Enabling network inference methods to handle missing data and outliers

BMC Bioinformatics

Abel Folch-Fortuny³  Alejandro F. Villaverde²  Alberto Ferrer³  Julio R. Banga¹ 

[1] BioProcess Engineering Group, IIM-CSIC, Eduardo Cabello 6, Vigo 36208, Spain

[2] Department of Systems and Control Engineering, Universidade de Vigo, Rua Maxwell, Vigo 36310, Spain

[3] Departamento de Estadística e Investigación Operativa Aplicadas y Calidad, Universitat Politècnica de València, Camino de Vera s/n, Valencia 46022, Spain

关键词: Mutual information;    Information theory;    Trimmed scores regression;    Projection to latent structures;    Outlier detection;    Missing data;    Network inference;   

Others  :  1229469
DOI  :  10.1186/s12859-015-0717-7

 received in 2015-02-03, accepted in 2015-08-24,  发布年份 2015

【 摘 要 】

Background

The inference of complex networks from data is a challenging problem in biological sciences, as well as in a wide range of disciplines such as chemistry, technology, economics, or sociology. The quantity and quality of the data greatly affect the results. While many methodologies have been developed for this task, they seldom take into account issues such as missing data or outlier detection and correction, which need to be properly addressed before network inference.

Results

Here we present an approach to (i) handle missing data and (ii) detect and correct outliers based on multivariate projection to latent structures. The method, called trimmed scores regression (TSR), enables network inference methods to analyse incomplete datasets by imputing the missing values coherently with the latent data structure. Furthermore, it substitutes the faulty values in a dataset by proper estimations. We provide an implementation of this approach, and show how it can be integrated with any network inference method as a preliminary data curation step. This functionality is demonstrated with a state of the art network inference method based on mutual information distance and entropy reduction, MIDER.

Conclusion

The methodology presented here enables network inference methods to analyse a large number of incomplete and faulty datasets that could not be reliably analysed so far. Our comparative studies show the superiority of TSR over other missing data approaches used by practitioners. Furthermore, the method allows for outlier detection and correction.

【 授权许可】

   
2015 Folch-Fortuny et al.

【 图 表 】

Fig. 1.

Fig. 2.

Fig. 3.

