Advances to Bayesian network inference for generating causal networks from observational biological data

By Jing Yu, V. Anne Smith, Paul P. Wang, Alexander J. Hartemink, Erich D. Jarvis. Bioinform., 2004

739 citations recorded by the source corpus.

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/

Subfields: Artificial Intelligence, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/bef787a41e2173fc7913fb87b4eddb53bad52149

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Inferring cellular networks – a review (2007, methodology): “[34] show that their own method, ARACNe, compares favorably against static Bayesian networks on a simulated network with 19 nodes [54] – but only if the dataset includes several hundreds of observations.”
A yeast synthetic network for in vivo assessment of reverse-engineering and modeling approaches. (2009, positive): “[Yu et al., 2004] Yu, J., Smith, V. A., Wang, P. P., Hartemink, A. J., and Jarvis, E. D. (2004).”
Comparison of co-expression measures: mutual information, correlation, and model based indices (2012, background): “Many authors have proposed to use Bayesian networks for analyzing gene expression data [44-47] and for generating causal networks from observational data [48] or genetic data [49,50].”
Inference of gene regulatory networks and compound mode of action from time course gene expression profiles (2006, methodology): “Each network was represented by a full rank sp arse matrix A (N X N) with eigenvalues with a real part less then 0 (Ljung (1999)) to ensure the stability of the dynamical syst ems, i.”
How to infer gene networks from expression profiles (2007, methodology): “We refer the reader to (Yu et al , 2004).”
Venture: a higher-order probabilistic programming platform with programmable inference (2014, background): “…recognition (Baker, 1979), information extraction (Pasula et al., 2002), multitarget tracking and sensor fusion (Oh et al., 2009; Arora et al., 2010), ecology (Csilléry et al., 2010) and computational biology (Friedman et al., 2000; Yu et al., 2004; Toni et al., 2009; Dowell and Eddy, 2004).”
Review of Causal Discovery Methods Based on Graphical Models (2019, background): “…and d’Alché Buc, 2013; Emad and Milenkovic, 2014; Carlin et al., 2017; Yang et al., 2017; Finkle et al., 2018), and similarly, some ﬁndings were based on dynamic Bayesian network learning from observational biological data (Yu et al., 2004; Wu and Liu, 2008; Vasimuddin and Srinivas, 2017).”
GeNGe: systematic generation of gene regulatory networks (2009, neutral): “, 2005), and dynamic Bayesian networks (Friedman et al., 1998; Yu et al., 2004; Werhli et al., 2006).”
Quantitative and logic modelling of gene and molecular networks (2015, methodology): “Directed influences are also predicted by probabilistic methods such as B AYESIAN INFERENCE (72) — for example, Banjo (73) and CatNet — which compute the probability that a certain set of data is produced by various networks.”
Inferring Regulatory Networks from Expression Data Using Tree-Based Methods (2010, background): “While this limitation is partially circumvented by dynamic Bayesian networks [17,19], these models can only be learned from time-series expression data.”