The application of multiple omics technologies in biomedical cohorts has the potential to reveal patient-level disease characteristics and individualized response to treatment. However, the scale and heterogeneous nature of multi-modal data makes integration and inference a non-trivial task. We developed a deep-learning-based framework, multi-omics variational autoencoders (MOVE), to integrate such data and applied it to a cohort of 789 people with newly diagnosed type 2 diabetes with deep multi-omics phenotyping from the DIRECT consortium. Using in silico perturbations, we identified drug–omics associations across the multi-modal datasets for the 20 most prevalent drugs given to people with type 2 diabetes with substantially higher sensitivity than univariate statistical tests. From these, we among others, identified novel associations between metformin and the gut microbiota as well as opposite molecular responses for the two statins, simvastatin and atorvastatin. We used the associations to quantify drug–drug similarities, assess the degree of polypharmacy and conclude that drug effects are distributed across the multi-omics modalities.

Modern biomarker and translational research as well as personalized health care studies rely heavily on powerful omics’ technologies, including metabolomics and lipidomics. However, to translate metabolomics and lipidomics discoveries into a high-throughput clinical setting, standardization is of utmost importance. Here, we compared and benchmarked a quantitative lipidomics platform. The employed Lipidyzer platform is based on lipid class separation by means of differential mobility spectrometry with subsequent multiple reaction monitoring. Quantitation is achieved by the use of 54 deuterated internal standards and an automated informatics approach. We investigated the platform performance across nine laboratories using NIST SRM 1950–Metabolites in Frozen Human Plasma, and three NIST Candidate Reference Materials 8231–Frozen Human Plasma Suite for Metabolomics (high triglyceride, diabetic, and African-American plasma). In addition, we comparatively analyzed 59 plasma samples from individuals with familial hypercholesterolemia from a clinical cohort study. We provide evidence that the more practical methyl-tert-butyl ether extraction outperforms the classic Bligh and Dyer approach and compare our results with two previously published ring trials. In summary, we present standardized lipidomics protocols, allowing for the highly reproducible analysis of several hundred human plasma lipids, and present detailed molecular information for potentially disease relevant and ethnicity-related materials.

Non-alcoholic fatty liver disease (NAFLD) is highly prevalent and causes serious health complications in individuals with and without type 2 diabetes (T2D). Early diagnosis of NAFLD is important, as this can help prevent irreversible damage to the liver and, ultimately, hepatocellular carcinomas. We sought to expand etiological understanding and develop a diagnostic tool for NAFLD using machine learning. We utilized the baseline data from IMI DIRECT, a multicenter prospective cohort study of 3,029 European-ancestry adults recently diagnosed with T2D (n = 795) or at high risk of developing the disease (n = 2,234). Multi-omics (genetic, transcriptomic, proteomic, and metabolomic) and clinical (liver enzymes and other serological biomarkers, anthropometry, measures of beta-cell function, insulin sensitivity, and lifestyle) data comprised the key input variables. The models were trained on MRI-image-derived liver fat content (<5% or ≥5%) available for 1,514 participants. We applied LASSO (least absolute shrinkage and selection operator) to select features from the different layers of omics data and random forest analysis to develop the models. The prediction models included clinical and omics variables separately or in combination. A model including all omics and clinical variables yielded a cross-validated receiver operating characteristic area under the curve (ROCAUC) of 0.84 (95% CI 0.82, 0.86; p < 0.001), which compared with a ROCAUC of 0.82 (95% CI 0.81, 0.83; p < 0.001) for a model including 9 clinically accessible variables. The IMI DIRECT prediction models outperformed existing noninvasive NAFLD prediction tools. One limitation is that these analyses were performed in adults of European ancestry residing in northern Europe, and it is unknown how well these findings will translate to people of other ancestries and exposed to environmental risk factors that differ from those of the present cohort. Another key limitation of this study is that the prediction was done on a binary outcome of liver fat quantity (<5% or ≥5%) rather than a continuous one. In this study, we developed several models with different combinations of clinical and omics data and identified biological features that appear to be associated with liver fat accumulation. In general, the clinical variables showed better prediction ability than the complex omics variables. However, the combination of omics and clinical variables yielded the highest accuracy. We have incorporated the developed clinical models into a web interface (see: https://www.predictliverfat.org/) and made it available to the community. ClinicalTrials.gov NCT03814915.

The presentation and underlying pathophysiology of type 2 diabetes (T2D) is complex and heterogeneous. Recent studies attempted to stratify T2D into distinct subgroups using data-driven approaches, but their clinical utility may be limited if categorical representations of complex phenotypes are suboptimal.

The interaction between floral oil secreting plants and oil-collecting bees is one of the most specialized of all pollination mutualisms. Yet, the specific stimuli used by the bees to locate their host flowers have remained elusive. This study identifies diacetin, a volatile acetylated glycerol, as a floral signal compound shared by unrelated oil plants from around the globe. Electrophysiological measurements of antennae and behavioural assays identified diacetin as the key volatile used by oil-collecting bees to locate their host flowers. Furthermore, electrophysiological measurements indicate that only oil-collecting bees are capable of detecting diacetin. The structural and obvious biosynthetic similarity between diacetin and associated floral oils make it a reliable cue for oil-collecting bees. It is easily perceived by oil bees, but can’t be detected by other potential pollinators. Therefore, diacetin represents the first demonstrated private communication channel in a pollination system.