Advances to Bayesian network inference for generating causal networks from observational biological data
Open accessThe DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Motivation: Network inference algorithms are powerful computational tools for identifying putative causal interactions among variables from observational data. Bayesian network inference algorithms hold particular promise in that they can capture linear, non-linear, combinatorial, stochastic and other types of relationships among variables across multiple levels of biological organization. However, challenges remain when applying these algorithms to limited quantities of experimental data collected from biological systems. Here, we use a simulation approach to make advances in our dynamic Bayesian network (DBN) inference algorithm, especially in the context of limited quantities of biological data. Results: We test a range of scoring metrics and search heuristics to find an effective algorithm configuration for evaluating our methodological advances. We also identify sampling intervals and levels of data discretization that allow the best recovery of the simulated networks. We develop a novel influence score for DBNs that attempts to estimate both the sign (activation or repression) and relative magnitude of interactions among variables. When faced with limited quantities of observational data, combining our influence score with moderate data interpolation reduces a significant portion of false positive interactions in the recovered networks. Together, our advances allow DBN inference algorithms to be more effective in recovering biological networks from experimentally collected data. Availability: Source code and simulated data are available upon request. Supplementary information: http://www.jarvislab.net/Bioinformatics/BNAdvances/
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Unlike BNs, DBNs can include cycles and may be constructed when time-course data are available [89–92].”
From Reverse engineering and identification in systems biology: strategies, perspectives and challenges (2014) · cites this paper as [89]
Citations
Cites
Genetic Algorithms in Search, Optimization and Machine Learning
Goldberg, D. E., & Robson, D. (1988) · Cited by 18,391
Goldberg, D. E., & Shakespeare, W. (2002) · Cited by 16,088
Using Bayesian Networks to Analyze Expression Data
Friedman, N., Linial, M., Nachman, I., & Pe'er, D. (2000) · Journal of Computational Biology · doi:10.1089/106652700750050961 · Cited by 3,266 · cited 1×
“They can effectively handle hundreds of variables (Friedman et al., 2000; Smithet al., 2002).”
BackgroundUncertainty in Artificial Intelligence
(1992) · Elsevier eBooks · doi:10.1016/c2013-0-12606-2 · Cited by 1,425
Inferring Genetic Networks and Identifying Compound Mode of Action via Expression Profiling
Gardner, T. S., di Bernardo, D., Lorenz, D., & Collins, J. J. (2003) · Science · doi:10.1126/science.1081900 · Cited by 1,117 · cited 1×
“A variety of network inference algorithms have recently been used to identify gene regulatory networks from observational gene expression data (Akutsu et al., 2000; Arkinet al., 1997; D’haeseleer et al., 1999; Friedmanet al., 2000; Gardner et al., 2003; Harteminket al., 2001; Lianget al., 1998; Weaver et al., 1999; Xu…”
MethodReveal, a general reverse engineering algorithm for inference of genetic network architectures.
Liang, S., Fuhrman, S., & Somogyi, R. (1998) · PubMed · Cited by 951
Learning the Structure of Dynamic Probabilistic Networks
Friedman, N., Murphy, K., & Russell, S. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1301.7374 · Cited by 561 · cited 1×
“∗To whom correspondence should be addressed.”
Husmeier, D. (2003) · Bioinformatics · doi:10.1093/bioinformatics/btg313 · Cited by 530 · cited 4×
“Bayesian network (BN) inference algorithms have shown particular promise (Harteminket al., 2002; Husmeier, 2003; Smithet al., 2002, 2003), because unlike most other modeling frameworks, they can capture many types of relationships between variables.”
BackgroundMethodInfluentialLINEAR MODELING OF mRNA EXPRESSION LEVELS DURING CNS DEVELOPMENT AND INJURY
D'HAESELEER, P., WEN, X., FUHRMAN, S., & SOMOGYI, R. (1998) · Biocomputing '99 · doi:10.1142/9789814447300_0005 · Cited by 498
MODELING REGULATORY NETWORKS WITH WEIGHT MATRICES
WEAVER, D. C., WORKMAN, C. T., & STORMO, G. D. (1998) · Biocomputing '99 · doi:10.1142/9789814447300_0011 · Cited by 402 · cited 1×
“A variety of network inference algorithms have recently been used to identify gene regulatory networks from observational gene expression data (Akutsu et al., 2000; Arkinet al., 1997; D’haeseleer et al., 1999; Friedmanet al., 2000; Gardner et al., 2003; Harteminket al., 2001; Lianget al., 1998; Weaver et al., 1999; Xu…”
Method
Cited by
Items 101–200 of 736
Comparison of Reverse‐Engineering Methods Using an in Silico Network
Camacho, D. M., LICONA, P. V., Mendes, P., & Laubenbacher, R. (2007) · Annals of the New York Academy of Sciences · doi:10.1196/annals.1407.006 · Cited by 48
Bonev, B., Castelo‐Branco, G., Chen, F., Codeluppi, S., Corces, M. R., Fan, J., Heiman, M., Harris, K., Inoue, F., Kellis, M., et al. (2024) · Nature Neuroscience · doi:10.1038/s41593-024-01806-0 · Cited by 47
Harnessing Diversity towards the Reconstructing of Large Scale Gene Regulatory Networks
Hase, T., Ghosh, S., Yamanaka, R., & Kitano, H. (2013) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003361 · Cited by 47
“networks (BNs) [13–17], regression-based algorithms [18–22], graphical gaussian model (ggm) [23], meta predictors that combine several different methods [24,25], and several other approaches that were recently proposed [26–32], i.”
