Abstract:
Ubiquitination is an essential post-translational modification mechanism involving the ubiquitin protein\'s bonding to a substrate protein. It is crucial in a variety of physiological activities including cell survival and differentiation, and innate and adaptive immunity. Any alteration in the ubiquitin system leads to the development of various human diseases. Numerous researches show the highly reversibility and dynamic of ubiquitin system, making the experimental identification quite difficult. To solve this issue, this article develops a model using a machine learning approach, tending to improve the ubiquitin protein prediction precisely. We deeply investigate the ubiquitination data that is proceed through different features extraction methods, followed by the classification. The evaluation and assessment are conducted considering Jackknife tests and 10-fold cross-validation. The proposed method demonstrated the remarkable performance in terms of 100 %, 99.88 %, and 99.84 % accuracy on Dataset-I, Dataset-II, and Dataset-III, respectively. Using Jackknife test, the method achieves 100 %, 99.91 %, and 99.99 % for Dataset-I, Dataset-II and Dataset-III, respectively. This analysis concludes that the proposed method outperformed the state-of-the-arts to identify the ubiquitination sites and helpful in the development of current clinical therapies. The source code and datasets will be made available at Github.
摘要:
泛素化是一种重要的翻译后修饰机制,涉及泛素蛋白与底物蛋白的结合。它在包括细胞存活和分化在内的多种生理活动中至关重要,以及先天和适应性免疫。泛素系统的任何改变都会导致各种人类疾病的发展。大量研究表明,泛素系统具有高度的可逆性和动态性,使实验鉴定相当困难。为了解决这个问题,本文使用机器学习方法开发了一个模型,倾向于提高泛素蛋白预测的准确性。我们深入研究了通过不同特征提取方法进行的泛素化数据,其次是分类。评估和评估是考虑Jackknife测试和10倍交叉验证进行的。所提出的方法在100%方面表现出了显著的性能,99.88%,数据集-I的准确率为99.84%,Dataset-II,和数据集-III,分别。使用刀刀测试,该方法达到100%,99.91%,和99.99%的数据集-I,数据集-II和数据集-III,分别。该分析得出的结论是,所提出的方法在识别泛素化位点方面优于现有技术,并有助于开发当前的临床疗法。源代码和数据集将在Github上提供。