• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

用于求解基因调控网络时间动态的图形处理单元增强型遗传算法

Graphics Processing Unit-Enhanced Genetic Algorithms for Solving the Temporal Dynamics of Gene Regulatory Networks.

作者信息

García-Calvo Raúl, Guisado J L, Diaz-Del-Rio Fernando, Córdoba Antonio, Jiménez-Morales Francisco

机构信息

Department of Computer Architecture and Technology, University of Seville, Seville, Spain.

Department of Condensed Matter Physics, University of Seville, Seville, Spain.

出版信息

Evol Bioinform Online. 2018 Apr 10;14:1176934318767889. doi: 10.1177/1176934318767889. eCollection 2018.

DOI:10.1177/1176934318767889
PMID:29662297
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC5898668/
Abstract

Understanding the regulation of gene expression is one of the key problems in current biology. A promising method for that purpose is the determination of the temporal dynamics between known initial and ending network states, by using simple acting rules. The huge amount of rule combinations and the nonlinear inherent nature of the problem make genetic algorithms an excellent candidate for finding optimal solutions. As this is a computationally intensive problem that needs long runtimes in conventional architectures for realistic network sizes, it is fundamental to accelerate this task. In this article, we study how to develop efficient parallel implementations of this method for the fine-grained parallel architecture of graphics processing units (GPUs) using the compute unified device architecture (CUDA) platform. An exhaustive and methodical study of various parallel genetic algorithm schemes-master-slave, island, cellular, and hybrid models, and various individual selection methods (roulette, elitist)-is carried out for this problem. Several procedures that optimize the use of the GPU's resources are presented. We conclude that the implementation that produces better results (both from the performance and the genetic algorithm fitness perspectives) is simulating a few thousands of individuals grouped in a few islands using elitist selection. This model comprises 2 mighty factors for discovering the best solutions: finding good individuals in a short number of generations, and introducing genetic diversity via a relatively frequent and numerous migration. As a result, we have even found the optimal solution for the analyzed gene regulatory network (GRN). In addition, a comparative study of the performance obtained by the different parallel implementations on GPU versus a sequential application on CPU is carried out. In our tests, a multifold speedup was obtained for our optimized parallel implementation of the method on medium class GPU over an equivalent sequential single-core implementation running on a recent Intel i7 CPU. This work can provide useful guidance to researchers in biology, medicine, or bioinformatics in how to take advantage of the parallelization on massively parallel devices and GPUs to apply novel metaheuristic algorithms powered by nature for real-world applications (like the method to solve the temporal dynamics of GRNs).

