COVID-19, caused by SARS-CoV-2, results in respiratory and cardiopulmonary infections. There is an urgent need to understand not just the pathogenic mechanisms of this disease but also its impact on the physiology of different organs and microbiomes. Multiple studies have reported the effects of COVID-19 on the gastrointestinal microbiota, such as promoting dysbiosis (imbalances in the microbiome) following the disease’s progression. Deconstructing the dynamic changes in microbiome composition that are specifically correlated with COVID-19 patients remains a challenge. Motivated by this problem, we implemented a biomarker discovery pipeline to identify candidate microbes specific to COVID-19. This involved a meta-analysis of large-scale COVID-19 metagenomic data to decipher the impact of COVID-19 on the human gut and respiratory microbiomes. Metagenomic studies of the gut and respiratory microbiomes of COVID-19 patients and of microbiomes from other respiratory diseases with symptoms similar to or overlapping with COVID-19 revealed 1169 and 131 differentially abundant microbes in the human gut and respiratory microbiomes, respectively, that uniquely associate with COVID-19. Furthermore, by utilizing machine learning models (LASSO and XGBoost), we demonstrated the power of microbial features in separating COVID-19 samples from metagenomic samples representing other respiratory diseases and controls (healthy individuals), achieving an overall accuracy of over 80%. Overall, our study provides insights into the microbiome shifts occurring in COVID-19 patients, shining a new light on the compositional changes.
Polyfluoroalkyl substances (PFAS) are persistent chemicals that accumulate in the body and environment. Although recent studies have indicated that PFAS may disrupt kidney function, the underlying mechanisms and overall effects on the organ remain unclear. Therefore, this study aims to elucidate the impact of PFAS on kidney health using machine learning techniques. Utilizing a dataset containing PFAS chemical features and kidney parameters, dimensionality reduction and clustering were performed to identify patterns. Machine learning models, including XGBoost classifier, regressor, and Random Forest regressor, were then developed to predict kidney type from PFAS descriptors, estimate PFAS accumulation in the body, and predict the ratio of glomerular surface area to proximal tubule volume, which indicates kidney filtration efficiency. The kidney type classifier achieved 100% accuracy, confirming that PFAS exposure alters kidney morphology. The PFAS accumulation model attained an R^2 of 1.00, providing a tool to identify at-risk individuals. The ratio prediction model reached an R^2 of 1.00, offering insights into PFAS effects on kidney function. Furthermore, PFAS descriptors and anatomical variables were identified through analyses using feature importance, demonstrating discernible links between PFAS and kidney health, offering further biological significance. Overall, this study can significantly contribute to the current findings on the effect of PFAS while offering machine learning as a contributive tool for similar studies.