MethodFunctional association networks as priors for gene regulatory network inference
Studham, M. E., Tjärnberg, A., Nordling, T. E. M., Nelander, S., & Sonnhammer, E. L. L. (2014) · Bioinformatics · doi:10.1093/bioinformatics/btu285 · Cited by 43
“Contact: matthew.studham@scilifelab.se Supplementary information: Supplementary data are available at Bioinformatics online.”
BackgroundTenenhaus, A., Guillemot, V., Gidrol, X., & Frouin, V. (2008) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2008.87 · Cited by 47
“BANJO uses the framework of Bayesian Networks in order to infer both static and dynamic gene regulation networks [ 52 ].”
BackgroundMethodInfluentialUse of pathway information in molecular epidemiology
Thomas, D. C., Conti, D. V., Baurley, J. W., Nijhout, H. F., Reed, M. C., & Ulrich, C. M. (2009) · Human Genomics · doi:10.1186/1479-7364-4-1-21 · Cited by 46
Ceccarelli, M., Cerulo, L., & Santone, A. (2014) · Methods · doi:10.1016/j.ymeth.2014.06.005 · Cited by 45
“On E. coli SOS network correlation methods (ARACNE and CLR) outperform all other methods in undirected predictions, whereas BANJO and TSNIF that perform better in directed and signed prediction respectively.”
BackgroundMethodInfluentialHill, K., Porco, S., Lobet, G., Zappala, S., Mooney, S. J., Draye, X., & Bennett, M. J. (2013) · PLANT PHYSIOLOGY · doi:10.1104/pp.113.227215 · Cited by 45
“They were later extended to solve inference problems on time-series expression data (dynamic Bayesian network; Perrin et al., 2003; Yu et al., 2004).”
MethodGraml, V. M., Studera, X. E., Lawson, J., Chessel, A., Geymonat, M., Bortfeld‐Miller, M., Walter, T., Wagstaff, L., Piddini, E., & Salas, R. E. C. (2014) · Developmental Cell · doi:10.1016/j.devcel.2014.09.005 · Cited by 45
“We next turned to cell shape and microtubule hits and investigated dependencies between their features using Bayesian network analysis (Collinet et al., 2010; Yu et al., 2004).”
MethodHoshino, E., van Putten, I. E., Girsang, W., Resosudarmo, B. P., & Yamazaki, S. (2016) · Ecology and Society · doi:10.5751/es-08285-210216 · Cited by 44
“This limitation can be overcome by including dynamic variables that represent two or more points in time that indirectly account for feedback between the current states and the future (Yu et al. 2004).”
BackgroundFerrazzi, F., Sebastiani, P., Ramoni, M. F., & Bellazzi, R. (2007) · BMC Bioinformatics · doi:10.1186/1471-2105-8-s5-s2 · Cited by 44
“[15] and Husmeier [13], but have some limitations in assessing the suitability of DBNs to analyze highly complex and nonlinear cellular systems.”
BackgroundAlam, M. S., & Gazder, U. (2019) · Neural Computing and Applications · doi:10.1007/s00521-019-04107-x · Cited by 43
Incorporating time-delays in S-System model for reverse engineering genetic networks
Chowdhury, A. R., Chetty, M., & Vinh, N. X. (2013) · BMC Bioinformatics · doi:10.1186/1471-2105-14-196 · Cited by 42
“While the previous S-System based methods ALG [34] and REGARD [19], and the BN based approach BANJO [43] considered all inferred edges as instantaneous, TDSS was able to not only infer and segregate these interactions correctly as instantaneous or time-delayed, but the delays were found to be in…”
BackgroundMethodResultInfluentialYang, B., Xu, Y., Maxwell, A., Koh, W., Gong, P., & Zhang, C. (2018) · BMC Systems Biology · doi:10.1186/s12918-018-0635-1 · Cited by 42
“By using the known interactions obtained from literature [33, 37, 38], Table 2 showed the comparison of our algorithm with other methods such as Perrin [39], BANJO [40], Global-MIT [41] and Morshed [33] for correct predictions on the regulatory relationships between these eight genes.”