摘要

理解基因表达调控是当前生物学的关键问题之一。为此，一种很有前景的方法是通过使用简单的作用规则来确定已知初始和结束网络状态之间的时间动态。大量的规则组合以及问题固有的非线性性质使得遗传算法成为寻找最优解的理想选择。由于这是一个计算密集型问题，对于实际网络规模而言，在传统架构中需要很长的运行时间，因此加速这项任务至关重要。在本文中，我们研究如何使用计算统一设备架构（CUDA）平台为图形处理单元（GPU）的细粒度并行架构开发该方法的高效并行实现。针对此问题，对各种并行遗传算法方案——主从、岛屿、细胞和混合模型，以及各种个体选择方法（轮盘赌、精英主义）进行了详尽且系统的研究。提出了几种优化GPU资源使用的程序。我们得出结论，从性能和遗传算法适应度角度来看，产生更好结果的实现方式是使用精英主义选择，模拟数千个个体并将其分组到几个岛屿中。该模型包含发现最佳解决方案的两个强大因素：在短代内找到优秀个体，以及通过相对频繁且大量的迁移引入遗传多样性。结果，我们甚至找到了所分析基因调控网络（GRN）的最优解。此外，还对GPU上不同并行实现与CPU上的顺序应用所获得的性能进行了比较研究。在我们的测试中，与在最新的英特尔i7 CPU上运行的等效顺序单核实现相比，我们在中等档次GPU上对该方法的优化并行实现获得了数倍的加速。这项工作可以为生物学、医学或生物信息学领域的研究人员提供有用的指导，帮助他们利用大规模并行设备和GPU上的并行化，将受自然启发的新型元启发式算法应用于实际应用（如解决GRN时间动态的方法）。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/2d83946df949/10.1177_1176934318767889-fig18.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/71f3d83a4d7d/10.1177_1176934318767889-fig1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/8e3b2078e504/10.1177_1176934318767889-fig2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/b592e840a46e/10.1177_1176934318767889-fig3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/ca0a0c47c91c/10.1177_1176934318767889-fig4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/cec4e9bdf3a3/10.1177_1176934318767889-fig5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/491dcafdc968/10.1177_1176934318767889-fig6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/0a51e4731566/10.1177_1176934318767889-fig7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/00924814cf72/10.1177_1176934318767889-fig8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/be5af032e2ff/10.1177_1176934318767889-fig9.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/86a4d47e4fcb/10.1177_1176934318767889-fig10.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/ca2b674e3ad8/10.1177_1176934318767889-fig11.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/451a7903c48c/10.1177_1176934318767889-fig12.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/988e7383c85e/10.1177_1176934318767889-fig13.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/9511a3d5bd89/10.1177_1176934318767889-fig14.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/7f8a9903a697/10.1177_1176934318767889-fig15.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/3ed8dd40a409/10.1177_1176934318767889-fig16.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/b477eb9a3376/10.1177_1176934318767889-fig17.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/2d83946df949/10.1177_1176934318767889-fig18.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/71f3d83a4d7d/10.1177_1176934318767889-fig1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/8e3b2078e504/10.1177_1176934318767889-fig2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/b592e840a46e/10.1177_1176934318767889-fig3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/ca0a0c47c91c/10.1177_1176934318767889-fig4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/cec4e9bdf3a3/10.1177_1176934318767889-fig5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/491dcafdc968/10.1177_1176934318767889-fig6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/0a51e4731566/10.1177_1176934318767889-fig7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/00924814cf72/10.1177_1176934318767889-fig8.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/be5af032e2ff/10.1177_1176934318767889-fig9.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/86a4d47e4fcb/10.1177_1176934318767889-fig10.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/ca2b674e3ad8/10.1177_1176934318767889-fig11.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/451a7903c48c/10.1177_1176934318767889-fig12.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/988e7383c85e/10.1177_1176934318767889-fig13.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/9511a3d5bd89/10.1177_1176934318767889-fig14.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/7f8a9903a697/10.1177_1176934318767889-fig15.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/3ed8dd40a409/10.1177_1176934318767889-fig16.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/b477eb9a3376/10.1177_1176934318767889-fig17.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1b31/5898668/2d83946df949/10.1177_1176934318767889-fig18.jpg

相似文献

1
Graphics Processing Unit-Enhanced Genetic Algorithms for Solving the Temporal Dynamics of Gene Regulatory Networks.用于求解基因调控网络时间动态的图形处理单元增强型遗传算法
Evol Bioinform Online. 2018 Apr 10;14:1176934318767889. doi: 10.1177/1176934318767889. eCollection 2018.
2
NMF-mGPU: non-negative matrix factorization on multi-GPU systems.NMF-mGPU：多GPU系统上的非负矩阵分解
BMC Bioinformatics. 2015 Feb 13;16:43. doi: 10.1186/s12859-015-0485-4.
3
Inference of dynamic spatial GRN models with multi-GPU evolutionary computation.使用多 GPU 进化计算推断动态空间 GRN 模型。
Brief Bioinform. 2021 Sep 2;22(5). doi: 10.1093/bib/bbab104.
4
Parallel Implementation of MAFFT on CUDA-Enabled Graphics Hardware.MAFFT在支持CUDA的图形硬件上的并行实现。
IEEE/ACM Trans Comput Biol Bioinform. 2015 Jan-Feb;12(1):205-18. doi: 10.1109/TCBB.2014.2351801.
5
CUDA-BLASTP: accelerating BLASTP on CUDA-enabled graphics hardware.CUDA-BLASTP：在支持 CUDA 的图形硬件上加速 BLASTP。
IEEE/ACM Trans Comput Biol Bioinform. 2011 Nov-Dec;8(6):1678-84. doi: 10.1109/TCBB.2011.33.
6
Multi-GPU implementation of a VMAT treatment plan optimization algorithm.容积调强放疗（VMAT）治疗计划优化算法的多图形处理器（Multi-GPU）实现
Med Phys. 2015 Jun;42(6):2841-52. doi: 10.1118/1.4919742.
7
Efficient parallel implementation of active appearance model fitting algorithm on GPU.
ScientificWorldJournal. 2014 Mar 2;2014:528080. doi: 10.1155/2014/528080. eCollection 2014.
8
A fast forward projection using multithreads for multirays on GPUs in medical image reconstruction.基于 GPU 的医学图像重建中多线程快速前向投影的多射线算法。
Med Phys. 2011 Jul;38(7):4052-65. doi: 10.1118/1.3591994.
9
GAMUT: GPU accelerated microRNA analysis to uncover target genes through CUDA-miRanda.GAMUT：通过CUDA-miRanda实现GPU加速的微小RNA分析以揭示靶基因
BMC Med Genomics. 2014;7 Suppl 1(Suppl 1):S9. doi: 10.1186/1755-8794-7-S1-S9. Epub 2014 May 8.
10
Parallel beamlet dose calculation via beamlet contexts in a distributed multi-GPU framework.基于分布式多 GPU 框架中的束流子区域进行平行束流子剂量计算。
Med Phys. 2019 Aug;46(8):3719-3733. doi: 10.1002/mp.13651. Epub 2019 Jun 30.

