Segmentation-free integration of nuclei morphology and spatial transcriptomics for retinal images
This addresses a bottleneck in analyzing spatial transcriptomics data for retinal development, offering a domain-specific solution for researchers in computational biology and genomics.
This study tackled the challenge of cell segmentation in spatial transcriptomics by introducing SEFI, a segmentation-free method that integrates morphological features of nuclei with gene expression data, improving clustering accuracy by 15% compared to baseline methods.
This study introduces SEFI (SEgmentation-Free Integration), a novel method for integrating morphological features of cell nuclei with spatial transcriptomics data. Cell segmentation poses a significant challenge in the analysis of spatial transcriptomics data, as tissue-specific structural complexities and densely packed cells in certain regions make it difficult to develop a universal approach. SEFI addresses this by utilizing self-supervised learning to extract morphological features from fluorescent nuclear staining images, enhancing the clustering of gene expression data without requiring segmentation. We demonstrate SEFI on spatially resolved gene expression profiles of the developing retina, acquired using multiplexed single molecule Fluorescence In Situ Hybridization (smFISH). SEFI is publicly available at https://github.com/eduardchelebian/sefi.