基于t检验和逐步网络搜索的有向基因调控网络推断算法

doi:10.11772/j.issn.1001-9081.2023010086

《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (1): 199-205.DOI: 10.11772/j.issn.1001-9081.2023010086

• 数据科学与技术 • 上一篇

基于t检验和逐步网络搜索的有向基因调控网络推断算法

陈都¹, 李圆媛², 陈彧¹()

^1.武汉理工大学理学院，武汉 430070
^2.武汉工程大学数理学院，武汉 430205

收稿日期:2023-02-06 修回日期:2023-04-23 接受日期:2023-04-23 发布日期:2023-06-06 出版日期:2024-01-10
通讯作者: 陈彧
作者简介:陈都（1998—），男，浙江温岭人，硕士研究生，主要研究方向：复杂网络识别、数据分析；
李圆媛（1980—），女，湖北宜昌人，教授，博士，主要研究方向：复杂网络、系统生物学；
第一联系人：陈彧（1980—），男，四川广安人，副教授，博士，CCF会员，主要研究方向：进化计算、系统生物学。
基金资助:
国家自然科学基金资助项目(12001408)

Directed gene regulatory network inference algorithm based on t-test and stepwise network search

Du CHEN¹, Yuanyuan LI², Yu CHEN¹()

^1.School of Science，Wuhan University of Technology，Wuhan Hubei 430070，China
^2.School of Mathematics and Physics，Wuhan Institute of Technology，Wuhan Hubei 430205，China

Received:2023-02-06 Revised:2023-04-23 Accepted:2023-04-23 Online:2023-06-06 Published:2024-01-10
Contact: Yu CHEN
About author:CHEN Du， born in 1998， M. S. candidate. His research interests include complex network identification， data analysis.
LI Yuanyuan， born in 1980， Ph. D.， professor. Her research interests include complex network， systems biology.
Supported by:
National Natural Science Foundation of China(12001408)

摘要/Abstract

摘要：

为了克服基于条件互信息的路径一致算法（PCA-CMI）无法识别调控方向的缺陷，并进一步提高网络推断准确率，提出了一种基于t检验和逐步网络搜索的有向网络推断算法（DNI-T-SRS）。首先，对不同实验条件下的表达数据进行t检验以辨别基因调控的上下游关系，指导路径一致（Path Consensus）算法中条件基因的选取，根据CMI2（Conditional Mutual Inclusive Information）剔除网络中的冗余边，得到了基于t检验的有向调控关系推断算法CMI2NI-T（CMI2-based Network Inference guided by t-Test）；然后，建立有向调控关系对应的米氏微分方程模型对数据进行拟合，根据贝叶斯信息准则进行逐步网络搜索以修正网络推断结果。利用CMI2NI-T推断DREAM6挑战中的两个测试网络，所得到的曲线下面积（AUC）分别为0.767 9和0.979 6，相较于PCA-CMI分别提高了16.23%和11.62%；通过进一步的数据拟合后DNI-T-SRS的推断准确率分别达到了86.67%和100.00%，相较于PCA-CMI分别提高了18.19%和10.52%。实验结果表明，所提DNI-T-SRS算法能够有效剔除间接调控关系并保留直接调控连接，得到精确的基因调控网络推断结果。

关键词: 基因调控网络, 条件互信息, t检验, 逐步网络搜索, 米氏微分方程模型, 贝叶斯信息准则

Abstract:

In order to overcome the shortage that the Path Consensus Algorithm based on Conditional Mutual Information （PCA-CMI） cannot identify the regulation direction and further improve the accuracy of network inference， a Directed Network Inference algorithm enhanced by t-Test and Stepwise Regulation Search （DNI-T-SRS） was proposed. First， the upstream and downstream relationships of genes were identified by a t-test performed on the expression data with different perturbation settings， by which the conditional genes were selected for guiding Path Consensus （PC） algorithm and calculating Conditional Mutual Inclusive Information （CMI2） to remove redundant regulations， and an algorithm named CMI2-based network inference guided by t-Test （CMI2NI-T） was developed. Then， the corresponding Michaelis-Menten differential equation model was established to fit the expression data， and the network inference result was further corrected by a stepwise network search based on Bayesian information criterion. Numerical experiments were conducted on two benchmark networks of the DREAM6 challenge， and the Area Under Curves （AUCs） of CMI2NI-T were 0.767 9 and 0.979 6， which were 16.23% and 11.62% higher than those of PCA-CMI. With the help of additional process of data fitting， the DNI-T-SRS achieved the inference accuracies of 86.67% and 100.00%， which were 18.19% and 10.52% higher than those of PCA-CMI. The experimental results demonstrate that the proposed DNI-T-SRS can eliminate indirect regulatory relationships and preserve direct regulatory connections， which contributes to precise inference results of gene regulatory networks.