【 参考文献 】

• [1]Albert R, Barabási AL. Statistical mechanics of complex networks. Rev Mod Phys. 2002; 74(1):47-97.
• [2]Newman MEJ. The structure and function of complex networks. SIAM Rev. 2003; 45(2):167-256.
• [3]De Smet R, Marchal K. Advantages and limitations of current network inference methods. Nat Rev Microbiol. 2010; 8(10):717-29.
• [4]Marbach D, Prill RJ, Schaffter T, Mattiussi C, Floreano D, Stolovitzky G. Revealing strengths and weaknesses of methods for gene network inference. Proc Natl Acad Sci. 2010; 107(14):6286-291.
• [5]Prill RJ, Saez-Rodriguez J, Alexopoulos LG, Sorger PK, Stolovitzky G. Crowdsourcing network inference: the DREAM predictive signaling network challenge. Sci Signal. 2011; 4(189):7.
• [6]Lecca P, Priami C. Biological network inference for drug discovery. Drug Discovery Today. 2013; 18(5-6):256-64.
• [7]Maetschke SR, Madhamshettiwar PB, Davis MJ, Ragan MA. Supervised, semi-supervised and unsupervised inference of gene regulatory networks. Brief Bioinform. 2013; 15(2):195-211.
• [8]Grung B, Manne R. Missing values in principal component analysis. Chemometr Intell Lab Syst. 1998; 42(1-2):125-39.
• [9]Arteaga F, Ferrer A. Missing data. Comprehensive chemometrics chemical and biochemical data analysis. Elsevier, Amsterdam; 2009.
• [10]Jackson JE. A user’s guide to principal components. Wiley Ser Probab Stat, Hoboken; 2004.
• [11]Walczak B, Massart DL. Dealing with missing data. Chemometr Intell Lab Syst. 2001; 58(1):15-27.
• [12]Martens H, Jr Russwurm H. Food research and data analysis. Elsevier Applied Science, London; New York, NY, USA; 1983.
• [13]Arteaga F, Ferrer A. Dealing with missing data in MSPC: Several methods, different interpretations, some examples. J Chemom. 2002; 16(8-10):408-18.
• [14]Folch-Fortuny A, Arteaga F, Ferrer A. PCA model building with missing data: new proposals and a comparative study. Chemometr Intell Lab Syst. 2015; 146:77-88.
• [15]Liao SG, Lin Y, Kang DD, Chandra D, Bon J, Kaminski N et al.. Missing value imputation in high-dimensional phenomic data: imputable or not, and how? BMC Bioinforma. 2014; 15(1):346. BioMed Central Full Text
• [16]Wold S, Esbensen K, Geladi P. Principal component analysis. Chemometr Intell Lab Syst. 1987; 2(1-3):37-52.
• [17]Kourti T, MacGregor JF. Process analysis, monitoring and diagnosis, using multivariate projection methods. Chemometr Intell Lab Syst. 1995; 28(1):3-21.
• [18]Ferrer A. Latent structures-based multivariate statistical process control: A paradigm shift. Qual Eng. 2014; 26(1):72-91.
• [19]Villaverde AF, Ross J, Morán F, Banga JR. MIDER: Network inference with mutual information distance and entropy reduction. PLoS ONE. 2014; 9(5):96732.
• [20]Shannon CE. A mathematical theory of communication. Bell Sys Tech J. 1948; 27(3):379-423.
• [21]Cover TM, Thomas JA. Elements of information theory. Wiley-Interscience, New York; 1991.
• [22]Villaverde AF, Ross J, Banga JR. Reverse engineering cellular networks with information theoretic methods. Cells. 2013; 2(2):306-29.
• [23]Faith JJ, Hayete B, Thaden JT, Mogno I, Wierzbowski J, Cottarel G et al.. Large-scale mapping and validation of escherichia coli transcriptional regulation from a compendium of expression profiles. PLoS Biol. 2007; 5(1):8.
• [24]Margolin AA, Nemenman I, Basso K, Wiggins C, Stolovitzky G, Favera RD et al.. ARACNE: An algorithm for the reconstruction of gene regulatory networks in a mammalian cellular context. BMC Bioinforma. 2006; 7 Suppl 1:7. BioMed Central Full Text
• [25]Meyer PE, Kontos K, Lafitte F, Bontempi G. Information-theoretic inference of large transcriptional regulatory networks. EURASIP J Bioinforma Syst Biol. 2007; 2007(1):79879.
• [26]Luo W, Hankenson KD, Woolf PJ. Learning transcriptional regulatory networks from high throughput gene expression data using continuous three-way mutual information. BMC Bioinforma. 2008; 9:467. BioMed Central Full Text
• [27]Zoppoli P, Morganella S, Ceccarelli M. TimeDelay-ARACNE: Reverse engineering of gene networks from time-course data by an information theoretic approach. BMC bioinforma. 2010; 11:154. BioMed Central Full Text
