Discovery of drug-omics associations in type 2 diabetes with generative deep-learning models.

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.

Machine learning and deep learning applications in microbiome research.

The many microbial communities around us form interactive and dynamic ecosystems called microbiomes. Though concealed from the naked eye, microbiomes govern and influence macroscopic systems including human health, plant resilience, and biogeochemical cycling. Such feats have attracted interest from the scientific community, which has recently turned to machine learning and deep learning methods to interrogate the microbiome and elucidate the relationships between its composition and function. Here, we provide an overview of how the latest microbiome studies harness the inductive prowess of artificial intelligence methods. We start by highlighting that microbiome data - being compositional, sparse, and high-dimensional - necessitates special treatment. We then introduce traditional and novel methods and discuss their strengths and applications. Finally, we discuss the outlook of machine and deep learning pipelines, focusing on bottlenecks and considerations to address them.

Diferencia de la incidencia de los efectos adversos, entre la primera y la segunda dosis de la vacuna Pfizer/Biontech en el personal de salud / Difference in the incidence of adverse effects between the first and second doses of thr Pfizer/Biontech vaccine in health workers

Objetivo: comparar la incidencia de los efectos adversos entre la primera y segunda dosis de la vacuna Pfizer/BioNTech en personal de salud. Material y métodos: estudio transversal analítico en trabajadores de salud que recibieron la primera y segunda dosis de la vacuna COVID-19 de Pfizer/BioNTech. La muestra fue de 540 pacientes. la comparación del promedio de síntomas en la primera y segunda dosis se realizó con la prueba de Wilcoxon para dos poblaciones. Resultados: los síntomas locales fueron estadísticamente diferentes entre la primera y la segunda dosis (Wilcoxon = 2,78, p = 0,005). El promedio de síntomas sistémicos en la primera dosis fue estadísticamente superior en los pacientes con antecedente de COVID-19 que en aquellos que no lo presentaron (Mann-Withney = 4,36, p = 0,006). Conclusión: hubo diferencia en la sintomatología local, siendo mayor en la primera dosis. Los pacientes con antecedente de COVID-19 tienen una mayor expresión de síntomas sistémicos tras la primera dosis.