摘要
神经毒素是一种应用非常广泛的毒素,因此有必要提出一种能够快速、准确预测神经毒素的算法.这里基于神经毒素蛋白质序列的n肽组分和序列的亲疏水性分布信息,提出了一种离散增量结合支持向量机的ID-SVM的算法,对神经毒素和细胞毒素进行了预测.为了将ID-SVM的预测算法和其它的预测算法进行比较,将ID-SVM算法应用到Saha和R aghava构建的神经毒素和非神经毒素的数据库上.预测结果显示,ID-SVM算法的预测结果高于Saha和R aghava所用的算法的预测结果.
Neurotoxins have very important application in research. So,it is necessary to predict them by using computer method. Here, based on the n-peptide components of local amino acid sequence and hydropathy,a new ID-SVM algorithm combined increment of diversity (ID) with support vector machines (SVM) is proposed to predict neurotoxins and cytotoxins. In order to estimate the effectiveness of the new algorithm,the neurotoxin and non-toxin datasets generated by Saha and Raghava are also used. The higher predictive success rates than the previous algorithms are obtained by the ID-SVM algorithm.
出处
《内蒙古大学学报(自然科学版)》
CAS
CSCD
北大核心
2009年第3期280-284,共5页
Journal of Inner Mongolia University:Natural Science Edition
基金
国家自然科学基金资助项目(30560039)
内蒙古自然科学基金资助项目(200607010101)
内蒙古自治区优秀学科带头人资助项目(20060702)