基于混合并行遗传算法和阈值限定法的基因调控网络构建

doi:10.13229/j.cnki.jdxbgxb201702038

吉林大学学报(工学版) ›› 2017, Vol. 47 ›› Issue (2): 624-631.doi: 10.13229/j.cnki.jdxbgxb201702038

基于混合并行遗传算法和阈值限定法的基因调控网络构建

郑明^{1, 2, 3}, 卓慕瑰², 张树功¹, 周柚³, 刘桂霞³

1.吉林大学数学学院,长春 130012;
2.梧州学院信息与电子工程学院,广西梧州 543002;
3.吉林大学计算机科学与技术学院,长春 130012

收稿日期:2015-11-14 出版日期:2017-03-20 发布日期:2017-03-20
通讯作者: 刘桂霞(1963-),女,教授,博士生导师.研究方向:生物信息学.E-mail:liugx@jlu.edu.cn
作者简介:郑明(1983-),男,在站博士后.研究方向:计算数学,生物信息学.E-mail:370505375@qq.com
基金资助:
国家自然科学基金项目(61502343,61373051,61175023); 中国博士后科学基金项目(2016M590260); 广西自然科学基金项目(2015GXNSFBA139262); 梧州学院广西高校行业软件技术重点实验室项目; 广西高校科研项目(KY2015ZD122); 梧州学院院级项目(2014A002); 吉林省科技发展项目(20140204004GX); 吉林大学“985工程”项目.

Reconstruction for gene regulatory network based on hybrid parallel genetic algorithm and threshold value method

ZHENG Ming^{1, 2, 3}, ZHUO Mu-gui², ZHANG Shu-gong¹, ZHOU You³, LIU Gui-xia³

1.College of Mathematics, Jilin University, Changchun 130012, China;
2.College of Information and Electronic Engineering, Wuzhou University, Wuzhou 543002, China;
3.College of Computer Science and Technology,Jilin University, Changchun 130012, China

Received:2015-11-14 Online:2017-03-20 Published:2017-03-20

摘要/Abstract

摘要： 为了解决传统基因调控网络构建算法准确度不高的问题,提出了一种基于混合并行遗传算法和阈值限定法的新型基因调控网络构建算法。该算法分缩小解空间和参数拟合两部分,缩小解空间阶段先用奇异值分解法限定数学上可行的基因调控网络,减少不必要计算,然后用阈值限定法将每个基因的控制基因限定到一定规模,提高计算效率的同时更合乎生物信息学规则。参数拟合部分先用并行遗传算法在整个解空间快速寻优,而后采用爬山法进行小范围细致求解,提高计算精度。实验部分将本文算法应用于人类复杂疾病的皮肤黑色素瘤和2型糖尿病基因调控网络的构建上。本文计算结果与真实网络作对比,验证了本文算法的有效性。同时将本文计算结果与传统遗传算法,粒子群算法进行比较,证明本文算法具有更高的执行效率。

关键词: 人工智能, 混合并行遗传算法, 阈值限定法, 奇异值分解, 微分方程模型, 基因调控网络

Abstract: In order to improve the efficiency of the Gene Regulatory Networks (GRNs) reconstruction, a novel algorithm based on hybrid parallel genetic algorithm and threshold value method was proposed. Two parts were included in this algorithm, the solution decomposition and parameter calculation. In solution decomposition, Singular Value Decomposition (SVD) method was used to obtain the solutions, which are capable in math framework. The threshold value method was used to reduce the unnecessary edges in the network, which can improve the efficiency and is suitable for the rules in bioinformatics. In parameter calculation, parallel genetic algorithm was used for optimizing the parameters in the whole solution space and hill climbing method was used to calculate the solutions in small region. In experiments, the proposed algorithm was validated on both melanoma data and diabetes data. The results of this work were compared with the results of real network in bioinformatics and the results of genetic algorithm and swarm particle algorithm, which demonstrate the higher efficiency of the proposed method.

Key words: artificial intelligence, hybrid parallel genetic algorithm, threshold value method, singular value decomposition, differential equation model, gene regulatory network

中图分类号:

TP18

郑明, 卓慕瑰, 张树功, 周柚, 刘桂霞. 基于混合并行遗传算法和阈值限定法的基因调控网络构建[J]. 吉林大学学报(工学版), 2017, 47(2): 624-631.

