首页|基于改进支持向量机的高通量测序生物仪器数据分析研究

基于改进支持向量机的高通量测序生物仪器数据分析研究

扫码查看
针对高通量测序生物仪器在获得基因序列数据后对序列缺失分析效率低、耗时长的缺点.研究将支持向量机用于序列缺失数据特征提取,再利用粒子群优化算法对支持向量机进行改进,并用于构建一种全新的基因缺失分析模型.结果表明,基因序列分析模型的数据处理精确率平均值和数据缺失误报率平均值分别为 96.81%和 1.85%.同时基因序列分析模型的数据计算效率平均值和F1 值分别为95.81%和0.91.这说明研究构建的基因序列分析模型在处理基因缺失数据时,序列缺失分析模型不仅计算效率高,还能够有效提升基因缺失数据分类的性能,实现基因缺失的高效、准确检测,并为生物信息学和基因组学领域的研究提供新的分析工具.
Research on High throughput Sequencing Bioinstrument Data Analysis Based on Improved Support Vector Machine
Aiming at the drawbacks of low efficiency and long time consumption in sequence deletion analysis of high-throughput sequencing biological instruments after obtaining gene sequence data.The study applies support vector machine for feature extraction of missing sequence data,and then improves the support vector machine using particle swarm optimization algorithm to construct a new gene deletion analysis model.The results showed that the average data processing accuracy and data missing false alarm rate of the gene sequence analysis model were 96.81%and 1.85%,respectively.The average data calculation efficiency and F1 value of the gene sequence analysis model are 95.81%and 0.91,respectively.This indicates that the gene sequence analysis model constructed in the study not only has high computational efficiency when processing gene deletion data,but also can effectively improve the perform-ance of gene deletion data classification,achieve efficient and accurate detection of gene deletions,and provide new analytical tools for research in the fields of bioinformatics and genomics.

support vector machineparticle swarm optimization algorithmhigh throughput sequencingbiological instrumentsdata analysis

李苗、张纯瑜、李晓艳

展开 >

西安思源学院,西安 710038

支持向量机 粒子群优化算法 高通量测序 生物仪器 数据分析

2024

自动化与仪器仪表
重庆工业自动化仪表研究所,重庆市自动化与仪器仪表学会

自动化与仪器仪表

CSTPCD
影响因子:0.327
ISSN:1001-9227
年,卷(期):2024.(11)