Using GeneReg to construct time delay gene regulatory networks
Huang, T., Liu, L., Qian, Z., Tu, K., Li, Y., & Xie, L. (2010) · BMC Research Notes · doi:10.1186/1756-0500-3-142 · Cited by 42
“Banjo is a representative gene network inference software based on Bayesian network formalism [6].”
MethodVariable selection and dependency networks for genomewide data
Dobra, A. (2009) · Biostatistics · doi:10.1093/biostatistics/kxp018 · Cited by 41
Inter-laminar microcircuits across neocortex: repair and augmentation
Opriș, I. C. (2013) · Frontiers in Systems Neuroscience · doi:10.3389/fnsys.2013.00080 · Cited by 41
“These methods allow to identify putative causal interactions and population codes within the neural circuits involved in perception and behavior (Yu et al., 2004; Beck et al., 2008).”
MethodFaria, J. P., Overbeek, R., Xia, F., Rocha, M., Rocha, I., & Henry, C. S. (2013) · Briefings in Bioinformatics · doi:10.1093/bib/bbs071 · Cited by 41
“In the first category [65, 100], the differential equation (ODEs)-based [101, 102], mutual information-based [103, 104], and Bayesian network-based methods [105, 106] are the most popular approaches.”
BackgroundNetwork Identifiability from Intrinsic Noise
Hayden, D., Yuan, Y., & Gonçalves, J. M. (2016) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2016.2640219 · Cited by 41
“Probabilistic methods, such as [5], seek to identify a network in which each state is considered conditionally independent of its non-descendants, given its parent states.”
BackgroundRubiolo, M., Milone, D. H., & Stegmayer, G. S. (2017) · Bioinformatics · doi:10.1093/bioinformatics/btx730 · Cited by 41
Model averaging strategies for structure learning in Bayesian networks with limited data
Broom, B. M., Do, K.-A., & Subramanian, D. (2012) · BMC Bioinformatics · doi:10.1186/1471-2105-13-s13-s10 · Cited by 40
“Figure 7 makes it clear that MDL/BIC performs very poorly, and also confirms Hartemink ’ s result [16] that BDe performs better than MDL/BIC.”
BackgroundLiang, Y., & Kelemen, A. (2017) · Briefings in Bioinformatics · doi:10.1093/bib/bbx036 · Cited by 41
Gene regulatory network inference based on causal discovery integrating with graph neural network
Feng, K., Jiang, H., Yin, C., & Sun, H. (2023) · Quantitative Biology · doi:10.1002/qub2.26 · Cited by 39
Barbosa, S., Niebel, B., Wolf, S., Mauch, K., & Takors, R. (2018) · Biosystems · doi:10.1016/j.biosystems.2018.10.008 · Cited by 39
Palle, S. R., Seeve, C. M., Eckert, A. J., Cumbie, W. P., Goldfarb, B., & Loopstra, C. A. (2010) · Tree Genetics & Genomes · doi:10.1007/s11295-010-0325-7 · Cited by 39
“BANJO can infer gene networks from gene expression data (Hartemink 2005; Yu et al. 2004).”
BackgroundZhang, Y., Zhang, W., & Xie, Y. (2013) · Neurocomputing · doi:10.1016/j.neucom.2013.02.015 · Cited by 39
“It is widely applied to a great variety of domains such as medical diagnosis [3], natural spoken dialog system [4], vision recognition, expert system [5], device fault diagnosis [6,7], fault prediction [8], and genetic regulatory network inference [9,10].”
BackgroundMorrissey, E. R., Juárez, M. A., Denby, K., & Burroughs, N. J. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btq421 · Cited by 39
Model-based redesign of global transcription regulation
Carrera, J., Rodrigo, G., & Jaramillo, A. (2009) · Nucleic Acids Research · doi:10.1093/nar/gkp022 · Cited by 39
“On the other hand, Bayesian methods (16–19) give networks with high precision but low proportion of true recovered interactions (they introduce few regulations with high con-fidence).”
BackgroundGupta, R., Stincone, A., Antczak, P., Durant, S., Bicknell, R., Bikfalvi, A., & Falciani, F. (2011) · BMC Systems Biology · doi:10.1186/1752-0509-5-52 · Cited by 38
“Bayesian networks have been among the first to be applied to biological problems [4].”
BackgroundA Dynamic Bayesian Network model for the simulation of Amyotrophic Lateral Sclerosis progression
Zandonà, A., Vasta, R., Chiò, A., & Camillo, B. D. (2019) · BMC Bioinformatics · doi:10.1186/s12859-019-2692-x · Cited by 38
Learning gene regulatory networks using the bees algorithm
Ruz, G. A., & Chacc, E. G. (2011) · Neural Computing and Applications · doi:10.1007/s00521-011-0750-z · Cited by 38
“For this, researches have proposed several mathematical models: Boolean networks [10], Probabilistic Boolean networks [26], Petri nets [28], Bayesian networks [32], recurrent neural networks [14], differential equations [8], linear regression [33], etc.”
