Publications by authors named "Alos B Diallo"
Over the past century, human lifespan has increased remarkably, yet the inevitability of aging persists. The disparity between biological age, which reflects pathological deterioration and disease, and chronological age, indicative of normal aging, has driven prior research focused on identifying mechanisms that could inform interventions to reverse excessive age-related deterioration and reduce morbidity and mortality. DNA methylation has emerged as an important predictor of age, leading to the development of epigenetic clocks that quantify the extent of pathological deterioration beyond what is typically expected for a given age.
View Article and Find Full Text PDFArticle Synopsis
- Deep learning applied to spatial transcriptomics (ST) helps understand how gene expression relates to tissue structure, allowing for large-scale studies that are more cost-effective compared to traditional methods.
- Most research has focused on improving algorithms, but there’s a lack of understanding about how tissue preparation and imaging quality impact model training, which is crucial for clinical use.
- A new enhanced tissue processing and imaging protocol was developed to improve model performance in predicting gene expression, showing promising results when compared to traditional methods using a study involving colorectal cancer patients.
Article Synopsis
- Spatial transcriptomics technologies are revolutionizing research by enabling the study of cellular and molecular dynamics within tissues, enhancing our understanding of development, disease, and tumor environments.
- Photoaging, caused by sun exposure, affects skin health and is linked to skin cancer, and spatial transcriptomics can provide a reliable method for evaluating its impact and developing new treatments.
- Despite challenges like high costs and patient variability in current technologies, using routine H&E-stained slides in combination with spatial transcriptomics can help analyze gene expression in skin specimens, potentially revealing valuable insights into photoaging and therapeutic efficacy.
Spatial Omics Driven Crossmodal Pretraining Applied to Graph-based Deep Learning for Cancer Pathology Analysis.
Pac Symp Biocomput
January 2024
Graph-based deep learning has shown great promise in cancer histopathology image analysis by contextualizing complex morphology and structure across whole slide images to make high quality downstream outcome predictions (ex: prognostication). These methods rely on informative representations (i.e.
View Article and Find Full Text PDFArticle Synopsis
- Deep learning methods applied to spatial transcriptomics help uncover relationships between gene expression and tissue architecture, especially in diseases, but face challenges due to variability in tissue preparation and small study cohorts.
- This research explores an improved tissue processing workflow using the Visium CytAssist assay to automate staining and optimize imaging, enabling better spatial transcriptomics profiling.
- Results show that the enhanced workflow significantly improves the performance of deep learning models in predicting gene expression compared to traditional manual methods.
Background: Spatial transcriptomics involves studying the spatial organization of gene expression within tissues, offering insights into the molecular diversity of tumors. While spatial gene expression is commonly amalgamated from 1-10 cells across 50-micron spots, recent methods have demonstrated the capability to disaggregate this information at subspot resolution by leveraging both expression and histological patterns. However, elucidating such information from histology alone presents a significant challenge but if solved can better permit spatial molecular analysis at cellular resolution for instances where Visium data is not available, reducing study costs.
View Article and Find Full Text PDF