• [28]Wu CC, Huang HC, Juan HF, Chen ST. GeneNetwork: an interactive tool for reconstruction of genetic networks using microarray data. Bioinformatics (Oxford, England). 2004; 20(18):3691-693.
• [29]Gustafsson M, Hörnquist M, Lombardi A. Constructing and analyzing a large-scale gene-to-gene regulatory network–lasso-constrained inference and biological validation. IEEE/ACM trans comput biol bioinform/IEEE, ACM. 2005; 2(3):254-61.
• [30]Guthke R, Möller U, Hoffmann M, Thies F, Töpfer S. Dynamic network reconstruction from gene expression data applied to immune response during bacterial infection. Bioinformatics (Oxford, England). 2005; 21(8):1626-34.
• [31]Schulze S, Henkel SG, Driesch D, Guthke R, Linde J. Computational prediction of molecular pathogen-host interactions based on dual transcriptome data. Front Microbiol. 2015; 6:65.
• [32]Hurley D, Araki H, Tamada Y, Dunmore B, Sanders D, Humphreys S et al.. Gene network inference and visualization tools for biologists: application to new human transcriptome datasets. Nucleic Acids Res. 2012; 40(6):2377-398.
• [33]Souto MCd, Jaskowiak PA, Costa IG. Impact of missing data imputation methods on gene expression clustering and classification. BMC Bioinforma. 2015; 16(1):64. BioMed Central Full Text
• [34]Guitart-Pla O, Kustagi M, Rügheimer F, Califano A, Schwikowski B. The Cyni framework for network inference in Cytoscape. Bioinformatics (Oxford, England). 2015; 31(9):1499-1501.
• [35]Camacho J, Picó J, Ferrer A. Data understanding with PCA: Structural and variance information plots. Chemometr Intell Lab Syst. 2010; 100(1):48-56.
• [36]Wold S. Cross-validatory estimation of the number of components in factor and principal components models. Technometrics. 1978; 20(4):397-405.
• [37]Camacho J, Ferrer A. Cross-validation in PCA models with the element-wise k-fold (ekf) algorithm: theoretical aspects. J Chemom. 2012; 26(7):361-73.
• [38]Little RJA, Rubin DB. Statistical analysis with missing data. Wiley-Interscience, Hoboken, NJ; 2002.
• [39]Ferrer A. Multivariate statistical process control based on principal component analysis (MSPC-PCA): Some reflections and a case study in an autobody assembly process. Qual Eng. 2007; 19(4):311-25.
• [40]MacGregor JF, Kourti T. Statistical process control of multivariate processes. Control Eng Pract. 1995; 3(3):403-14.
• [41]Stanimirova I, Daszykowski M, Walczak B. Dealing with missing values and outliers in principal component analysis. Talanta. 2007; 72(1):172-8.
• [42]Abdi H, Williams LJ. Principal component analysis. Wiley Interdiscip Rev Comput Stat. 2010; 2(4):433-59.
• [43]Camacho J, Picó J, Ferrer A. The best approaches in the on-line monitoring of batch processes based on PCA: Does the modelling structure matter? Anal Chim Acta. 2009; 642(1-2):59-68.
• [44]González-Martínez JM, de Noord OE, Ferrer A. Multisynchro: a novel approach for batch synchronization in scenarios of multiple asynchronisms. J Chemom. 2014; 28(5):462-75.
• [45]Samoilov MS. Reconstruction and Functional Analysis of General Chemical Reactions and Reaction Networks. Stanford University, California, United States; 1997.
• [46]Samoilov M, Arkin A, Ross J. On the deduction of chemical reaction pathways from measurements of time series of concentrations. Chaos (Woodbury, NY). 2001; 11(1):108-14.
• [47]Cantone I, Marucci L, Iorio F, Ricci MA, Belcastro V, Bansal M et al.. A yeast synthetic network for in vivo assessment of reverse-engineering and modeling approaches. Cell. 2009; 137(1):172-81.
• [48]Arkin A, Shen P, Ross J. A test case of correlation metric construction of a reaction pathway from measurements. Science. 1997; 277(5330):1275-9.
• [49]Schaffter T, Marbach D, Floreano D. GeneNetWeaver: in silico benchmark generation and performance profiling of network inference methods. Bioinformatics (Oxford, England). 2011; 27(16):2263-270.
• [50]Marbach D, Schaffter T, Mattiussi C, Floreano D. Generating realistic in silico gene networks for performance assessment of reverse engineering methods. J Comput Biol J Comput Mol Cell Biol. 2009; 16(2):229-39.