摘要: 生物信息学应用领域存在高维小样本和内部空间疏散的特性,因而数据分析面临着巨大的挑战。基于此,在蚁群算法的搜索过程中将特征的信噪比作为先验信息,结合支撑向量用于筛选血清蛋白相关生物标记物,实验结果表明,该方法建立的癌症诊断模型取得了较好的分类性能测试仿真结果,敏感度和特异度分别达到94%和92.4%。
关键词:
表面增强激光解析电离飞行时间质谱,
蛋白质组学,
蚁群优化算法,
特征选择技术,
生物标记物
Abstract:
The high dimensional and small sample sizes natures of bioinformatics pose a great challenge for many modeling problems. A novel method is raised that combines using SNR as prior information in the Ant Colony Optimization(ACO) searching process. Combined with support vector machines, it is applied to identify relevant serum proteomic biomarkers. Experimental results show that the proposed method has strong power in distinguishing cancer patients from healthy individuals, and yields up to 94% sensitivity and 92.4% specificity.
Key words:
Surface-Enhanced Laster Desorption/Ionization Time-Of-Flight Mass Spectrometry(SELDI-TOF-MS),
proteomics,
Ant Colony Optimization(ACO) algorithm,
feature selection technology,
biomarker
中图分类号:
张 蓉;冯 斌. 基于ACO-SVM的质谱数据分析[J]. 计算机工程, 2010, 36(4): 158-160.
ZHANG Rong; FENG Bin. Analysis of Mass Spectral Data Based on ACO-SVM[J]. Computer Engineering, 2010, 36(4): 158-160.