Frank Dondelinger

Inferring species interaction networks from species abundance data: A comparative evaluation of various statistical and machine learning methods

Abstract The complexity of ecosystems is staggering, with hundreds or thousands of species interacting in a number of ways from competition and predation to facilitation and mutualism. Understanding the networks that form the systems is of growing importance, e.g. to understand how species will respond to climate change, or to predict potential knock-on effects of a biological control agent. In recent years, a variety of summary statistics for characterising the global and local properties of such networks have been derived, which provide a measure for gauging the accuracy of a mathematical model for network formation processes. However, the critical underlying assumption is that the true network is known. This is not a straightforward task to accomplish, and typically requires minute observations and detailed field work. More importantly, knowledge about species interactions is restricted to specific kinds of interactions. For instance, while the interactions between pollinators and their host plants are amenable to direct observation, other types of species interactions, like those mentioned above, are not, and might not even be clearly defined from the outset. To discover information about complex ecological systems efficiently, new tools for inferring the structure of networks from field data are needed. In the present study, we investigate the viability of various statistical and machine learning methods recently applied in molecular systems biology: graphical Gaussian models, L1-regularised regression with least absolute shrinkage and selection operator (LASSO), sparse Bayesian regression and Bayesian networks. We have assessed the performance of these methods on data simulated from food webs of known structure, where we combined a niche model with a stochastic population model in a 2-dimensional lattice. We assessed the network reconstruction accuracy in terms of the area under the receiver operating characteristic (ROC) curve, which was typically in the range between 0.75 and 0.9, corresponding to the recovery of about 60% of the true species interactions at a false prediction rate of 5%. We also applied the models to presence/absence data for 39 European warblers, and found that the inferred species interactions showed a weak yet significant correlation with phylogenetic similarity scores, which tended to weakly increase when including bio-climate covariates and allowing for spatial autocorrelation. Our findings demonstrate that relevant patterns in ecological networks can be identified from large-scale spatial data sets with machine learning methods, and that these methods have the potential to contribute novel important tools for gaining deeper insight into the structure and stability of ecosystems.

Dynamic Bayesian networks in molecular plant science: inferring gene regulatory networks from multiple gene expression time series

To understand the processes of growth and biomass production in plants, we ultimately need to elucidate the structure of the underlying regulatory networks at the molecular level. The advent of high-throughput postgenomic technologies has spurred substantial interest in reverse engineering these networks from data, and several techniques from machine learning and multivariate statistics have recently been proposed. The present article discusses the problem of inferring gene regulatory networks from gene expression time series, and we focus our exposition on the methodology of Bayesian networks. We describe dynamic Bayesian networks and explain their advantages over other statistical methods. We introduce a novel information sharing scheme, which allows us to infer gene regulatory networks from multiple sources of gene expression data more accurately. We illustrate and test this method on a set of synthetic data, using three different measures to quantify the network reconstruction accuracy. The main application of our method is related to the problem of circadian regulation in plants, where we aim to reconstruct the regulatory networks of nine circadian genes in Arabidopsis thaliana from four gene expression time series obtained under different experimental conditions.

Reverse Engineering Gene Regulatory Networks Related to Quorum Sensing in the Plant Pathogen Pectobacterium atrosepticum

The objective of the project reported in the present chapter was the reverse engineering of gene regulatory networks related to quorum sensing in the plant pathogen Pectobacterium atrosepticum from micorarray gene expression profiles, obtained from the wild-type and eight knockout strains. To this end, we have applied various recent methods from multivariate statistics and machine learning: graphical Gaussian models, sparse Bayesian regression, LASSO (least absolute shrinkage and selection operator), Bayesian networks, and nested effects models. We have investigated the degree of similarity between the predictions obtained with the different approaches, and we have assessed the consistency of the reconstructed networks in terms of global topological network properties, based on the node degree distribution. The chapter concludes with a biological evaluation of the predicted network structures.

Nonhomogeneous dynamic Bayesian networks in systems biology.

Dynamic Bayesian networks (DBNs) have received increasing attention from the computational biology community as models of gene regulatory networks. However, conventional DBNs are based on the homogeneous Markov assumption and cannot deal with inhomogeneity and nonstationarity in temporal processes. The present chapter provides a detailed discussion of how the homogeneity assumption can be relaxed. The improved method is evaluated on simulated data, where the network structure is allowed to change with time, and on gene expression time series during morphogenesis in Drosophila melanogaster.