Peptide-based drug discovery through artificial intelligence: towards an autonomous design of therapeutic peptides.

With their diverse biological activities, peptides are promising candidates for therapeutic applications, showing antimicrobial, antitumour and hormonal signalling capabilities. Despite their advantages, therapeutic peptides face challenges such as short half-life, limited oral bioavailability and susceptibility to plasma degradation. The rise of computational tools and artificial intelligence (AI) in peptide research has spurred the development of advanced methodologies and databases that are pivotal in the exploration of these complex macromolecules. This perspective delves into integrating AI in peptide development, encompassing classifier methods, predictive systems and the avant-garde design facilitated by deep-generative models like generative adversarial networks and variational autoencoders. There are still challenges, such as the need for processing optimization and careful validation of predictive models. This work outlines traditional strategies for machine learning model construction and training techniques and proposes a comprehensive AI-assisted peptide design and validation pipeline. The evolving landscape of peptide design using AI is emphasized, showcasing the practicality of these methods in expediting the development and discovery of novel peptides within the context of peptide-based drug discovery.

The role of machine learning in health policies during the COVID-19 pandemic and in long COVID management.

The ongoing COVID-19 pandemic is arguably one of the most challenging health crises in modern times. The development of effective strategies to control the spread of SARS-CoV-2 were major goals for governments and policy makers. Mathematical modeling and machine learning emerged as potent tools to guide and optimize the different control measures. This review briefly summarizes the SARS-CoV-2 pandemic evolution during the first 3 years. It details the main public health challenges focusing on the contribution of mathematical modeling to design and guide government action plans and spread mitigation interventions of SARS-CoV-2. Next describes the application of machine learning methods in a series of study cases, including COVID-19 clinical diagnosis, the analysis of epidemiological variables, and drug discovery by protein engineering techniques. Lastly, it explores the use of machine learning tools for investigating long COVID, by identifying patterns and relationships of symptoms, predicting risk indicators, and enabling early evaluation of COVID-19 sequelae.

Role of Tonsillar Chronic Inflammation and Commensal Bacteria in the Pathogenesis of Pediatric OSA.

Immune responses at the boundary between the host and the world beyond are complex and mucosal tissue homeostasis relies on them. Obstructive sleep apnea (OSA) is a syndrome suffered by children with hypertrophied tonsils. We have previously demonstrated that these tonsils present a defective regulatory B cell (Breg) compartment. Here, we extend those findings by uncovering the crucial role of resident pro-inflammatory B and T cells in sustaining tonsillar hypertrophy and hyperplasia by producing TNFα and IL17, respectively, in ex vivo cultures. Additionally, we detected prominent levels of expression of CD1d by tonsillar stratified as well as reticular epithelium, which have not previously been reported. Furthermore, we evidenced the hypertrophy of germinal centers (GC) and the general hyperplasia of B lymphocytes within the tissue and the lumen of the crypts. Of note, such B cells resulted mainly (IgG/IgM)+ cells, with some IgA+ cells located marginally in the follicles. Finally, by combining bacterial culture from the tonsillar core and subsequent identification of the respective isolates, we determined the most prevalent species within the cohort of OSA patients. Although the isolated species are considered normal oropharyngeal commensals in children, we confirmed their capacity to breach the epithelial barrier. Our work sheds light on the pathological mechanism underlying OSA, highlighting the relevance taken by the host immune system when defining infection versus colonization, and opening alternatives of treatment.

Characterization of tonsillar IL10 secreting B cells and their role in the pathophysiology of tonsillar hypertrophy.

The comprehension of unconventional immune functions of tonsillar B cells, their role in tolerance induction and protective immune responses, is crucial to unveil the dynamic interactions of the upper aero digestive tract with polymicrobial commensal flora and pathogens, in health and disease. Here, we describe the kinetics of IL10 intracellular expression and compare it with that of cytokines known to be produced by tonsillar B cells. Additionally, we detected a relevant proportion of IL17-expressing tonsillar B cells, which has not previously been reported. We immunophenotyped tonsillar IL10-expressing B cells (B10) and observed IL10 production in activated B cells at every developmental stage. Finally, we identified a relationship between decreased B10 percentages, increased proportion of the germinal centre (GC) population and hypertrophied tonsils (HT). Our findings provide greater insight into the role of B10 in GC reactions and characterized their involvement in the pathogenesis of tonsillar dysfunction.