Using Reduced Amino Acid Alphabet and Biological Properties to Analyze and Predict Animal Neurotoxin Protein

Author(s): Yao Yu, Shiyuan Wang, Yakun Wang, Yiyin Cao, Chunlu Yu, Yi Pan, Dongqing Su, Qianzi Lu, Yongchun Zuo*, Lei Yang*

Journal Name: Current Drug Metabolism

Volume 21 , Issue 10 , 2020

Become EABM
Become Reviewer
Call for Editor

Graphical Abstract:


Aims: Because of the high affinity of these animal neurotoxin proteins for some special target site, they were usually used as pharmacological tools and therapeutic agents in medicine to gain deep insights into the function of the nervous system.

Background and Objective: The animal neurotoxin proteins are one of the most common functional groups among the animal toxin proteins. Thus, it was very important to characterize and predict the animal neurotoxin proteins.

Methods: In this study, the differences between the animal neurotoxin proteins and non-toxin proteins were analyzed.

Result: Significant differences were found between them. In addition, the support vector machine was proposed to predict the animal neurotoxin proteins. The predictive results of our classifier achieved the overall accuracy of 96.46%. Furthermore, the random forest and k-nearest neighbors were applied to predict the animal neurotoxin proteins.

Conclusion: The compared results indicated that the predictive performances of our classifier were better than other two algorithms.

Keywords: Neurotoxin protein, reduced amino acid alphabet, biological property, support vector machine, non-toxin protein, pharmacological tools.

Rights & PermissionsPrintExport Cite as

Article Details

Year: 2020
Published on: 15 December, 2020
Page: [810 - 817]
Pages: 8
DOI: 10.2174/1389200221666200520090555
Price: $65

Article Metrics

PDF: 9