iDPPIV-SCM: A Sequence-Based Predictor for Identifying and Analyzing Dipeptidyl Peptidase IV (DPP-IV) Inhibitory Peptides Using a Scoring Card Method
iDPPIV-SCM: A Sequence-Based Predictor for Identifying and Analyzing Dipeptidyl Peptidase IV (DPP-IV) Inhibitory Peptides Using a Scoring Card Method
复制标题
DOI：
10.1021/acs.jproteome.0c00590
复制
发表时间：
2020-10-02
影响因子：
4.4
通讯作者：
Shoombuatong, Watshara
中科院分区：
文献类型：
--
作者：
Charoenkwan, Phasit;Kanthawong, Sakawrat;Shoombuatong, Watshara
二肽基肽酶IV（DPP-IV，E.C.3.4.14.5）的抑制被公认为治疗2型糖尿病（T2 D）的新途径。到目前为止，肽样DDP-IV抑制剂已被证明可以使T2 D受试者的血糖浓度正常化。据我们所知，目前还没有使用序列信息预测和分析DPP-IV抑制肽的计算模型。在这项研究中，我们首次提出了一个简单，易于解释的基于序列的预测使用记分卡方法（SCM）建模的DPP-IV抑制肽（iDPPIV-SCM）的生物活性。特别地，iDPPIV-SCM是通过采用SCM方法与氨基酸的倾向评分一起开发的。严格的独立测试结果表明，所提出的iDPPIV-SCM被发现上级众所周知的机器学习（ML）分类器（例如，k-最近邻、逻辑回归和决策树），其准确性、MCC和AUC分别提高了2-11、4-22和7-10%，同时还实现了与支持向量机相当的结果。此外，对源自iDPPIV-SCM的氨基酸的估计倾向评分进行了分析，以便更深入地了解增强DPP-IV抑制效力的分子基础。总之，这些结果表明，iDPPIV-SCM由于其简单性、可解释性和有效性而优于其他知名ML分类器的上级。为了方便生物学家，预测模型被部署为可公开访问的Web服务器，网址为http://camt.pythonanywhere.com/iDPPIV-SCM。预计iDPPIV-SCM可以作为一个重要的工具，用于快速筛选有前途的DPP-IV抑制肽之前，他们的合成。
The inhibition of dipeptidyl peptidase IV (DPP-IV, E.C.3.4.14.5) is well recognized as a new avenue for the treatment of Type 2 diabetes (T2D). Until now, peptide-like DDP-IV inhibitors have been shown to normalize the blood glucose concentration in T2D subjects. To the best of our knowledge, there is yet no computational model for predicting and analyzing DPP-IV inhibitory peptides using sequence information. In this study, we present for the first time a simple and easily interpretable sequence-based predictor using the scoring card method (SCM) for modeling the bioactivity of DPP-IV inhibitory peptides (iDPPIV-SCM). Particularly, the iDPPIV-SCM was developed by employing the SCM method together with the propensity scores of amino acids. Rigorous independent test results demonstrated that the proposed iDPPIV-SCM was found to be superior to those of well-known machine learning (ML) classifiers (e.g., k-nearest neighbor, logistic regression, and decision tree) with demonstrated improvements of 2-11, 4-22, and 7-10% for accuracy, MCC, and AUC, respectively, while also achieving comparable results to that of the support vector machine. Furthermore, the analysis of estimated propensity scores of amino acids as derived from the iDPPIV-SCM was performed so as to provide a more in-depth understanding on the molecular basis for enhancing the DPP-IV inhibitory potency. Taken together, these results revealed that iDPPIV-SCM was superior to those of other well-known ML classifiers owing to its simplicity, interpretability, and validity. For the convenience of biologists, the predictive model is deployed as a publicly accessible web server at http://camt.pythonanywhere.com/iDPPIV-SCM. It is anticipated that iDPPIV-SCM can serve as an important tool for the rapid screening of promising DPP-IV inhibitory peptides prior to their synthesis.