Computational dynamic approaches for temporal omics data with applications to systems medicine
Liang, Y., & Kelemen, A. (2017) · BioData Mining · doi:10.1186/s13040-017-0140-x · Cited by 38
“The computational or statistical approaches for network construction include various levels such as transcriptional regulation network, metabolic network, protein-protein, and disease-drug-genes network [76 – 88].”
BackgroundAdvances in Bayesian networks for industrial process analytics: Bridging data and mechanisms
Zheng, J., Zhuo, Y., Jiang, X., Zeng, L., & Ge, Z. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126670 · Cited by 37
Reconstruction of a GRN model of salt stress response in arabidopsis using genetic algorithms
Ruz, G. A., Timmermann, T., & Chacc, E. G. (2015) · IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) · doi:10.1109/cibcb.2015.7300306 · Cited by 37
Gregoretti, F., Belcastro, V., di Bernardo, D., & Oliva, G. (2010) · PLoS ONE · doi:10.1371/journal.pone.0010179 · Cited by 37
“This is the case of BANJO [2], that assumes that the gene network can be modeled as a Bayesian network.”
BackgroundBuetti‐Dinh, A., Dethlefsen, O., Friedman, R., & Dopson, M. (2016) · Microbiology · doi:10.1099/mic.0.000314 · Cited by 37
“In addition, Bayesian network (BN) analysis can be used to infer regulatory linkages between mRNA abundances (Friedman, 2004; Hurley et al., 2012; Sachs et al., 2005; Yu et al., 2004).”
BackgroundHan, B., & Chen, X.-W. (2011) · BMC Genomics · doi:10.1186/1471-2164-12-s2-s9 · Cited by 37
“BDe score can penalize the structure complexity inherently by integrating P D S S ( | , ) and measuring the average expected likelihood over different possible choices of ˆ S ( ˆ S is an estimate of parameters from the maximum likelihood method for the structure S ) [35,36].”
MethodCamacho, D. M., & Collins, J. J. (2009) · Cell · doi:10.1016/j.cell.2009.03.032 · Cited by 36
“They considered inference methods based on ordinary differential equations or ODEs (Gardner et al., 2003; Lorenz et al., 2009), Bayesian networks (Yu et al., 2004), and information theory In this issue, Cantone et al. (2009) address this problem and present us with the systems biology equivalent of…”
MethodThomas, R., Paredes, C. J., Mehrotra, S., Vassily Hatzimanikatis, A., & Papoutsakis, E. T. (2007) · BMC Bioinformatics · doi:10.1186/1471-2105-8-228 · Cited by 36
“[20-23] are representative of methods which analyze the time course gene expression data using a Bayesian network framework.”
BackgroundMethodAn algebra-based method for inferring gene regulatory networks
Vera‐Licona, P., Jarrah, A. S., Puente, L. D. G., McGee, J., & Laubenbacher, R. (2014) · BMC Systems Biology · doi:10.1186/1752-0509-8-37 · Cited by 35
“To counteract the data limitation due to the 2-state data discretization, we used our inference method as a meta-algorithm, that is, we input a previously inferred network topology from the dynamic Bayesian method BANJO [18].”
BackgroundMethodInfluentialComputational biology approaches for mapping transcriptional regulatory networks
Saint‐André, V. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.08.028 · Cited by 35
“An influence score for dynamic Bayesian networks that attempts to estimate both the sign and relative magnitude of interactions among variables was used in Banjo (Bayesian Network Inference with Java Objects) [63].”
MethodInfluentialbLARS: An Algorithm to Infer Gene Regulatory Networks
Singh, N. K., & Vidyasagar, M. (2015) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2015.2450740 · Cited by 36
“Around the same time, graphical model based Bayesian methods have also been proposed [5], [16].”
MethodA framework to analyze multiple time series data: A case study with Streptomyces coelicolor
Mehra, S., Lian, W., Jayapal, K. P., Charaniya, S., Sherman, D. H., & Hu, W. (2005) · Journal of Industrial Microbiology & Biotechnology · doi:10.1007/s10295-005-0034-7 · Cited by 35
“Various computational frameworks based on Boolean networks [16], dynamic Bayesian networks [23, 24], and Hidden Markov models [18] have been proposed to model time series and gene perturbation data to build the complete gene network.”
An integrated approach for inference and mechanistic modeling for advancing drug development
Aksenov, S. V., Church, B., Dhiman, A., Georgieva, A., Sarangapani, R., Helmlinger, G., & Khalil, I. G. (2005) · FEBS Letters · doi:10.1016/j.febslet.2005.02.012 · Cited by 35
“been used to infer probabilistic graph models of gene regulatory networks from genomic expression data [21,22].”