Key words: Gene Regulatory Network (GRN), conditional mutual information, t-test, stepwise network search, Michaelis-Menten differential equation model, Bayesian Information Criterion (BIC)

中图分类号:

TP18

陈都, 李圆媛, 陈彧. 基于t检验和逐步网络搜索的有向基因调控网络推断算法[J]. 计算机应用, 2024, 44(1): 199-205.

Du CHEN, Yuanyuan LI, Yu CHEN. Directed gene regulatory network inference algorithm based on t-test and stepwise network search[J]. Journal of Computer Applications, 2024, 44(1): 199-205.

图/表 8

图1 基因X通过Z1和Z2调控基因Y

Fig. 1 Gene X regulating gene Y via genes Z1 and Z2

图2 DREAM6-Model1网络推断结果

Fig. 2 Network inference results for DREAM6-Model1

图3 3种算法在Model1网络中的ROC曲线

Fig. 3 Receiver operating characteristic curves of three algorithms for Model1

表1 Model1网络推断结果评估

Tab. 1 Network inference result evaluation for Model1

网络	TP	FP	TPR/%	FPR/%	PPV/%	ACC/%
t检验网络	14	12	100.00	75.00	53.85	60.00
PCA-CMI推断网络	10	4	71.43	25.00	71.43	73.33
CMI2NI推断网络	8	4	57.14	25.00	66.67	66.67
CMI2NI-T推断网络	10	2	71.43	12.50	83.33	80.00
DNI-T-SRS推断网络	12	2	85.71	12.50	85.71	86.67

图4 蛋白质4在不同环境下的真实表达曲线

Fig. 4 Expression curves of protein 4 under different perturbations

图5 DREAM6-Model2网络推断结果

Fig. 5 Network inference results for DREAM6-Model2

图6 3种算法在Model2网络中的ROC曲线

Fig. 6 Receiver operating characteristic curves of three algorithms for Model2

表2 Model2网络推断结果评估

Tab. 2 Network inference result evaluation for Model2

网络	TP	FP	TPR/%	FPR/%	PPV/%	ACC/%
t检验网络	14	18	100.00	64.29	43.75	57.14
PCA-CMI推断网络	12	2	85.71	7.14	85.71	90.48
CMI2NI推断网络	12	2	85.71	7.14	85.71	90.48
CMI2NI-T推断网络	12	0	85.71	0.00	100.00	95.24
DNI-T-SRS推断网络	14	0	100.00	0.00	100.00	100.00

