Hunan Provincial Key Laboratory on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha 410083, China.
School of Computer and Information Technology, Xinyang Normal University, Xinyang 464000, China.
Bioinformatics. 2020 Dec 30;36(Suppl_2):i735-i744. doi: 10.1093/bioinformatics/btaa806.
Knowledge of protein-binding residues (PBRs) improves our understanding of protein-protein interactions, contributes to the prediction of protein functions and facilitates protein-protein docking calculations. While many sequence-based predictors of PBRs were published, they offer modest levels of predictive performance and most of them cross-predict residues that interact with other partners. One unexplored option to improve the predictive quality is to design consensus predictors that combine results produced by multiple methods.
We empirically investigate predictive performance of a representative set of nine predictors of PBRs. We report substantial differences in predictive quality when these methods are used to predict individual proteins, which contrast with the dataset-level benchmarks that are currently used to assess and compare these methods. Our analysis provides new insights for the cross-prediction concern, dissects complementarity between predictors and demonstrates that predictive performance of the top methods depends on unique characteristics of the input protein sequence. Using these insights, we developed PROBselect, first-of-its-kind consensus predictor of PBRs. Our design is based on the dynamic predictor selection at the protein level, where the selection relies on regression-based models that accurately estimate predictive performance of selected predictors directly from the sequence. Empirical assessment using a low-similarity test dataset shows that PROBselect provides significantly improved predictive quality when compared with the current predictors and conventional consensuses that combine residue-level predictions. Moreover, PROBselect informs the users about the expected predictive quality for the prediction generated from a given input protein.
PROBselect is available at http://bioinformatics.csu.edu.cn/PROBselect/home/index.
Supplementary data are available at Bioinformatics online.
了解蛋白质结合残基 (PBR) 可以帮助我们更好地理解蛋白质-蛋白质相互作用，有助于预测蛋白质的功能，并促进蛋白质-蛋白质对接计算。虽然已经发表了许多基于序列的 PBR 预测器，但它们的预测性能都不高，而且大多数预测器都可以预测与其他伴侣相互作用的残基。提高预测质量的一种未被探索的选择是设计结合多种方法结果的共识预测器。
我们实证研究了一组 9 个 PBR 预测器的代表性集合的预测性能。当这些方法用于预测单个蛋白质时，我们报告了预测质量的显著差异，这与目前用于评估和比较这些方法的数据集级别基准形成对比。我们的分析为交叉预测问题提供了新的见解，剖析了预测器之间的互补性，并证明了顶级方法的预测性能取决于输入蛋白质序列的独特特征。利用这些见解，我们开发了 PROBselect，这是首个 PBR 共识预测器。我们的设计基于蛋白质水平上的动态预测器选择，其中选择依赖于回归模型，该模型可以直接从序列中准确估计所选预测器的预测性能。使用低相似度测试数据集进行的实证评估表明，与当前的预测器和结合残基预测的传统共识相比，PROBselect 提供了显著提高的预测质量。此外，PROBselect 可以为用户提供有关从给定输入蛋白质生成的预测的预期预测质量的信息。
PROBselect 可在 http://bioinformatics.csu.edu.cn/PROBselect/home/index 上获得。
补充数据可在 Bioinformatics 在线获得。
