Precision medicine relies on the identification of robust disease and risk factor signatures from omics data. However, current knowledge-driven approaches may overlook novel or unexpected phenomena due to the inherent biases in biological knowledge. In this study, we present a data-driven signature discovery workflow for DNA methylation analysis utilizing network-coherent autoencoders (NCAEs) with biologically relevant latent embeddings. First, we explored the architecture space of autoencoders trained on a large-scale pan-tissue compendium (n = 75 272) of human epigenome-wide association studies. We observed the emergence of co-localized patterns in the deep autoencoder latent space representations that corresponded to biological network modules. We determined the NCAE configuration with the strongest co-localization and centrality signals in the human protein interactome. Leveraging the NCAE embeddings, we then trained interpretable deep neural networks for risk factor (aging, smoking) and disease (systemic lupus erythematosus) prediction and classification tasks. Remarkably, our NCAE embedding-based models outperformed existing predictors, revealing novel DNA methylation signatures enriched in gene sets and pathways associated with the studied condition in each case. Our data-driven biomarker discovery workflow provides a generally applicable pipeline to capture relevant risk factor and disease information. By surpassing the limitations of knowledge-driven methods, our approach enhances the understanding of complex epigenetic processes, facilitating the development of more effective diagnostic and therapeutic strategies.

MOTIVATION: The simultaneous availability of ATAC-seq and RNA-seq experiments allows to obtain a more in-depth knowledge on the regulatory mechanisms occurring in gene regulatory networks. In this article, we highlight and analyze two novel aspects that leverage on the possibility of pairing RNA-seq and ATAC-seq data. Namely we investigate the causality of the relationships between transcription factors, chromatin and target genes and the internal consistency between the two omics, here measured in terms of structural balance in the sample correlations along elementary length-3 cycles. RESULTS: We propose a framework that uses the a priori knowledge on the data to infer elementary causal regulatory motifs (namely chains and forks) in the network. It is based on the notions of conditional independence and partial correlation, and can be applied to both longitudinal and non-longitudinal data. Our analysis highlights a strong connection between the causal regulatory motifs that are selected by the data and the structural balance of the underlying sample correlation graphs: strikingly, >97% of the selected regulatory motifs belong to a balanced subgraph. This result shows that internal consistency, as measured by structural balance, is close to a necessary condition for 3-node regulatory motifs to satisfy causality rules. AVAILABILITY AND IMPLEMENTATION: The analysis was carried out in MATLAB and the code can be found at https://github.com/albertozenere/Multi-omics-elementary-regulatory-motifs. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Hub transcription factors, regulating many target genes in gene regulatory networks (GRNs), play important roles as disease regulators and potential drug targets. However, while numerous methods have been developed to predict individual regulator-gene interactions from gene expression data, few methods focus on inferring these hubs. RESULTS: We have developed ComHub, a tool to predict hubs in GRNs. ComHub makes a community prediction of hubs by averaging over predictions by a compendium of network inference methods. Benchmarking ComHub against the DREAM5 challenge data and two independent gene expression datasets showed a robust performance of ComHub over all datasets. CONCLUSIONS: In contrast to other evaluated methods, ComHub consistently scored among the top performing methods on data from different sources. Lastly, we implemented ComHub to work with both predefined networks and to perform stand-alone network inference, which will make the method generally applicable.

MOTIVATION: High correlation in expression between regulatory elements is a persistent obstacle for the reverse-engineering of gene regulatory networks. If two potential regulators have matching expression patterns, it becomes challenging to differentiate between them, thus increasing the risk of false positive identifications. RESULTS: To allow for gene regulation predictions of high confidence, we propose a novel method, the Linear Profile Likelihood (LiPLike), that assumes a regression model and iteratively searches for interactions that cannot be replaced by a linear combination of other predictors. To compare the performance of LiPLike with other available inference methods, we benchmarked LiPLike using three independent datasets from the Dialogue on Reverse Engineering Assessment and Methods 5 (DREAM5) network inference challenge. We found that LiPLike could be used to stratify predictions of other inference tools, and when applied to the predictions of DREAM5 participants, we observed an average improvement in accuracy of >140% compared to individual methods. Furthermore, LiPLike was able to independently predict networks better than all DREAM5 participants when applied to biological data. When predicting the Escherichia coli network, LiPLike had an accuracy of 0.38 for the top-ranked 100 interactions, whereas the corresponding DREAM5 consensus model yielded an accuracy of 0.11. AVAILABILITY AND IMPLEMENTATION: We made LiPLike available to the community as a Python toolbox, available at https://gitlab.com/Gustafsson-lab/liplike. We believe that LiPLike will be used for high confidence predictions in studies where individual model interactions are of high importance, and to remove false positive predictions made by other state-of-the-art gene-gene regulation prediction tools. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Complex diseases are due to the dense interactions of many disease-associated factors that dysregulate genes that in turn form the so-called disease modules, which have shown to be a powerful concept for understanding pathological mechanisms. There exist many disease module inference methods that rely on somewhat different assumptions, but there is still no gold standard or best-performing method. Hence, there is a need for combining these methods to generate robust disease modules. RESULTS: We developed MODule IdentiFIER (MODifieR), an ensemble R package of nine disease module inference methods from transcriptomics networks. MODifieR uses standardized input and output allowing the possibility to combine individual modules generated from these methods into more robust disease-specific modules, contributing to a better understanding of complex diseases. AVAILABILITY AND IMPLEMENTATION: MODifieR is available under the GNU GPL license and can be freely downloaded from https://gitlab.com/Gustafsson-lab/MODifieR and as a Docker image from https://hub.docker.com/r/ddeweerd/modifier. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Recent technological advancements have made time-resolved, quantitative, multi-omics data available for many model systems, which could be integrated for systems pharmacokinetic use. Here, we present large-scale simulation modeling (LASSIM), which is a novel mathematical tool for performing large-scale inference using mechanistically defined ordinary differential equations (ODE) for gene regulatory networks (GRNs). LASSIM integrates structural knowledge about regulatory interactions and non-linear equations with multiple steady state and dynamic response expression datasets. The rationale behind LASSIM is that biological GRNs can be simplified using a limited subset of core genes that are assumed to regulate all other gene transcription events in the network. The LASSIM method is implemented as a general-purpose toolbox using the PyGMO Python package to make the most of multicore computers and high performance clusters, and is available at https://gitlab.com/Gustafsson-lab/lassim. As a method, LASSIM works in two steps, where it first infers a non-linear ODE system of the pre-specified core gene expression. Second, LASSIM in parallel optimizes the parameters that model the regulation of peripheral genes by core system genes. We showed the usefulness of this method by applying LASSIM to infer a large-scale non-linear model of naïve Th2 cell differentiation, made possible by integrating Th2 specific bindings, time-series together with six public and six novel siRNA-mediated knock-down experiments. ChIP-seq showed significant overlap for all tested transcription factors. Next, we performed novel time-series measurements of total T-cells during differentiation towards Th2 and verified that our LASSIM model could monitor those data significantly better than comparable models that used the same Th2 bindings. In summary, the LASSIM toolbox opens the door to a new type of model-based data analysis that combines the strengths of reliable mechanistic models with truly systems-level data. We demonstrate the power of this approach by inferring a mechanistically motivated, genome-wide model of the Th2 transcription regulatory system, which plays an important role in several immune related diseases.