Mapping the Immune Cell Microenvironment with Spatial Profiling in Muscle Tissue Injected with the Venom of Daboia russelii.

Pathological and inflammatory events in muscle after the injection of snake venoms vary in different regions of the affected tissue and at different time intervals. In order to study such heterogeneity in the immune cell microenvironment, a murine model of muscle necrosis based on the injection of the venom of Daboia russelii was used. Histological and immunohistochemical methods were utilized to identify areas in muscle tissue with a different extent of muscle cell damage, based on the presence of hypercontracted muscle cells, a landmark of necrosis, and on the immunostaining for desmin. A gradient of inflammatory cells (neutrophils and macrophages) was observed from heavily necrotic areas to less damaged and non-necrotic areas. GeoMx® Digital Spatial Profiler (NanoString, Seattle, WA, USA) was used for assessing the presence of markers of various immune cells by comparing high-desmin (nondamaged) and low-desmin (damaged) regions of muscle. Markers of monocytes, macrophages, M2 macrophages, dendritic cells, neutrophils, leukocyte adhesion and migration markers, and hematopoietic precursor cells showed higher levels in low-desmin regions, especially in samples collected 24 hr after venom injection, whereas several markers of lymphocytes did not. Moreover, apoptosis (BAD) and extracellular matrix (fibronectin) markers were also increased in low-desmin regions. Our findings reveal a hitherto-unknown picture of immune cell microheterogeneity in venom-injected muscle which greatly depends on the extent of muscle cell damage and the time lapse after venom injection.

Boamente: A Natural Language Processing-Based Digital Phenotyping Tool for Smart Monitoring of Suicidal Ideation.

People at risk of suicide tend to be isolated and cannot share their thoughts. For this reason, suicidal ideation monitoring becomes a hard task. Therefore, people at risk of suicide need to be monitored in a manner capable of identifying if and when they have a suicidal ideation, enabling professionals to perform timely interventions. This study aimed to develop the Boamente tool, a solution that collects textual data from users' smartphones and identifies the existence of suicidal ideation. The solution has a virtual keyboard mobile application that passively collects user texts and sends them to a web platform to be processed. The platform classifies texts using natural language processing and a deep learning model to recognize suicidal ideation, and the results are presented to mental health professionals in dashboards. Text classification for sentiment analysis was implemented with different machine/deep learning algorithms. A validation study was conducted to identify the model with the best performance results. The BERTimbau Large model performed better, reaching a recall of 0.953 (accuracy: 0.955; precision: 0.961; F-score: 0.954; AUC: 0.954). The proposed tool demonstrated an ability to identify suicidal ideation from user texts, which enabled it to be experimented with in studies with professionals and their patients.