable predictor of binding affinity changes upon single point mutation, based on a random forest approach. Our method, iSEE, uses a limited number of interface Structure, Evolution, and Energy‐based features for the prediction. iSEE achieves, using only 31 features, a high prediction performance with a Pearson correlation coefficient (PCC) of 0.80 and a root mean square error of 1.41 kcal/mol on a diverse training dataset consisting of 1102 mutations in 57 protein‐protein complexes. It competes with existing state‐of‐the‐art methods on two blind test datasets. Predictions for a new dataset of 487 mutations in 56 protein complexes from the recently published SKEMPI 2.0 database reveals that none of the current methods perform well (PCC < 0.42), although their combination does improve the predictions. Feature analysis for iSEE underlines the significance of evolutionary conservations for quantitative prediction of mutation effects. As an application example, we perform a full mutation scanning of the interface residues in the MDM2–p53 complex.
DOI: 10.1098/rsif.2012.0835
发表时间: 2013-02
期刊: Journal of the Royal Society, Interface
影响因子: --
作者:
Kastritis PL;Bonvin AM
通讯作者: Bonvin AM
DOI: 10.1016/s0022-2836(02)00442-4
发表时间: 2002-07-05
影响因子: 5.6
作者:
Guerois, R;Nielsen, JE;Serrano, L
通讯作者: Serrano, L
DOI: 10.1038/s41598-017-08321-2
发表时间: 2017-08-14
期刊: Scientific reports
影响因子: 4.6
作者:
Moreira IS;Koukos PI;Melo R;Almeida JG;Preto AJ;Schaarschmidt J;Trellet M;Gümüş ZH;Costa J;Bonvin AMJJ
通讯作者: Bonvin AMJJ
DOI: 10.1371/journal.pone.0107353
发表时间: 2014
期刊: PloS one
影响因子: 3.7
作者:
Berliner N;Teyra J;Colak R;Garcia Lopez S;Kim PM
通讯作者: Kim PM
DOI: 10.1021/ct4000372
发表时间: 2013-03-01
影响因子: 5.5
作者:
Martins, Silvia A.;Perez, Marta A. S.;Fernandes, P. A.
通讯作者: Fernandes, P. A.