Potassium channels play a key role in regulating the flow of ions through the plasma membrane, orchestrating many cellular processes including cell volume regulation, hormone secretion and electrical impulse formation. Ligand peptides of potassium channels are molecules used in basic and applied research and are now considered promising alternatives in the treatment of many diseases, such as cardiovascular diseases and cancer. Currently, there are various bioinformatics tools focused on the prediction of peptides with different activities. However, none of the current tools can predict ligand peptides of potassium channels. In this work, we developed a tool called PPLK⁺C; this is the first tool that can predict peptide ligands of potassium channels. We also evaluated several amino acid molecular features and four machine-learning algorithms for the prediction of potassium channel ligand peptides: random forest, nearest neighbors, support vector machine and artificial neural network. All the biological data used in this study for training and validating models were obtained from peptides with experimentally verified activity. PPLK⁺C is a bioinformatics software written in the Python programming language, which showed a high predictive capacity with a model generated with the random forest algorithm: 0.77 sensitivity, 0.94 specificity, 0.91 accuracy and 0.70 Matthews correlation coefficient. PPLK⁺C is a novel tool with a friendly interface that can be used for the discovery of novel ligand peptides of potassium channels with high reliability, using only primary structure information.

钾离子通道在调节离子通过质膜的流动，协调许多细胞过程（包括细胞体积调节，激素分泌和电脉冲形成）中起着关键作用。钾通道的配体肽是基础研究和应用研究中使用的分子，现在被认为是治疗许多疾病（如心血管疾病和癌症）的有希望的替代方法。当前，有多种生物信息学工具致力于预测具有不同活性的肽。但是，当前的工具都无法预测钾通道的配体肽。在这项工作中，我们开发了一个名为PPLK ⁺的工具C; 这是第一个可以预测钾通道肽配体的工具。我们还评估了几种氨基酸分子特征和四种机器学习算法，用于预测钾通道配体肽：随机森林，最近邻居，支持向量机和人工神经网络。本研究中用于训练和验证模型的所有生物学数据均来自具有实验验证活性的多肽。PPLK ⁺ C是一种用Python编程语言编写的生物信息学软件，该模型具有通过随机森林算法生成的模型具有较高的预测能力：0.77灵敏度，0.94特异性，0.91准确性和0.70 Matthews相关系数。PPLK ⁺C是一种具有友好界面的新型工具，可仅使用一级结构信息就可以高度可靠地发现钾通道的新型配体肽。