Interspecies Translation of Disease Networks Increases Robustness and Predictive Accuracy

Gene regulatory networks give important insights into the mechanisms underlying physiology and pathophysiology. The derivation of gene regulatory networks from high-throughput expression data via machine learning strategies is problematic as the reliability of these models is often compromised by limited and highly variable samples, heterogeneity in transcript isoforms, noise, and other artifacts. Here, we develop a novel algorithm, dubbed Dandelion, in which we construct and train intraspecies Bayesian networks that are translated and assessed on independent test sets from other species in a reiterative procedure. The interspecies disease networks are subjected to multi-layers of analysis and evaluation, leading to the identification of the most consistent relationships within the network structure. In this study, we demonstrate the performance of our algorithms on datasets from animal models of oculopharyngeal muscular dystrophy (OPMD) and patient materials. We show that the interspecies network of genes coding for the proteasome provide highly accurate predictions on gene expression levels and disease phenotype. Moreover, the cross-species translation increases the stability and robustness of these networks. Unlike existing modeling approaches, our algorithms do not require assumptions on notoriously difficult one-to-one mapping of protein orthologues or alternative transcripts and can deal with missing data. We show that the identified key components of the OPMD disease network can be confirmed in an unseen and independent disease model. This study presents a state-of-the-art strategy in constructing interspecies disease networks that provide crucial information on regulatory relationships among genes, leading to better understanding of the disease molecular mechanisms. Author Summary: The identification of gene regulatory networks can provide vital information on biological processes. Despite numerous advancements in developing machine learning strategies, the stochastic nature of such biological systems complicates the construction of robust and reliable network structures. In recent years, the use of cross-species datasets enabled scientists to better understand the molecular mechanisms that are associated with human disorders. However, it also presents a challenge in dealing with especially difficult mapping of protein orthologues, alternative transcript splicing, noise, or other artifacts. Here, we developed a novel algorithm for constructing interspecies disease networks that provide accurate predictive value over the disease phenotype and gene expression. We show that the disease-association of potential key regulators that play a role in interspecies disease networks can be reproduced and validated in an unseen and independent model system. This study presents a novel strategy for constructing networks that can be translated across species whilst providing a comprehensive view of regulatory relationships associated with the disease.