MethodLim, N., Şenbabaoğlu, Y., Michailidis, G. C., & d’Alché–Buc, F. (2013) · Bioinformatics · doi:10.1093/bioinformatics/btt167 · Cited by 34
“A number of methods have been used for this task, including dynamic Bayesian networks (Morrissey et al. , 2010; Yu et al. , 2004), Granger causality models (see Shojaie and Michailidis, 2010b and references therein) and state-space models (Perrin et al. , 2003; Rangel et al. , 2004).”
MethodEvolving dynamic Bayesian networks with Multi-objective genetic algorithms
Ross, B. J., & Zuviria, E. (2006) · Applied Intelligence · doi:10.1007/s10489-006-0002-6 · Cited by 34
“use an influence heuristic to evaluate the strength of correlation for linkages [15].”
BackgroundMethodInfluentialSize matters: network inference tackles the genome scale
Hayete, B., Gardner, T. S., & Collins, J. J. (2007) · Molecular Systems Biology · doi:10.1038/msb4100118 · Cited by 33
“…focus on transcriptional regulatory networks (Kholodenko et al , 1997; Tavazoie et al , 1999; Gardner et al , 2003; Segal et al , 2003; Beer and Tavazoie, 2004; Yu et al , 2004; di Bernardo et al , 2005; Gardner and Faith, 2005; Woolf et al , 2005; Margolin et al , 2006; Faith et al , 2007).”
Zhang, Y., Deng, Z., Jiang, H., & Jia, P. (2007) · Springer eBooks · doi:10.1007/978-3-540-73255-6_17 · Cited by 33
“[24] stated that three categories seem to best balance the tradeoff between information loss and insufficient data for estimation.”
BackgroundConstructing non-stationary Dynamic Bayesian Networks with a flexible lag choosing mechanism
Jia, Y., & Huan, J. (2010) · BMC Bioinformatics · doi:10.1186/1471-2105-11-s6-s27 · Cited by 33
“Further, Hartemink and Imoto extended their techniques to DBNs [11,14].”
MethodModeling regulatory networks using machine learning for systems metabolic engineering
Kwon, M. S., Lee, B. T., Lee, S. Y., & Kim, H. U. (2020) · Current Opinion in Biotechnology · doi:10.1016/j.copbio.2020.02.014 · Cited by 32
Systems biology approaches to understanding stem cell fate choice
Peltier, J., & Schaffer, D. V. (2009) · IET Systems Biology · doi:10.1049/iet-syb.2009.0011 · Cited by 32
“Since the publication of this work, however, other work has discovered additional transcription factors that play a role in maintaining pluripotency [35].”
BackgroundKim, T.-J., Kwon, H.-H., & Lima, C. (2018) · Journal of Hydrology · doi:10.1016/j.jhydrol.2018.07.082 · Cited by 32
Causal inference in the medical domain: a survey
Wu, X., Peng, S., Li, J., Zhang, J., Sun, Q., Li, W., Qian, Q., Liu, Y., & Guo, Y. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05338-9 · Cited by 31
Discovery of complex pathways from observational data
Baurley, J. W., Conti, D. V., Gauderman, W. J., & Thomas, D. C. (2010) · Statistics in Medicine · doi:10.1002/sim.3962 · Cited by 31
“Bayesian networks have been widely used for exploring relationships between variables in in silico experiments and analysis of gene expression properties and patterns [7, 28, 29].”
Inference algorithms for gene networks: a statistical mechanics analysis
Braunstein, A., Pagnani, A., Weigt, M., & Zecchina, R. (2008) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/2008/12/p12001 · Cited by 31
New probabilistic graphical models for genetic regulatory networks studies
Wang, J., Cheung, L. W.-K., & Delabie, J. (2005) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2005.04.003 · Cited by 31
“…NA IGFD: (P = 0.05, OV) 9.5 0 57.1 4 IGFD: (P = 0.2, OV) 14.3 0 28.6 44 IGB: (P = 0.05, OV) 14.3 0 47.6 27 IGB: (P = 0.15, OV) 14.3 0 33.3 33 IGF: (P = 0.05, OV) 9.5 0 57.1 19 EG + GN: (OV) 9.5 0 52.4 223 IGFD + GN: (OV) 14.3 0 52.4 230 IGFD + GN: (UV) 14.3 9.5 28.6 1148 EG + GN: (UV) 9.5 9.5…”
InfluentialFuzzy modeling of signal transduction networks
Huang, Z. J., & Hahn, J. (2009) · Chemical Engineering Science · doi:10.1016/j.ces.2009.01.041 · Cited by 31
Wang, W. “., Wang, G., Li, J., Chen, J., Gao, Z., Fang, L., Ren, S., & Wang, Q. (2025) · Water Research X · doi:10.1016/j.wroa.2025.100369 · Cited by 30
A Survey on Evolutionary Algorithm Based Hybrid Intelligence in Bioinformatics
Li, S., Kang, L., & Zhao, X. (2014) · BioMed Research International · doi:10.1155/2014/362738 · Cited by 29
“[53] utilized GA to determine the optimal network structure consistent with experimental data along with the dynamic Bayesian network by defining an evaluation function based on Bayesian dirichlet equivalence (BDe) score and Bayesian information criterion (BIC) score.”
