Uncertainty-Aware Interpretable Deep Learning for Slum Mapping and Monitoring

Over a billion people live in slums, with poor sanitation, education, property rights and working conditions having a direct impact on current residents and future generations. Slum mapping is one of the key problems concerning slums. Policymakers need to delineate slum settlements to make informed decisions about infrastructure development and allocation of aid. A wide variety of machine learning and deep learning methods have been applied to multispectral satellite images to map slums with outstanding performance. Since the physical and visual manifestation of slums significantly varies with geographical region and comprehensive slum maps are rare, it is important to quantify the uncertainty of predictions for reliable and confident application of models to downstream tasks. In this study, we train a U-Net model with Monte Carlo Dropout (MCD) on 13-band Sentinel-2 images, allowing us to calculate pixelwise uncertainty in the predictions. The obtained outcomes show that the proposed model outperforms the previous state-of-the-art model, having both higher AUPRC and lower uncertainty when tested on unseen geographical regions of Mumbai using the regional testing framework introduced in this study. We also use SHapley Additive exPlanations (SHAP) values to investigate how the different features contribute to our model’s predictions which indicate a certain shortwave infrared image band is a powerful feature for determining the locations of slums within images. With our results, we demonstrate the usefulness of including an uncertainty quantification approach in detecting slum area changes over time.

Structure-guided design of multi-epitopes vaccine against variants of concern (VOCs) of SARS-CoV-2 and validation through In silico cloning and immune simulations.

Severe Acute Respiratory Syndrome Corovirus2 (SARS-CoV-2) has been determined to be the cause of the current pandemic. Typical symptoms of patient having COVID-19 are fever, runny nose, cough (dry or not) and dyspnea. Several vaccines are available in markets that are tackling current pandemic. Many different strains of SAR-CoV-2 have been evolved with the passage of time. The emergence of VOCs particularly the B.1.351 ("South African") variant of SARS-CoV-2 has been reported to be more resistant than other SARS-CoV-2 strains to the current vaccines. Thus, the current research is focused to design multi-epitope subunit Vaccine (MEV) using structural vaccinology techniques. As a result, the designed MEV exhibit antigenic properties and possess therapeutic features that can trigger an immunological response against COVID-19. Furthermore, validation of the MEV using immune simulation and in silico cloning revealed that the proposed vaccine candidate effectively triggered the immune response. Conclusively, the developed MEV needs further wet lab exploration and could be a viable vaccine to manage and prevent COVID-19.

ERS International Congress 2020: highlights from the Epidemiology and Environment Assembly.

In this article, early career members of the Epidemiology and Environment Assembly of the European Respiratory Society (ERS) summarise a selection of five sessions from the ERS 2020 Virtual International Congress. The topics covered include risk factors for chronic respiratory diseases over the life course, from early life origins to occupational exposures in adulthood, and the interplay between these risk factors, including gene-environment interactions. Novel results were also presented on smoking prevention and potential risks of vaping. Finally, the challenges and opportunities for epidemiological and environmental research brought by the coronavirus disease 2019 (COVID-19) pandemic were a major topic of this year's congress.