Machine Learning Model for Identifying Antioxidant Proteins Using Features Calculated from Primary Sequences.
Machine Learning Model for Identifying Antioxidant Proteins Using Features Calculated from Primary Sequences.
复制标题
DOI：
10.3390/biology9100325
复制
发表时间：
2020-10-06
期刊：
影响因子：
4.2
通讯作者：
Le NQK
中科院分区：
文献类型：
--
作者：
Ho Thanh Lam L;Le NH;Van Tuan L;Tran Ban H;Nguyen Khanh Hung T;Nguyen NTK;Huu Dang L;Le NQK
抗氧化化合物保护人体免受多种疾病以及年龄的退化。在上个世纪发现的几种微量营养素，如维生素A、C和E，在我们的生活中变得很受欢迎。科学家们不仅通过实验室实验，还通过计算机辅助，试图找到越来越多的抗氧化化合物。我们的研究利用了一种快速和经济的抗氧化剂化合物的鉴定计算方法。该研究提出了一种预测器，用于检测抗氧化剂的准确率高达84.6%。因此，我们的预测是有希望成为一个有用的工具，发现一个新的抗氧化剂化合物。抗氧化蛋白参与细胞生命活动的许多方面。它们保护细胞和DNA免受氧化物质（如过氧化物，一氧化氮，氧自由基等）的侵害。它们被称为活性氧（ROS）。自由基生成和抗氧化防御是人体中的对立因素，它们之间的平衡是保持健康身体所必需的。一个不健康的日常生活或年龄的退化可以打破平衡，导致更多的活性氧比抗氧化剂，造成损害健康。一般来说，抗氧化机制是抗氧化剂分子和ROS在单电子反应中结合。创建计算模型，以及时识别抗氧化剂候选人是在实验室中支持抗氧化剂检测实验至关重要。在这项研究中，我们提出了一个基于机器学习的模型，用于从一组基准测序数据中进行预测。实验通过对训练过程使用10倍交叉验证进行，并通过三个不同的独立数据集进行验证。不同的机器学习和深度学习算法已经在最佳序列特征集上进行了评估。其中，随机森林被认为是识别抗氧化蛋白质的最佳模型，具有最高的性能。我们的最佳模型实现了84.6%的高准确率，以及在训练数据集上识别抗氧化蛋白的灵敏度（81.5%）和特异性（85.1%）的平衡。来自不同独立数据集的性能结果也显示了我们的模型与先前发表的抗氧化蛋白鉴定工作相比的重要性。
Antioxidant compounds protect the human body from many kinds of diseases as well as the degeneration of age. Several micronutrients that were found in the last century such as vitamins A, C, and E have become popular in our life. Scientists are trying to find more and more antioxidant compounds not only from experimenting in the laboratory but also from assisting by the computer. Our research utilized a computational method for the swift and economic identification of antioxidant compounds. The research presents a predictor that got a high accuracy of 84.6% for the detection of antioxidants. Therefore, our predictor is promising to be a useful tool to discover a new antioxidant compound. Antioxidant proteins are involved importantly in many aspects of cellular life activities. They protect the cell and DNA from oxidative substances (such as peroxide, nitric oxide, oxygen-free radicals, etc.) which are known as reactive oxygen species (ROS). Free radical generation and antioxidant defenses are opposing factors in the human body and the balance between them is necessary to maintain a healthy body. An unhealthy routine or the degeneration of age can break the balance, leading to more ROS than antioxidants, causing damage to health. In general, the antioxidant mechanism is the combination of antioxidant molecules and ROS in a one-electron reaction. Creating computational models to promptly identify antioxidant candidates is essential in supporting antioxidant detection experiments in the laboratory. In this study, we proposed a machine learning-based model for this prediction purpose from a benchmark set of sequencing data. The experiments were conducted by using 10-fold cross-validation on the training process and validated by three different independent datasets. Different machine learning and deep learning algorithms have been evaluated on an optimal set of sequence features. Among them, Random Forest has been identified as the best model to identify antioxidant proteins with the highest performance. Our optimal model achieved high accuracy of 84.6%, as well as a balance in sensitivity (81.5%) and specificity (85.1%) for antioxidant protein identification on the training dataset. The performance results from different independent datasets also showed the significance in our model compared to previously published works on antioxidant protein identification.
登录
查看更多内容
DOI：
10.4103/0973-7847.70902
发表时间：
2010-07
期刊：
Pharmacognosy reviews
影响因子：
--
作者：
Lobo V;Patil A;Phatak A;Chandra N
通讯作者：
Chandra N
AOPs-SVM：使用支持向量机的基于序列的抗氧化蛋白分类器
影响因子：
5.7
作者：
Meng, Chaolu;Jin, Shunshan;Zou, Quan
通讯作者：
Zou, Quan
iLearn：一个集成平台和元学习器，用于 DNA、RNA 和蛋白质序列数据的特征工程、机器学习分析和建模
影响因子：
9.5
作者：
Chen, Zhen;Zhao, Pei;Song, Jiangning
通讯作者：
Song, Jiangning
DOI：
10.1073/pnas.92.19.8700
发表时间：
1995-09-12
影响因子：
11.1
作者：
DUBCHAK, I;MUCHNIK, I;KIM, SH
通讯作者：
KIM, SH
影响因子：
--
作者：
Le NQK;Do DT;Chiu FY;Yapp EKY;Yeh HY;Chen CY
通讯作者：
Chen CY