Publications by authors named "Gokul Srinivasan"
Article 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.
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 PDFIntraoperative margin analysis is crucial for the successful removal of cutaneous squamous cell carcinomas (cSCC). Artificial intelligence technologies (AI) have previously demonstrated potential for facilitating rapid and complete tumour removal using intraoperative margin assessment for basal cell carcinoma. However, the varied morphologies of cSCC present challenges for AI margin assessment.
View Article and Find Full Text PDFGraph-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 PDFThe advent of spatial transcriptomics technologies has heralded a renaissance in research to advance our understanding of the spatial cellular and transcriptional heterogeneity within tissues. Spatial transcriptomics allows investigation of the interplay between cells, molecular pathways and the surrounding tissue architecture and can help elucidate developmental trajectories, disease pathogenesis, and various niches in the tumor microenvironment. Photoaging is the histological and molecular skin damage resulting from chronic/acute sun exposure and is a major risk factor for skin cancer.
View Article and Find Full Text PDFImportance: Intraoperative margin analysis is crucial for the successful removal of cutaneous squamous cell carcinomas (cSCC). Artificial intelligence technologies (AI) have previously demonstrated potential for facilitating rapid and complete tumor removal using intraoperative margin assessment for basal cell carcinoma. However, the varied morphologies of cSCC present challenges for AI margin assessment.
View Article and Find Full Text PDFThe present study aims at understanding the effects of fuel preheating on engine characteristics of waste animal fat-oil (WAF-O) biodiesel in a single-cylinder CI engine, with the preheating technique proposed as an effective means for enhancing the fuel properties. To understand the effects of the preheated fuel, the WAF-O biodiesel was preheated at 60, 80, 100 and 120 °C and tested along with neat diesel and unheated WAF-O biodiesel. For this purpose, biodiesel was produced from different animal wastes by means of KOH-assisted ethanol-based transesterification, reporting its maximum yield as 96.
View Article and Find Full Text PDFPerovskite types of nanocomposites of BiFeO-GdFeO (BFO-GFO) has been synthesized using sol-gel route for the first time. The nanocomposite powders were characterized by powder X-Ray diffraction (PXRD) to confirm the existence of mixed crystallographic phases. EDX analysis on nanocomposites estimates the composition of individual element present in BFO-GFO matrix.
View Article and Find Full Text PDF