BackgroundAnalysis of muscle biopsies allowed to characterize the pathophysiological changes of Duchenne and Becker muscular dystrophies (D/BMD) leading to the clinical phenotype. Muscle tissue is often investigated during interventional dose finding studies to show in situ proof of concept and pharmacodynamics effect of the tested drug. Less invasive readouts are needed to objectively monitor patients' health status, muscle quality, and response to treatment. The identification of serum biomarkers correlating with clinical function and able to anticipate functional scales is particularly needed for personalized patient management and to support drug development programs.MethodsA large‐scale proteomic approach was used to identify serum biomarkers describing pathophysiological changes (e.g. loss of muscle mass), association with clinical function, prediction of disease milestones, association with in vivo 31P magnetic resonance spectroscopy data and dystrophin levels in muscles. Cross‐sectional comparisons were performed to compare DMD patients, BMD patients, and healthy controls. A group of DMD patients was followed up for a median of 4.4 years to allow monitoring of individual disease trajectories based on yearly visits.ResultsCross‐sectional comparison enabled to identify 10 proteins discriminating between healthy controls, DMD and BMD patients. Several proteins (285) were able to separate DMD from healthy, while 121 proteins differentiated between BMD and DMD; only 13 proteins separated BMD and healthy individuals. The concentration of specific proteins in serum was significantly associated with patients' performance (e.g. BMP6 serum levels and elbow flexion) or dystrophin levels (e.g. TIMP2) in BMD patients. Analysis of longitudinal trajectories allowed to identify 427 proteins affected over time indicating loss of muscle mass, replacement of muscle by adipose tissue, and cardiac involvement. Over‐representation analysis of longitudinal data allowed to highlight proteins that could be used as pharmacodynamic biomarkers for drugs currently in clinical development.ConclusionsSerum proteomic analysis allowed to not only discriminate among DMD, BMD, and healthy subjects, but it enabled to detect significant associations with clinical function, dystrophin levels, and disease progression.

Compounds that are candidates for drug repurposing can be ranked by leveraging knowledge available in the biomedical literature and databases. This knowledge, spread across a variety of sources, can be integrated within a knowledge graph, which thereby comprehensively describes known relationships between biomedical concepts, such as drugs, diseases, genes, etc. Our work uses the semantic information between drug and disease concepts as features, which are extracted from an existing knowledge graph that integrates 200 different biological knowledge sources. RepoDB, a standard drug repurposing database which describes drug-disease combinations that were approved or that failed in clinical trials, is used to train a random forest classifier. The 10-times repeated 10-fold cross-validation performance of the classifier achieves a mean area under the receiver operating characteristic curve (AUC) of 92.2%. We apply the classifier to prioritize 21 preclinical drug repurposing candidates that have been suggested for Autosomal Dominant Polycystic Kidney Disease (ADPKD). Mozavaptan, a vasopressin V2 receptor antagonist is predicted to be the drug most likely to be approved after a clinical trial, and belongs to the same drug class as tolvaptan, the only treatment for ADPKD that is currently approved. We conclude that semantic properties of concepts in a knowledge graph can be exploited to prioritize drug repurposing candidates for testing in clinical trials.

Background and Aims Protein profiling in patients with inflammatory bowel diseases (IBD) for diagnostic and therapeutic purposes is underexplored in IBD. This study analysed the association between phenotype, genotype and the plasma proteome in IBD. Methods Ninety-two (92) inflammation-related proteins were quantified in plasma of 1,028 patients with IBD (567 Crohn’s disease [CD]; 461 ulcerative colitis [UC]) and 148 healthy individuals to assess protein-phenotype associations. Corresponding whole-exome sequencing and global screening array data of 919 patients with IBD were included to analyse the effect of genetics on protein levels (protein quantitative trait loci (pQTL) analysis). Intestinal mucosal RNA sequencing and fecal metagenomic data were used for complementary analyses. Results Thirty-two (32) proteins were differentially abundant between IBD and healthy individuals, of which 22 proteins independent of active inflammation. Sixty-nine (69) proteins were associated with 15 demographic and clinical factors. Fibroblast growth factor-19 levels were decreased in CD patients with ileal disease or a history of ileocecal resection. Thirteen novel cis-pQTLs were identified and 10 replicated from previous studies. One trans-pQTL of the fucosyltransferase 2 (FUT2) gene (rs602662) and two independent cis-pQTLs of C-C motif chemokine 25 (CCL25) affected plasma CCL25 levels. Intestinal gene expression data revealed an overlapping cis-expression (e)QTL-variant (rs3745387) of the CCL25 gene. The FUT2 rs602662 trans-pQTL was associated with reduced abundances of fecal butyrate-producing bacteria. Conclusions This study shows that genotype and multiple disease phenotypes strongly associate with the plasma inflammatory proteome in IBD and identifies disease-associated pathways that may help to improve disease management in the future.

Deep generative models, such as variational autoencoders (VAE), have gained increasing attention in computational biology due to their ability to capture complex data manifolds which subsequently can be used to achieve better performance in downstream tasks, such as cancer type prediction or subtyping of cancer. However, these models are difficult to train due to the large number of hyperparameters that need to be tuned. To get a better understanding of the importance of the different hyperparameters, we examined six different VAE models when trained on TCGA transcriptomics data and evaluated on the downstream task of cluster agreement with cancer subtypes. We studied the effect of the latent space dimensionality, learning rate, optimizer and initialization on the quality of subsequent clustering of the TCGA samples. We found β-TCVAE and DIP-VAE to have a sensitive to hyperparameters selection. Based on these experiments, we derived recommendations for selecting the different hyperparameters settings. In addition, we examined whether the learned latent spaces capture biologically relevant information. Hereto, we correlated the different representations with various data characteristics such as age, days to metastasis, immune infiltration, and mutation signatures. We found that for all models the latent factors, in general, do not uniquely correlate with one of the data characteristics even for models specifically designed for disentanglement