98%
921
2 minutes
20
Imaging-based spatial-omics advances biomedical discoveries with subcellular resolution and high sensitivity, but accurately identifying signal spots from diverse images remains challenging. We develop U-FISH, a deep learning method that enhances images for consistent spot detection across various spatial-omics data. We establish a comprehensive FISH image dataset from seven spatial-omics methods. Benchmark analysis shows U-FISH has superior accuracy and generalizability compared to existing methods and can effectively decode 3D FISH data. U-FISH is the first spot detection software integrated with large language models, as demonstrated in AI-assisted diagnostics. Our study provides a valuable tool for spatial-omics analysis and diagnostics.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12400573 | PMC |
http://dx.doi.org/10.1186/s13059-025-03736-x | DOI Listing |
Genome Biol
September 2025
Faculty of Life and Health Sciences, Shenzhen University of Advanced Technology, 518107, Shenzhen, China.
Imaging-based spatial-omics advances biomedical discoveries with subcellular resolution and high sensitivity, but accurately identifying signal spots from diverse images remains challenging. We develop U-FISH, a deep learning method that enhances images for consistent spot detection across various spatial-omics data. We establish a comprehensive FISH image dataset from seven spatial-omics methods.
View Article and Find Full Text PDFScience
August 2025
State Key Laboratory of Genome and Multi-omics Technologies, BGI Research, Shenzhen, China.
Single-cell sequencing technologies have advanced our understanding of cellular heterogeneity and biological complexity. However, existing methods face limitations in throughput, capture uniformity, cell size flexibility, and technical extensibility. We present Stereo-cell, a spatial enhanced-resolution single-cell sequencing platform based on high-density DNA nanoball (DNB)-patterned arrays, which enables scalable and unbiased cell capture at a wide input range and supports high-fidelity transcriptome profiling.
View Article and Find Full Text PDFTrends Genet
June 2025
Department of Molecular and Integrative Physiology and Institute of Gerontology, University of Michigan Medical School, Ann Arbor, MI, USA. Electronic address:
Spatial transcriptomics (ST) enables systematic profiling of whole-transcriptome gene expression in tissues while preserving spatial context. Recent advances in sequencing- and imaging-based ST technologies have ushered in the era of microscopic-resolution ST (μST), allowing transcriptome mapping at cellular and even subcellular scales with unprecedented precision. Despite these advances, μST faces substantial challenges, including sparse transcript discovery per submicron (or micron)-sized spatial units and data fragmentation across platforms, hindering integration and analysis.
View Article and Find Full Text PDFNat Commun
May 2025
Center for Mass Spectrometry and Optical Spectroscopy (CeMOS), Technische Hochschule Mannheim, Mannheim, Germany.
In spatial'omics, highly confident molecular identifications are indispensable for the investigation of complex biology and for spatial biomarker discovery. However, current mass spectrometry imaging (MSI)-based spatial 'omics must compromise between data acquisition speed and biochemical profiling depth. Here, we introduce fast, label-free quantum cascade laser mid-infrared imaging microscopy (QCL-MIR imaging) to guide MSI to high-interest tissue regions as small as kidney glomeruli, cultured multicellular spheroid cores or single motor neurons.
View Article and Find Full Text PDFbioRxiv
February 2025
Department of Molecular & Integrative Physiology, University of Michigan.
Sequencing-based spatial transcriptomics (sST) enables transcriptome-wide gene expression mapping but falls short of reaching the optical resolution (200-300 nm) of imaging-based methods. Here, we present Seq-Scope-X (Seq-Scope-eXpanded), which empowers submicrometer-resolution Seq-Scope with tissue expansion to surpass this limitation. By physically enlarging tissues, Seq-Scope-X minimizes transcript diffusion effects and increases spatial feature density by an additional order of magnitude.
View Article and Find Full Text PDF