引用本文的文献

1
Spherical model for Minimalist Machine Learning paradigm in handling complex databases.用于处理复杂数据库的极简主义机器学习范式的球形模型。
Front Artif Intell. 2025 Feb 14;8:1521063. doi: 10.3389/frai.2025.1521063. eCollection 2025.

本文引用的文献

1
An Algorithm for Motif Discovery with Iteration on Lengths of Motifs.一种基于基序长度迭代的基序发现算法。
IEEE/ACM Trans Comput Biol Bioinform. 2015 Jan-Feb;12(1):136-41. doi: 10.1109/TCBB.2014.2351793.
2
Evolving robust gene regulatory networks.进化稳健的基因调控网络。
PLoS One. 2015 Jan 23;10(1):e0116258. doi: 10.1371/journal.pone.0116258. eCollection 2015.
3
DNA strand generation for DNA computing by using a multi-objective differential evolution algorithm.使用多目标差分进化算法进行DNA计算的DNA链生成
Biosystems. 2014 Feb;116:49-64. doi: 10.1016/j.biosystems.2013.12.005. Epub 2013 Dec 19.
4
Optimizing ion channel models using a parallel genetic algorithm on graphical processors.利用图形处理器上的并行遗传算法优化离子通道模型。
J Neurosci Methods. 2012;206(2):183-94. doi: 10.1016/j.jneumeth.2012.02.024. Epub 2012 Mar 8.
5
Evolving gene regulatory networks.
Biosystems. 2009 Dec;98(3):vi-vii. doi: 10.1016/S0303-2647(09)00181-6.
6
A multi-objective differential evolutionary approach toward more stable gene regulatory networks.一种用于构建更稳定基因调控网络的多目标差分进化方法。
Biosystems. 2009 Dec;98(3):127-36. doi: 10.1016/j.biosystems.2009.09.002. Epub 2009 Oct 21.
7
On the evolution of scale-free topologies with a gene regulatory network model.基于基因调控网络模型的无标度拓扑结构的演化
Biosystems. 2009 Dec;98(3):137-48. doi: 10.1016/j.biosystems.2009.06.006. Epub 2009 Jul 3.
8
Computational methods for discovering gene networks from expression data.从表达数据中发现基因网络的计算方法。
Brief Bioinform. 2009 Jul;10(4):408-23. doi: 10.1093/bib/bbp028.
9
A cellular mechanism for multi-robot construction via evolutionary multi-objective optimization of a gene regulatory network.一种通过基因调控网络的进化多目标优化实现多机器人构建的细胞机制。
Biosystems. 2009 Dec;98(3):193-203. doi: 10.1016/j.biosystems.2009.05.003. Epub 2009 May 13.
10
Survival of the sparsest: robust gene networks are parsimonious.最精简者的生存：稳健的基因网络是简约的。
Mol Syst Biol. 2008;4:213. doi: 10.1038/msb.2008.52. Epub 2008 Aug 5.