While gene expression profiling is commonly used to gain an overview of cellular processes, the identification of upstream processes that drive expression changes remains a challenge. To address this issue, we introduce CARNIVAL, a causal network contextualization tool which derives network architectures from gene expression footprints. CARNIVAL (CAusal Reasoning pipeline for Network identification using Integer VALue programming) integrates different sources of prior knowledge including signed and directed protein–protein interactions, transcription factor targets, and pathway signatures. The use of prior knowledge in CARNIVAL enables capturing a broad set of upstream cellular processes and regulators, leading to a higher accuracy when benchmarked against related tools. Implementation as an integer linear programming (ILP) problem guarantees efficient computation. As a case study, we applied CARNIVAL to contextualize signaling networks from gene expression data in IgA nephropathy (IgAN), a condition that can lead to chronic kidney disease. CARNIVAL identified specific signaling pathways and associated mediators dysregulated in IgAN including Wnt and TGF-β, which we subsequently validated experimentally. These results demonstrated how CARNIVAL generates hypotheses on potential upstream alterations that propagate through signaling networks, providing insights into diseases.

Background Drug-induced liver injury (DILI) is a major safety concern characterized by a complex and diverse pathogenesis. In order to identify DILI early in drug development, a better understanding of the injury and models with better predictivity are urgently needed. One approach in this regard are in silico models which aim at predicting the risk of DILI based on the compound structure. However, these models do not yet show sufficient predictive performance or interpretability to be useful for decision making by themselves, the former partially stemming from the underlying problem of labeling the in vivo DILI risk of compounds in a meaningful way for generating machine learning models. Results As part of the Critical Assessment of Massive Data Analysis (CAMDA) “CMap Drug Safety Challenge” 2019 (http://camda2019.bioinf.jku.at), chemical structure-based models were generated using the binarized DILIrank annotations. Support Vector Machine (SVM) and Random Forest (RF) classifiers showed comparable performance to previously published models with a mean balanced accuracy over models generated using 5-fold LOCO-CV inside a 10-fold training scheme of 0.759 ± 0.027 when predicting an external test set. In the models which used predicted protein targets as compound descriptors, we identified the most information-rich proteins which agreed with the mechanisms of action and toxicity of nonsteroidal anti-inflammatory drugs (NSAIDs), one of the most important drug classes causing DILI, stress response via TP53 and biotransformation. In addition, we identified multiple proteins involved in xenobiotic metabolism which could be novel DILI-related off-targets, such as CLK1 and DYRK2. Moreover, we derived potential structural alerts for DILI with high precision, including furan and hydrazine derivatives; however, all derived alerts were present in approved drugs and were over specific indicating the need to consider quantitative variables such as dose. Conclusion Using chemical structure-based descriptors such as structural fingerprints and predicted protein targets, DILI prediction models were built with a predictive performance comparable to previous literature. In addition, we derived insights on proteins and pathways statistically (and potentially causally) linked to DILI from these models and inferred new structural alerts related to this adverse endpoint.