计算机与现代化 ›› 2024, Vol. 0 ›› Issue (07): 7-12.doi: 10.3969/j.issn.1006-2475.2024.07.002

• 人工智能 • 上一篇    下一篇

 一种面向生物基因多序列比对算法的任务调度方法


  

  1. (广州华商学院数据科学学院,广东 广州 511300)
  • 出版日期:2024-07-25 发布日期:2024-08-07
  • 基金资助:
    国家自然科学基金面上项目(61972444); 广州华商学院校内科研导师制项目(2023HSDS34)

A Task Scheduling Method for Biological Gene Multi Sequence Alignment Algorithm

  1. (School of Data Science, Guangzhou Huashang College, Guangzhou 511300, China)
  • Online:2024-07-25 Published:2024-08-07

摘要: 摘要:针对现阶段生物基因多序列比对算法在面对大规模数据时存在比对效率慢的问题,提出一种面向生物基因多序列比对算法的任务调度方法,以提高生物基因多序列比对的效率。通过Trie树方法对生物基因多序列数据展开分割处理,从而提高后续基因多序列比对过程中数据查找和匹配的效率;构建基因多序列BWT索引,利用BWT索引方法完成生物基因多序列比对;以多序列比对方法为基础,采用CPU与GPU异构并行系统完成多序列比对的任务调度。实验结果表明,所提的面向生物基因多序列比对算法的任务调度方法效率更高、性能更好,且更适合于实际应用。

关键词: 生物基因, 任务调度, 多序列比对, CPU与GPU, BWT索引方法

Abstract: Abstract: Aiming at the problem of slow alignment efficiency in current biological gene multi sequence alignment algorithms when facing large-scale data, a task scheduling method for biological gene multi sequence alignment algorithms is proposed to improve the efficiency of biological gene multi sequence alignment. Firstly, the Trie tree method is used to segment biological gene multi sequence data, thereby optimizing the efficiency of data search and matching in the subsequent gene multi sequence alignment process; Secondly a gene multi sequence BWT index is constructed and the BWT index method is used to complete biological gene multi sequence alignment; Finally, based on the multi sequence alignment method, a heterogeneous parallel system of CPU and GPU is used to complete the task scheduling of multi sequence alignment. The experimental results show that the proposed task scheduling method for biological gene multi sequence alignment algorithm is more efficient, performs better, and is more suitable for practical applications.

Key words:  , biological genes; task scheduling; multiple sequence alignment; CPU and GPU; BWT indexing method

中图分类号: