Fan Guo-Liang, Liu Yan-Ling, Wang Hui
Department of Physics, School of Physical Science and Technology, Inner Mongolia University, Hohhot 010021, China.
Department of Physics, School of Physical Science and Technology, Inner Mongolia University, Hohhot 010021, China.
J Theor Biol. 2016 Oct 21;407:138-142. doi: 10.1016/j.jtbi.2016.07.010. Epub 2016 Jul 7.
Thermophilic proteins can thrive stalely at the high temperatures. Identification of thermophilic protein could be helpful to learn the function of protein. Automated prediction of thermophilic protein is an important tool for genome annotation. In this work, a powerful predictor is proposed by combining amino acid composition, evolutionary information, and acid dissociation constant. The overall prediction accuracy of 93.53% was obtained for using the algorithm of support vector machine. In order to check the performance of our method, two low-similarity independent testing datasets are used to test the proposed method. Comparisons with other methods show that the prediction results were better than other existing methods in literature. This indicates that our approach was effective to predict thermophilic proteins.
嗜热蛋白能够在高温下稳定存在。嗜热蛋白的鉴定有助于了解蛋白质的功能。嗜热蛋白的自动预测是基因组注释的重要工具。在这项工作中，通过结合氨基酸组成、进化信息和酸解离常数，提出了一种强大的预测器。使用支持向量机算法获得了93.53%的总体预测准确率。为了检验我们方法的性能，使用了两个低相似度的独立测试数据集来测试所提出的方法。与其他方法的比较表明，预测结果优于文献中其他现有方法。这表明我们的方法对于预测嗜热蛋白是有效的。