MethodLearning Genetic Regulatory Network Connectivity from Time Series Data
Barker, N., Myers, C. J., & Kuwahara, H. (2009) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2009.48 · Cited by 29
“Promising preliminary results are also reported for an analysis of experimental data for genes involved in the yeast cell cycle.”
BackgroundminiTUBA: medical inference by network integration of temporal data using Bayesian analysis
Xiang, Z., Minter, R. M., Bi, X., WOOLF, P. J., & He, Y. O. (2007) · Bioinformatics · doi:10.1093/bioinformatics/btm372 · Cited by 29
“DBNs have been applied to bioinformatic analyses of gene expression data (Yu et al., 2004; Zou and Conzen, 2005), and have generated insights that could not be obtained from static Bayesian analysis.”
Hui, E., Stafford, R., Matthews, I., & Smith, V. A. (2021) · Ecological Informatics · doi:10.1016/j.ecoinf.2021.101539 · Cited by 28
“This can be done by utilizing the influence score [Yu et al., 2004] and the mutual information (MI).”
MethodSelf-citationAdaptive regulatory genes cardinality for reconstructing genetic networks
Chowdhury, A. R., Chetty, M., & Vinh, N. X. (2012) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2012.6256462 · Cited by 28
Linear matrix inequalities approach to reconstruction of biological networks
Cosentino, C., Curatola, W., Montefusco, F., Bansal, M., di Bernardo, D., & Amato, F. (2007) · IET Systems Biology · doi:10.1049/iet-syb:20060054 · Cited by 28
Inferring causal networks of dynamical systems through transient dynamics and perturbation
Stepaniants, G., Brunton, B. W., & Kutz, J. N. (2020) · Physical review. E · doi:10.1103/physreve.102.042309 · Cited by 27
“Yet other methodologies such as Dynamic Causal Modeling [29] and Bayesian networks [30] have been developed to solve this ill-posed problem in application to neuronal dynamics and gene regulatory networks.”
MethodImproving gene regulatory network inference using network topology information
Nair, A., Chetty, M., & Wangikar, P. P. (2015) · Molecular BioSystems · doi:10.1039/c5mb00122f · Cited by 27
A Scale-Free Structure Prior for Graphical Models with Applications in Functional Genomics
Sheridan, P. J., Kamimura, T., & Shimodaira, H. (2010) · PLoS ONE · doi:10.1371/journal.pone.0013580 · Cited by 27
“To this end, we used the software packages ARACNE [54], [55] and BANJO [23] to analyze the gene expression data as well.”
MethodThe Local Edge Machine: inference of dynamic models of gene regulation
McGoff, K. A., Guo, X., Deckard, A., Kelliher, C., Leman, A. R., Francey, L. J., Hogenesch, J. B., Haase, S. B., & Harer, J. (2016) · Genome biology · doi:10.1186/s13059-016-1076-z · Cited by 27
“Four of the algorithms (TD-ARACNE [19], Inferelator [17, 18], Banjo [20, 21], and Granger Causality [14]), representing distinct approaches to inference, were selected for comparison due to their (or their predecessors’) strong performances in previous testing, including in the DREAM network…”
MethodPoLoBag: Polynomial Lasso Bagging for signed gene regulatory network inference from expression data
Roy, G. G., Geard, N. L., Verspoor, K. M., & He, S. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa651 · Cited by 27
Analysis of nasopharyngeal carcinoma risk factors with Bayesian networks
Aussem, A., de Morais, S. R., & Corbex, M. A. (2011) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2011.09.002 · Cited by 27
Neural model of gene regulatory network: a survey on supportive meta-heuristics
Biswas, S., & Acharyya, S. (2016) · Theory in Biosciences · doi:10.1007/s12064-016-0224-z · Cited by 27
A large-scale benchmark for network inference from single-cell perturbation data
Chevalley, M., Roohani, Y. H., Mehrjou, A., Leskovec, J., & Schwab, P. (2025) · Communications Biology · doi:10.1038/s42003-025-07764-y · Cited by 26
“…technology that could theoretically support performing causal inference in cellular systems at the scale of thousands of perturbations per experiment, and therefore holds enormous promise in potentially enabling researchers to uncover the intricate wiring diagrams of cellular biology 10 – 13 .”