ZHENG Ming, ZHUO Mu-gui, ZHANG Shu-gong, ZHOU You, LIU Gui-xia. Reconstruction for gene regulatory network based on hybrid parallel genetic algorithm and threshold value method[J]. 吉林大学学报(工学版), 2017, 47(2): 624-631.

参考文献

[1] Li L M, Wei L, Jiang H Y, et al. Rapid development of polymorphic microsatellite markers for the Amur sturgeon (Acipenser schrenckii) using next-generation sequencing technology[J]. Genetics and Molecular Research, 2015,14(3): 7910-7913.
[2] C ˇ apková M,Šáchová J,Strnad H, et al. Microarray analysis of serum mRNA in patients with head and neck squamous cell carcinoma at whole-genome scale[J]. Biomed Research International, 2014(23): 408683.
[3] Gao L S, Gao Y, Xu E P, et al. Microarray analysis of the major depressive disorder mRNA profile data[J]. Psychiatry Investigation, 2015,12(3): 388-396.
[4] Driscoll A O, Seator R D. Synthetic DNA: the next generation of big data storage[J]. Bioengineered, 2013, 4(3): 123-125.
[5] Kannadasan R, Saleembahsha M S, Arnoldemerson I. Survey on molecular cryptographic network DNA (MCND) using big data[J]. Big Data, Cloud and Computing Challenges, 2015,50: 3-9.
[6] Ma S N, Jiang T, Jiang R. Differential regulation enrichment analysis via the integration of transcriptional regulatory network and gene expression data[J]. Bioinformatics, 2015,31(4): 563-571.
[7] Taylor-Teeples M, Lin L, De Lucas M, et al.An arabidopsis gene regulatory network for secondary cell wall synthesis[J]. Nature, 2015,517(7536):571.
[8] Bauer-Mehren A, Bundschus M, Rautschka M, et al. Gene-disease network analysis reveals functional modules in mendelian, complex and environmental diseases[J]. Plos One, 2011, 6(6):e20284.
[9] Hertlein E K, Yu L B, Zhang J Y, et al. Micro-RNA and gene expression in CLL: network analysis elucidating the complex role of the NF-kappa B signaling pathway in disease[J]. Blood, 2010,116(21): 1497-1498.
[10] Ruz G A, Timmermann T, Barrera J, et al. Neutral space analysis for a Boolean network model of the fission yeast cell cycle network[J]. Biological Research, 2014, 47(1):64.
[11] Konishi T, Kubo T, Watanabe K, et al.Variational Bayesian inference algorithms for infinite relational model of network data[J]. IEEE Transactions on Neural Networks and Learning Systems, 2015,26(9): 2176-2181.
[12] Li Z J, Xia Y Q, Su C Y, et al. Missile guidance law based on robust model predictive control using neural-network optimization[J]. IEEE Transactions on Neural Networks and Learning Systems,2015,26(8): 1803-1809.
[13] Borcea L, Druskin V, Mamonov A V, et al. A model reduction approach to numerical inversion for a parabolic partial differential equation[J]. Inverse Problems,2014, 30(12):125011.
[14] Wang Y X R, Huang H Y.Review on statistical methods for gene network reconstruction using expression data[J]. Journal of Theoretical Biology, 2014,362: 53-61.
[15] Tong X H, Ye Z, Xu Y S, et al. A novel subpixel phase correlation method using singular value decomposition and unified random sample consensus[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015,53(8): 4143-4156.
[16] Zheng M, Liu G X, Zhou C G, et al.Gravitation field algorithm and its application in gene cluster[J]. Algorithms for Molecular Biology, 2015, 5(1):1-11.
[17] Zheng M, Sun Y, Liu G X, et al. Improved gravitation field algorithm and its application in hierarchical clustering[J]. Plos One, 2012, 7(11):e49039.
[18] Zheng M, Wu J N, Huang Y X, et al. Inferring gene regulatory networks by singular value decomposition and gravitation field algorithm[J]. Plos One, 2012, 7(7):e51141.
[19] Cruz-Chavez M A. Neighbourhood generation mechanism applied in simulated annealing to job shop scheduling problems[J]. International Journal of Systems Science, 2015,46(15): 2673-2685.
[20] Dai C, Wang Y P, Ye M. A new multi-objective particle swarm optimization algorithm based on decomposition[J]. Information Sciences, 2015, 325: 541-557.
[21] Jong W R, Lai P J. The navigation process of mould-manufacturing scheduling optimisation by applying genetic algorithm[J]. International Journal of Computer Integrated Manufacturing, 2015, 28(12): 1331-1349.
[22] Bansal M, Belcastro V, Ambesi-Impiombato A, et al. How to infer gene networks from expression profiles[J]. Molecular Systems Biology, 2007, 3(1):78.
[23] Le D H, Kwon Y K. GPEC: A Cytoscape plug-in for random walk-based gene prioritization and biomedical evidence collection[J]. Computational Biology and Chemistry, 2012, 37: 17-23.
[24] Funauchi Y, Tanikawa C, Yi Lo P H, et al. Regulation of iron homeostasis by the p53-ISCU pathway[J]. Sci Rep, 2015,5: 16497.
[25] Tang S L, Gao Y L, Chen X B. Wnt/beta-catenin up-regulates midkine expression in glioma cells[J]. Int J Clin Exp Med, 2015,8(8): 12644-12649.
[26] Gaulton K J, Ferreira T, Lee Y, et al. Genetic fine mapping and genomic annotation defines causal mechanisms at type 2 diabetes susceptibility loci[J]. Nat Genet,2015, 47(12):1415-1425.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于混合并行遗传算法和阈值限定法的基因调控网络构建

