canSAR (http://cansar.icr.ac.uk) is the largest, public, freely available, integrative translational research and drug discovery knowledgebase for oncology. canSAR integrates vast multidisciplinary data from across genomic, protein, pharmacological, drug and chemical data with structural biology, protein networks and more. It also provides unique data, curation and annotation and crucially, AI-informed target assessment for drug discovery. canSAR is widely used internationally by academia and industry. Here we describe significant developments and enhancements to the data, web interface and infrastructure of canSAR in the form of the new implementation of the system: canSARblack. We demonstrate new functionality in aiding translation hypothesis generation and experimental design, and show how canSAR can be adapted and utilised outside oncology.

The aryl hydrocarbon receptor (AhR) is a nuclear receptor regulating a wide range of biological and toxicological effects. Metabolites of L-tryptophan are able to bind and activate AhR, providing a link between tryptophan catabolism and a novel mechanism of protective tolerance, referred to as "disease tolerance". The notion that pharmacologic modulation of genes associated with endotoxin tolerance would be beneficial in clinical settings dominated by acute hyperinflammatory responses to infection thrusts AhR into the limelight as an interesting druggable target. Combining homology modeling, docking studies, and molecular dynamic simulations with mutagenesis experiments and gene profiling, in this work we report that 2,3,7,8-tetrachlorodibenzo-p-dioxin (TCDD) and two different L-tryptophan metabolites, namely L-Kynurenine and FICZ (6-formylindolo[3,2-b]carbazole), are able to bind to mAhR, exploiting different key interactions with distinct set of fingerprint residues. As a result, they stabilize different conformations of mAhR that, in turn, selectively regulate downstream signaling and transcription of specific target genes. Collectively, these results open new avenues for the design and development of selective AhR modulators that, by targeting specific receptor conformations associated with specific AhR functions, may offer novel therapeutic opportunities in infectious diseases and other morbidity that may be associated with the receptor.

AbstractcanSAR (http://cansar.icr.ac.uk) is a public, freely available, integrative translational research and drug discovery knowlegebase. canSAR informs researchers to help solve key bottlenecks in cancer translation and drug discovery. It integrates genomic, protein, pharmacological, drug and chemical data with structural biology, protein networks and unique, comprehensive and orthogonal ‘druggability’ assessments. canSAR is widely used internationally by academia and industry. Here we describe major enhancements to canSAR including new and expanded data. We also describe the first components of canSARblack—an advanced, responsive, multi-device compatible redesign of canSAR with a question-led interface.

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.