Banerjee, A., Chandra, S., & Ott, E. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2216030120 · Cited by 26
Hussain, L., Ali, A., Rathore, S., Saeed, S., Idris, A., Usman, M. U., Iftikhar, M. A., & Suh, D. Y. (2018) · IEEE Access · doi:10.1109/access.2018.2886644 · Cited by 26
“The Bayesian networks (BNs) have been used to develop relationship among genes, environment and diseases [33], gene-environmental factors [33], medical diagnosis, forensic science, crime and terrorism risk, and ecological conservation [33], analyzing gene expression data [34], [35], predict protein-protein interaction…”
BackgroundRank-based edge reconstruction for scale-free genetic regulatory networks
Chen, G., Larsen, P., Almasri, E., & Dai, Y. D. (2008) · BMC Bioinformatics · doi:10.1186/1471-2105-9-75 · Cited by 26
“[9] was selected because our simulated profiles were generated following their procedure, though our networks possess the scale-free property while no structure was assumed in theirs.”
BackgroundMethodResultInfluentialKim, J., Bates, D. G., Postlethwaite, I., Heslop-Harrison, J. S., & Cho, K. (2008) · Bioinformatics · doi:10.1093/bioinformatics/btn107 · Cited by 26
“Although dynamical Bayesian methods can overcome these problems, the resulting problem formulation needs to be solved using global optimization algorithms such as greedy search, simulated annealing and genetic algorithms (Yu et al ., 2004), which are computationally expensive.”
MethodLefèvre, T., Lepresle, A., & Chariot, P. (2015) · International Journal of Legal Medicine · doi:10.1007/s00414-015-1164-8 · Cited by 25
“Bayesian networks are usually computed for relatively small samples, as in genetics [15, 22–25].”
BackgroundEmad, A., & Milenković, O. (2014) · PLoS ONE · doi:10.1371/journal.pone.0090781 · Cited by 25
“The performance of two additional algorithms utilizing sparsity and causality, TSNI [56] and BANJO [57], were evaluated in [8] using the same dataset.”
Methods for the Inference of Biological Pathways and Networks
Bumgarner, R. E., & Yeung, K. Y. (2009) · Methods in molecular biology · doi:10.1007/978-1-59745-243-4_11 · Cited by 25
Avoiding pitfalls in L1-regularised inference of gene networks
Tjärnberg, A., Nordling, T. E. M., Studham, M., Nelander, S., & Sonnhammer, E. L. L. (2014) · Molecular BioSystems · doi:10.1039/c4mb00419a · Cited by 24
Yao, C.-W., Hsu, B., & Chen, B. (2011) · BMC Bioinformatics · doi:10.1186/1471-2105-12-335 · Cited by 24
“Various approaches of reverse engineering have been used to identify plausible gene networks, including clustering algorithms, ordinary differential equation (ODE) models and Bayesian networks (BNs), which have been extended to construct dynamic Bayesian networks (DBNs) [14,15].”
MethodPolynomial Time Algorithm for Learning Globally Optimal Dynamic Bayesian Network
Vinh, N. X., Chetty, M., Coppel, R. L., & Wangikar, P. P. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24965-5_81 · Cited by 24
“Since its inception, DBN has received particular interest, especially from the bioinformatics community [7, 13, 14, 12].”
BackgroundMethodInfluentialRuz, G. A., & Chacc, E. G. (2010) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2010.139 · Cited by 24
“Several mathematical models have been proposed to represent GRN: Boolean networks [1], Probabilistic Boolean networks [2], Petri nets [3], Bayesian networks [4], recurrent neural networks [5], differential equations [6], linear regression [7], etc.”
BackgroundBernabé, B. P., Shin, S., Rios, P., Broadbelt, L. J., Shea, L. D., & Seidlits, S. K. (2016) · Integrative Biology · doi:10.1039/c6ib00093b · Cited by 24
Chan, S. C., Zhang, L., Wu, H. C., & Tsui, K. M. (2014) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2014.2343951 · Cited by 23
“cients can be shrunk to zero.”
Modeling of Critically Ill Patient Pathways to Support Intensive Care Delivery
Trevena, W., Lal, A., Zec, S., Cubro, E., Zhong, X., Dong, Y., & Gajic, O. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3183253 · Cited by 23
Detecting direction of causal interactions between dynamically coupled signals
Ishiguro, K., Otsu, N., Lungarella, M., & Kuniyoshi, Y. (2008) · Physical Review E · doi:10.1103/physreve.77.026216 · Cited by 23
Reverse engineering biomolecular systems using -omic data: challenges, progress and opportunities
Quo, C. F., Kaddi, C. D., Phan, J. H., Zollanvari, A., Xu, M., Wang, M. D., & Alterovitz, G. (2012) · Briefings in Bioinformatics · doi:10.1093/bib/bbs026 · Cited by 23
Morshed, N., Chetty, M., & Vinh, N. X. (2012) · BMC Systems Biology · doi:10.1186/1752-0509-6-62 · Cited by 22
“We used 30, 50 and 100 samples, generated 5 datasets in each case and compared our approach with two other DBN based methods, namely BANJO [16] and BNFinder [17].”
