Asthma is a heterogeneous disease in which there is a differential response to asthma treatments. This heterogeneity needs to be evaluated so that a personalized management approach can be provided. We stratified patients with moderate-to-severe asthma based on clinicophysiologic parameters and performed an omics analysis of sputum. Partition-around-medoids clustering was applied to a training set of 266 asthmatic participants from the European Unbiased Biomarkers for the Prediction of Respiratory Diseases Outcomes (U-BIOPRED) adult cohort using 8 prespecified clinic-physiologic variables. This was repeated in a separate validation set of 152 asthmatic patients. The clusters were compared based on sputum proteomics and transcriptomics data. Four reproducible and stable clusters of asthmatic patients were identified. The training set cluster T1 consists of patients with well-controlled moderate-to-severe asthma, whereas cluster T2 is a group of patients with late-onset severe asthma with a history of smoking and chronic airflow obstruction. Cluster T3 is similar to cluster T2 in terms of chronic airflow obstruction but is composed of nonsmokers. Cluster T4 is predominantly composed of obese female patients with uncontrolled severe asthma with increased exacerbations but with normal lung function. The validation set exhibited similar clusters, demonstrating reproducibility of the classification. There were significant differences in sputum proteomics and transcriptomics between the clusters. The severe asthma clusters (T2, T3, and T4) had higher sputum eosinophilia than cluster T1, with no differences in sputum neutrophil counts and exhaled nitric oxide and serum IgE levels. Clustering based on clinicophysiologic parameters yielded 4 stable and reproducible clusters that associate with different pathobiological pathways.

Omics data are normally high dimensional with large number of molecular features and relatively small number of available samples with clinical labels. The “curse of dimensionality” makes it challenging to train a machine learning model using high dimensional omics data like DNA methylation and gene expression profiles. Here we propose an end-to-end deep learning model called OmiVAE to extract low dimensional features and classify samples from multi-omics data. OmiVAE combines the basic structure of variational autoencoders with a classifier to achieve task-oriented feature extraction and multi-class classification. The training procedure of OmiVAE is comprised of an unsupervised phase and a supervised phase. During the unsupervised phase, a hierarchical cluster structure of samples can be automatically formed without the need for labels. And in the supervised phase, OmiVAE achieved an average accuracy of 97.49% after 10-fold cross-validation among 33 tumour types and normal samples, which shows better performance than existing methods. The integrated model learned from multi-omics datasets outperformed those using only one type of omics data, which indicates that the complementary information from different omics datatypes provides useful insights for biomedical tasks like cancer classification.

The global pandemic of the 2019-nCov requires the evaluation of policy interventions to mitigate future social and economic costs of quarantine measures worldwide. We propose an epidemiological model for forecasting and policy evaluation which incorporates new data in real-time through variational data assimilation. We analyze and discuss infection rates in the UK, US and Italy. We furthermore develop a custom compartmental SIR model fit to variables related to the available data of the pandemic, named SITR model, which allows for more granular inference on infection numbers. We compare and discuss model results which conducts updates as new observations become available. A hybrid data assimilation approach is applied to make results robust to initial conditions and measurement errors in the data. We use the model to conduct inference on infection numbers as well as parameters such as the disease transmissibility rate or the rate of recovery. The parameterisation of the model is parsimonious and extendable, allowing for the incorporation of additional data and parameters of interest. This allows for scalability and the extension of the model to other locations or the adaption of novel data sources.