Search

Introduction: Immune dysregulation plays a major role in cancer progression. The quantification of lymphocytic spatial inflammation may enable spatial system biology, improve understanding of therapeutic resistance, and contribute to prognostic imaging biomarkers., Methods: In this paper, we propose a knowledge-guided deep learning framework to measure the lymphocytic spatial architecture on human H&E tissue, where the fidelity of training labels is maximized through single-cell resolution image registration of H&E to IHC. We demonstrate that such an approach enables pixel-perfect ground-truth labeling of lymphocytes on H&E as measured by IHC. We then experimentally validate our technique in a genetically engineered, immune-compromised Rag2 mouse model, where Rag2 knockout mice lacking mature lymphocytes are used as a negative experimental control. Such experimental validation moves beyond the classical statistical testing of deep learning models and demonstrates feasibility of more rigorous validation strategies that integrate computational science and basic science., Results: Using our developed approach, we automatically annotated more than 111,000 human nuclei (45,611 CD3/CD20 positive lymphocytes) on H&E images to develop our model, which achieved an AUC of 0.78 and 0.71 on internal hold-out testing data and external testing on an independent dataset, respectively. As a measure of the global spatial architecture of the lymphocytic microenvironment, the average structural similarity between predicted lymphocytic density maps and ground truth lymphocytic density maps was 0.86 ± 0.06 on testing data. On experimental mouse model validation, we measured a lymphocytic density of 96.5 ± %1% in a Rag2 +/- control mouse, compared to an average of 16.2 ± %5% in Rag2 -/- immune knockout mice (p<0.0001, ANOVA-test)., Discussion: These results demonstrate that CD3/CD20 positive lymphocytes can be accurately detected and characterized on H&E by deep learning and generalized across species. Collectively, these data suggest that our understanding of complex biological systems may benefit from computationally-derived spatial analysis, as well as integration of computational science and basic science., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Li, Heirman, Rickard, Sotolongo, Castillo, Adanlawo, Everitt, Hodgin, Watts, Janowczyk, Mowery, Barisoni and Lafata.)

Case Study: On May 9th, 2023, a U.S. Border Patrol detained a family of five near Brownsville, TX. During processing, one of the family members, an eight-year-old girl, ADRA, was noted to have sickle cell anemia and a heart disease condition. Five days after they arrived at the Donna Facility, on May 14th, ADRA displayed symptoms, including abdominal pain and fever, and tested positive for Influenza A. She was administered medication and transferred to a designated isolation unit at the Harlingen Border Patrol Station. Despite her deteriorating condition and her mother's urgent requests for medical intervention, there were no documented consultations with an on-call physician or considerations for her transfer to a local hospital. On May 17th, ADRA's health critically declined, marked by multiple visits to the medical unit for vomiting and abdominal pain. An ambulance was dispatched only after ADRA experienced a seizure and became unresponsive, Fig. 1. Her subsequent death was deemed a "preventable tragedy" attributed to systemic failures in the Border Patrol's medical care and decision-making processes in a juvenile care monitor's report. 1 IMPACT: This article adds to the existing literature by: Summarizing the gap in age-specific guidelines for six chronic diseases that occur in children and adolescents held in custody. Identifying the lack of adequate intervention strategies for acute management of chronic diseases for youth held in custody and strategies for improving health equity., (© 2023. The Author(s).)

Gametogenesis requires packaging of the cellular components needed for the next generation. In budding yeast, this process includes degradation of many mitotically stable proteins, followed by their resynthesis. Here, we show that one such case-Superoxide dismutase 1 (Sod1), a protein that commonly aggregates in human ALS patients-is regulated by an integrated set of events, beginning with the formation of pre-meiotic Sod1 aggregates. This is followed by degradation of a subset of the prior Sod1 pool and clearance of Sod1 aggregates. As degradation progresses, Sod1 protein production is transiently blocked during mid-meiotic stages by transcription of an extended and poorly translated SOD1 mRNA isoform, SOD1LUTI. Expression of SOD1LUTI is induced by the Unfolded Protein Response, and it acts to repress canonical SOD1 mRNA expression. SOD1LUTI is no longer expressed following the meiotic divisions, enabling a resurgence of canonical mRNA and synthesis of new Sod1 protein such that gametes inherit a full complement of Sod1 protein. Failure to aggregate and degrade Sod1 results in reduced gamete fitness in the presence of oxidants, highlighting the importance of this regulation. Investigation of Sod1 during yeast gametogenesis, an unusual cellular context in which Sod1 levels are tightly regulated, could shed light on conserved aspects of its aggregation and degradation, with relevance to understanding Sod1's role in human disease., (© 2023 Vander Wende et al.)