参考文献 32

1	SAINT-ANTOINE M M， SINGH A. Network inference in systems biology： Recent developments， challenges， and applications ［J］. Current Opinion in Biotechnology， 2020， 63： 89-98. 10.1016/j.copbio.2019.12.002
2	DELGADO F M， GÓMEZ-VELA F. Computational methods for gene regulatory networks reconstruction and analysis： a review ［J］. Artificial Intelligence in Medicine， 2019， 95： 133-145. 10.1016/j.artmed.2018.10.006
3	ZHAO M， HE W， TANG J， et al. A comprehensive overview and critical evaluation of gene regulatory network inference technologies ［J］. Briefings in Bioinformatics， 2021， 22（5）： bbab009. 10.1093/bib/bbab009
4	MU Y， LIU X， WANG L. A Pearson’s correlation coefficient based decision tree and its parallel implementation ［J］. Information Sciences， 2018， 435： 40-58. 10.1016/j.ins.2017.12.059
5	SHI J， ZHAO J， LI T， et al. Detecting direct associations in a network by information theoretic approaches ［J］. SCIENCE CHINA Mathematics， 2019， 62： 823-838. 10.1007/s11425-017-9206-0
6	MARGOLIN A A， NEMENMAN I， BASSO K， et al. ARACNE： An algorithm for the reconstruction of gene regulatory networks in a mammalian cellular context ［J］. BMC Bioinformatics， 2006， 7： No. S7. 10.1186/1471-2105-7-s1-s7
7	LANGFELDER P， HORVATH S. WGCNA： An R package for weighted correlation network analysis ［J］. BMC Bioinformatics， 2008， 9： No. 559. 10.1186/1471-2105-9-559
8	SAITO S， HIROKAWA T， HORIMOTO K. Discovery of chemical compound groups with common structures by a network analysis approach （affinity prediction method）［J］. Journal of Chemical Information and Modeling， 2011， 51： 61-68. 10.1021/ci100262s
9	ZHANG X， ZHAO X-M， HE K， et al. Inferring gene regulatory networks from gene expression data by path consistency algorithm based on conditional mutual information ［J］. Bioinformatics， 2012， 28（1）： 98-104. 10.1093/bioinformatics/btr626
10	ZHANG X， ZHAO J， HAO J-K， et al. Conditional mutual inclusive information enables accurate quantification of associations in gene regulatory networks ［J］. Nucleic Acids Research， 2015， 43（5）： e31. 10.1093/nar/gku1315
11	ZHAO J， ZHOU Y， ZHANG X， et al. Part mutual information for quantifying direct associations in networks ［J］. Proceedings of the National Academy of Sciences， 2016， 113（18）： 5130-5135. 10.1073/pnas.1522586113
12	雷继萌.基于混合熵优化互信息的基因网络构建方法研究［D］.武汉：华中农业大学， 2022： 18-25. 10.1093/bioinformatics/btac717
	LEI J M. Research of gene network construction method based on mixed entropy optimizing mutual information ［D］. Wuhan： Huazhong Agricultural University， 2022： 18-25. 10.1093/bioinformatics/btac717
13	AGHDAM R， GANJALI M， ZHANG X， et al. CN： A consensus algorithm for inferring gene regulatory networks using the SORDER algorithm and conditional mutual information test ［J］. Molecular BioSystems， 2015， 11（3）： 942-949. 10.1039/c4mb00413b
14	YAN Y， ZHANG X， TIAN T. Inference method for reconstructing regulatory networks using statistical path-consistency algorithm and mutual information ［C］// Proceedings of the 2020 International Conference on Intelligent Computing Theories and Application. Cham： Springer， 2020： 45-56. 10.1007/978-3-030-60802-6_5
15	肖非.基于候选基因选择的调控网络构建方法［D］.西安：西安电子科技大学， 2015： 19-23.
	XIAO F. Reconstruction of regulatory networks based on selection of candidate gene ［D］. Xi’an： Xidian University， 2015： 19-23.
16	AGHDAM R， GANJALI M， ESLAHCHI C. IPCA-CMI： an algorithm for inferring gene regulatory networks based on a combination of PCA-CMI and MIT score ［J］. PLoS ONE， 2014， 9（4）： e92600. 10.1371/journal.pone.0092600
17	MAHMOODI S H， AGHDAM R， ESLAHCHI C. An order independent algorithm for inferring gene regulatory network using quantile value for conditional independence tests ［J］. Scientific Reports， 2021， 11： No.7605. 10.1038/s41598-021-87074-5
18	XU J， YANG G， LIU G， et al. Inferring gene regulatory networks via ensemble path consistency algorithm based on conditional mutual information ［J］. IEEE/ACM Transactions on Computational Biology and Bioinformatics， 2023， 20（3）： 1807-1816. 10.1109/tcbb.2022.3220581
19	ZHAO R， WANG B， HAN L， et al. New results on model reconstruction of Boolean networks with application to gene regulatory networks ［J］. Mathematical Methods in the Applied Sciences， 2023， 46（4）： 3741-3757. 10.1002/mma.8719
20	QU L， WANG Z， LI C， et al. Dynamic Bayesian network modeling based on structure prediction for gene regulatory network ［J］. IEEE Access， 2021， 9： 123616-123634. 10.1109/access.2021.3109133
21	DU Z， ZHONG X， WANG F， et al. Inference of gene regulatory networks based on the Light Gradient Boosting Machine ［J］. Computational Biology and Chemistry， 2022， 101： 107769. 10.1016/j.compbiolchem.2022.107769
22	PUŠNIK Ž， MRAZ M， ZIMIC N， et al. Review and assessment of Boolean approaches for inference of gene regulatory networks ［J］. Heliyon， 2022， 8（8）： e10222. 10.1016/j.heliyon.2022.e10222
23	YANG B， CHEN Y. Overview of gene regulatory network inference based on differential equation models ［J］. Current Protein & Peptide Science， 2020， 21（11）： 1054-1059. 10.2174/1389203721666200213103350
24	HUYNH-THU V A， IRRTHUM A， WEHENKEL L， et al. Inferring regulatory networks from expression data using tree-based methods ［J］. PLoS ONE， 2010， 5（9）： e12776. 10.1371/journal.pone.0012776
25	ZHENG R， LI M， CHEN X， et al. BiXGBoost： A scalable， flexible boosting-based method for reconstructing gene regulatory networks ［J］. Bioinformatics， 2019， 35（11）： 1893-1900. 10.1093/bioinformatics/bty908
26	VAN DEN BROECK L， GORDON M， INZÉ D， et al. Gene regulatory network inference： connecting plant biology and mathematical modeling ［J］. Frontiers in Genetics， 2020， 11： 457. 10.3389/fgene.2020.00457
27	SANTILLÁN M. On the use of the Hill functions in mathematical models of gene regulatory networks ［J］. Mathematical Modelling of Natural Phenomena， 2008， 3（2）： 85-97. 10.1051/mmnp:2008056
28	SCHWARZ G. Estimating the dimension of a model ［J］. The Annals of Statistics， 1978， 6（2）： 461-464. 10.1214/aos/1176344136
29	MEYER P， COKELAER T， CHANDRAN D， et al. Network topology and parameter estimation： from experimental design methods to gene regulatory network kinetics using a community based approach ［J］. BMC Systems Biology， 2014， 8： No. 13. 10.1186/1752-0509-8-13
30	KASS R E， RAFTERY A E. Bayes factors ［J］. Journal of the American Statistical Association， 1995， 90： 773-795. 10.1080/01621459.1995.10476572
31	HINDMARSH A C， BROWN P N， GRANT K E， et al. SUNDIALS： Suite of nonlinear and differential/algebraic equation solvers ［J］. ACM Transactions on Mathematical Software， 2005， 31（3）： 363-396. 10.1145/1089014.1089020
32	MCKAY M D， BECKMAN R， CONOVER W J. A comparison of three methods for selecting values of input variables in the analysis of output from a computer code ［J］. Technometrics， 2000， 42（1）： 55-61. 10.1080/00401706.2000.10485979