Walker, M. L., Holt, K. E., Anderson, G. P., Teo, S. M., Sly, P. D., Holt, P. G., & Inouye, M. (2014) · Frontiers in Immunology · doi:10.3389/fimmu.2014.00447 · Cited by 22
“To avoid getting “stuck” on a suboptimal network, which happens to be better than those most similar to it, it is possible to run the algorithm multiple times from different starting points (156) or to allow (165) limited excursions “downhill” so that higher hills (which better fit the data) might be found.”
BackgroundPark, S. B., Chung, C. K., Gonzalez, E., & Yoo, C. (2018) · Journal of Bone Metabolism · doi:10.11005/jbm.2018.25.4.251 · Cited by 22
Prediction of cardiac transcription networks based on molecular data and complex clinical phenotypes
Tönjes, M., Schueler, M., Hammer, S., Pape, U. J., Fischer, J. J., Berger, F. F., Vingron, M., & Sperling, S. (2008) · Molecular BioSystems · doi:10.1039/b800207j · Cited by 22
Inference of Cancer-specific Gene Regulatory Networks Using Soft Computing Rules
Wang, X., & Gotoh, O. (2010) · Gene Regulation and Systems Biology · doi:10.4137/grsb.s4509 · Cited by 22
Miller, M. A., Feng, X., Li, G., & RABITZ, H. A. (2012) · PLoS ONE · doi:10.1371/journal.pone.0037664 · Cited by 22
“To capture both linear and nonlinear interactions, Bayesian networks (BNs) [19,20], clustering algorithms [21,22], and information-theoretic approaches [5,23,24] have been employed.”
MethodNetwork clustering: probing biological heterogeneity by sparse graphical models
Mukherjee, S., & Hill, S. M. (2011) · Bioinformatics · doi:10.1093/bioinformatics/btr070 · Cited by 22
Computational Inference of Neural Information Flow Networks
Smith, V. A., Yu, J., Smulders, T. V., Hartemink, A. J., & Jarvis, E. D. (2005) · PLoS Computational Biology · doi:10.1371/journal.pcbi.0020161.eor · Cited by 22
Self-citationQuantitative imaging of focal adhesion dynamics and their regulation by HGF and Rap1 signaling
Spanjaard, E., Smal, I., Angelopoulos, N., Verlaan-Klink, I., Matov, A., Meijering, E. H. W., Wessels, L. F. A., Bos, H., & de Rooij, J. (2014) · Experimental Cell Research · doi:10.1016/j.yexcr.2014.10.012 · Cited by 22
A Survey of Methods, Challenges and Perspectives in CausalityPreprint
Gendron, G., Witbrock, M., & Dobbie, G. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.00293 · Cited by 22
“Causality also has applications in biology for modeling dynamic systems such as ecosystems [171, 194] or attributing gene expression to phenotypical attributes in an individual [32, 154, 204].”
BackgroundHuang, A. Y., Joerger, G., Salmon, R., Dunkin, B. J., Sherman, V., Bass, B. L., & Garbey, M. (2015) · Surgical Endoscopy · doi:10.1007/s00464-015-4610-2 · Cited by 21
Petrovskiy, E. D., Saik, O., Tiys, E., Lavrik, I. N., Kolchanov, N. A., & Иванисенко, В. А. (2015) · BMC Genomics · doi:10.1186/1471-2164-16-s13-s3 · Cited by 21
“Approaches that use these data to reconstruct the network of genetic regulation and to define its parameters include approaches that use Bayesian networks [17-20] and ones based on mutual information [21,22].”
Method
Metadata
- Authors
- Yu, J., Smith, V. A., Wang, P. P., Hartemink, A. J., & Jarvis, E. D.
- Affiliations
- Duke University (US)
- Corresponding author
- Yu, Jing
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2004-07-29
- Volume
- 20
- Issue
- 18
- Pages
- 3594-3603
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- OpenAlex
- W2161511352
- Cited by
- 675
- References
- 23
- Citations by year
- 2026: 7 · 2025: 15 · 2024: 21 · 2023: 16 · 2022: 17 · 2021: 17 · 2020: 28 · 2019: 33 · 2018: 30 · 2017: 34 · 2016: 31 · 2015: 40 · 2014: 43 · 2013: 41 · 2012: 42
- FWCI
- 20.57
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- cc-by-nc-nd
- Locations
- Bioinformatics (publishedVersion)
- PubMed (publishedVersion)
- DukeSpace (Duke University) (submittedVersion, cc-by-nc-nd)
- Funders
- National Science Foundation
- David and Lucile Packard Foundation
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene Regulatory Network Analysis
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Keywords
- Bayesian network inference, dynamic Bayesian networks, causal network inference, data scarcity, influence score, data discretization, sampling interval, data interpolation, false positive interactions, search heuristics
- MeSH terms
- Algorithms, Bayes Theorem, Computer Simulation, Gene Expression Regulation, Models, Genetic, Software, Models, Statistical, Signal Transduction, Oligonucleotide Array Sequence Analysis, Gene Expression Profiling
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.