iBitter-SCM: Identi fication and characterization of bitter peptides using a scoring card method with propensity scores of dipeptides
iBitter-SCM: Identi fication and characterization of bitter peptides using a scoring card method with propensity scores of dipeptides
复制标题
DOI：
10.1016/j.ygeno.2020.03.019
复制
发表时间：
2020-07-01
期刊：
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;Yana, Janchai;Shoombuatong, Watshara
一般来说，水解蛋白、植物源性生物碱和毒素表现出令人不快的苦味。因此，对苦味的感知在保护动物免受有毒植物和环境毒素的侵害方面起着至关重要的作用。治疗肽作为一种新型药物引起了人们的广泛关注。苦肽的成功鉴定和表征对药物开发和营养研究具有重要意义。由于后基因组时代产生了大量的肽，迫切需要开发快速有效地区分苦肽和非苦肽的计算方法。据我们所知，目前还没有利用序列信息预测和分析苦味肽的计算模型。在这项研究中，我们首次提出了一个名为iBitter-SCM的计算模型，该模型可以直接从氨基酸序列中预测肽的苦味，而不依赖于它们的功能域或结构信息。iBitter-SCM是一种简单有效的方法，它采用记分卡法（SCM）估算氨基酸和二肽的倾向得分。我们的基准测试结果表明，iBitter-SCM在独立数据集上的准确性和马修斯系数相关性分别为84.38%和0.688。严格的独立测试表明，由于其简单性、可解释性和可实现性，iBitterSCM优于其他广泛使用的机器学习分类器（如k近邻、朴素贝叶斯、决策树和随机森林）。此外，对氨基酸和二肽的估计倾向得分进行了分析，以更好地了解苦味肽的生物物理和生化特性。为了方便实验科学家，在http://camt.pythonanywhere.com/ iBitter-SCM上公开提供了一个web服务器。预计该方法将为苦味肽的高通量预测和重新设计提供重要的工具。
In general, hydrolyzed proteins, plant-derived alkaloids and toxins displays unpleasant bitter taste. Thus, the perception of bitter taste plays a crucial role in protecting animals from poisonous plants and environmental toxins. Therapeutic peptides have attracted great attention as a new drug class. The successful identification and characterization of bitter peptides are essential for drug development and nutritional research. Owing to the large volume of peptides generated in the post-genomic era, there is an urgent need to develop computational methods for rapidly and effectively discriminating bitter peptides from non-bitter peptides. To the best of our knowledge, there is yet no computational model for predicting and analyzing bitter peptides using sequence information. In this study, we present for the first time a computational model called the iBitter-SCM that can predict the bitterness of peptides directly from their amino acid sequence without any dependence on their functional domain or structural information. iBitter-SCM is a simple and effective method that was built using the scoring card method (SCM) with estimated propensity scores of amino acids and dipeptides. Our benchmarking results demonstrated that iBitter-SCM achieved an accuracy and Matthews coefficient correlation of 84.38% and 0.688, respectively, on the independent dataset. Rigorous independent test indicated that iBitterSCM was superior to those of other widely used machine-learning classifiers (e.g. k-nearest neighbor, naive Bayes, decision tree and random forest) owing to its simplicity, interpretability and implementation. Furthermore, the analysis of estimated propensity scores of amino acids and dipeptides were performed to provide a better understanding of the biophysical and biochemical properties of bitter peptides. For the convenience of experimental scientists, a web server is provided publicly at http://camt.pythonanywhere.com/ iBitter-SCM. It is anticipated that iBitter-SCM can serve as an important tool to facilitate the high-throughput prediction and de novo design of bitter peptides.