Reconstruction for gene regulatory network based on hybrid parallel genetic algorithm and threshold value method

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	董飒, 刘大有, 欧阳若川, 朱允刚, 李丽娜. 引入二阶马尔可夫假设的逻辑回归异质性网络分类方法[J]. 吉林大学学报(工学版), 2018, 48(5): 1571-1577.
[2]	顾海军, 田雅倩, 崔莹. 基于行为语言的智能交互代理[J]. 吉林大学学报(工学版), 2018, 48(5): 1578-1585.
[3]	王旭, 欧阳继红, 陈桂芬. 基于垂直维序列动态时间规整方法的图相似度度量[J]. 吉林大学学报(工学版), 2018, 48(4): 1199-1205.
[4]	张浩, 占萌苹, 郭刘香, 李誌, 刘元宁, 张春鹤, 常浩武, 王志强. 基于高通量数据的人体外源性植物miRNA跨界调控建模[J]. 吉林大学学报(工学版), 2018, 48(4): 1206-1213.
[5]	黄岚, 纪林影, 姚刚, 翟睿峰, 白天. 面向误诊提示的疾病-症状语义网构建[J]. 吉林大学学报(工学版), 2018, 48(3): 859-865.
[6]	李雄飞, 冯婷婷, 骆实, 张小利. 基于递归神经网络的自动作曲算法[J]. 吉林大学学报(工学版), 2018, 48(3): 866-873.
[7]	刘杰, 张平, 高万夫. 基于条件相关的特征选择方法[J]. 吉林大学学报(工学版), 2018, 48(3): 874-881.
[8]	王旭, 欧阳继红, 陈桂芬. 基于多重序列所有公共子序列的启发式算法度量多图的相似度[J]. 吉林大学学报(工学版), 2018, 48(2): 526-532.
[9]	杨欣, 夏斯军, 刘冬雪, 费树岷, 胡银记. 跟踪-学习-检测框架下改进加速梯度的目标跟踪[J]. 吉林大学学报(工学版), 2018, 48(2): 533-538.
[10]	刘雪娟, 袁家斌, 许娟, 段博佳. 量子k-means算法[J]. 吉林大学学报(工学版), 2018, 48(2): 539-544.
[11]	李娟, 孟可心, 李月, 刘慧力. 基于相似匹配维纳滤波的地震资料噪声压制[J]. 吉林大学学报(工学版), 2017, 47(6): 1964-1968.
[12]	曲慧雁, 赵伟, 秦爱红. 基于优化算子的快速碰撞检测算法[J]. 吉林大学学报(工学版), 2017, 47(5): 1598-1603.
[13]	李嘉菲, 孙小玉. 基于谱分解的不确定数据聚类方法[J]. 吉林大学学报(工学版), 2017, 47(5): 1604-1611.
[14]	邵克勇, 陈丰, 王婷婷, 王季驰, 周立朋. 无平衡点分数阶混沌系统全状态自适应控制[J]. 吉林大学学报(工学版), 2017, 47(4): 1225-1230.
[15]	王生生, 王创峰, 谷方明. OPRA方向关系网络的时空推理[J]. 吉林大学学报(工学版), 2017, 47(4): 1238-1243.