[1]	陈永波, 李巧勤, 刘勇国. 基于动态相关性的特征选择算法[J]. 《计算机应用》唯一官方网站, 2022, 42(1): 109-114.
[2]	程玉胜, 宋帆, 王一宾, 钱坤. 基于专家特征的条件互信息多标记特征选择算法[J]. 《计算机应用》唯一官方网站, 2020, 40(2): 503-509.
[3]	毛莺池, 曹海, 平萍, 李晓芳. 基于最大联合条件互信息的特征选择[J]. 计算机应用, 2019, 39(3): 734-741.
[4]	孟军, 史贯丽. 融合粒子群优化和遗传算法的基因调控网络构建[J]. 计算机应用, 2016, 36(11): 2969-2973.
[5]	张继宏李小霞孙波. 基于非线性支持向量机的原核生物基因识别[J]. 计算机应用, 2009, 29(10): 2748-2750.
[6]	杜智华王宜伟. 一种新颖的基因调控网络结构学习方法[J]. 计算机应用, 2009, 29(06): 1539-1543.
[7]	白志杰李弼程彭天强. 基于BIC的新闻视频近似重复帧检测方法[J]. 计算机应用, 2009, 29(06): 1694-1701.
[8]	王卫玲刘培玉初建崇. 一种改进的基于条件互信息的特征选择算法[J]. 计算机应用, 2007, 27(2): 433-435.
[9]	陈国平;杜利民;付跃文;王劲林. 基于MBIC的决策树聚类算法在连续语音识别中的应用[J]. 计算机应用, 2005, 25(12): 2792-2794.
[10]	聂文广，刘惟一，杨运涛，杨明. 基于信息论的Bayesian网络结构学习算法研究[J]. 计算机应用, 2005, 25(01): 1-3.

基于t检验和逐步网络搜索的有向基因调控网络推断算法

Directed gene regulatory network inference algorithm based on t-test and stepwise network search

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 32

相关文章 10

编辑推荐

Metrics