Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 18, 2026

Comprehensive Spatial Profiling of Species-agnostic Transcriptomes via Stereo-seq

Comprehensive Spatial Profiling of Species-agnostic Transcriptomes via Stereo-seq

Published on: October 31, 2025

SpatialCell AI achieves reference-free single-cell resolution from spot-based spatial transcriptomics through

Abdalla Elbialy¹

¹SpatialCell AI, LLC, Oak Lawn, IL, USA. aelbialy@spatialcell.tech.

Scientific Reports

|June 16, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Unveiling racial disparities in prostate cancer using an integrative genomic and transcriptomic analysis.

Cell insight·2025

Same author

Patient-Derived Conditionally Reprogrammed Cells in Prostate Cancer Research.

Cells·2024

Same author

Antioxidants and azd0156 Rescue Inflammatory Response in Autophagy-Impaired Macrophages.

International journal of molecular sciences·2024

Same author

Induction of endoplasmic reticulum stress markers in an acromegaly model.

Journal of cellular biochemistry·2022

Same author

In vivo autophagy quantification: Measuring LC3 and P62 puncta in 3D image system from zebrafish larvae.

Journal of cellular biochemistry·2021

Same author

Ageing genetic signature of hypersomatotropism.

Open biology·2021

SpatialCell AI is a novel framework for spatial transcriptomics that provides per-cell expression data without needing external references or dataset-specific training. It outperforms existing methods, especially on high-resolution Visium HD data.

Area of Science:

Genomics
Computational Biology
Bioinformatics

Background:

Spatial transcriptomics platforms like 10x Visium offer whole-transcriptome data but at spot-level resolution, aggregating signals from multiple cells.
Current deconvolution methods often rely on external single-cell RNA sequencing (scRNA-seq) references or require dataset-specific training for morphology-guided approaches.

Purpose of the Study:

To introduce SpatialCell AI, a groundbreaking framework for spatial transcriptomics.
To enable reference-free, training-free integration of expression data with per-cell output granularity.
To overcome limitations of existing computational deconvolution methods.

Main Methods:

Developed SpatialCell AI, a novel computational framework for spatial transcriptomics analysis.

Keywords:

Cell segmentation Computational biology Morphological features Single-cell analysis Spatial transcriptomics Validation framework

Related Experiment Videos

Last Updated: Jun 18, 2026

Comprehensive Spatial Profiling of Species-agnostic Transcriptomes via Stereo-seq

Comprehensive Spatial Profiling of Species-agnostic Transcriptomes via Stereo-seq

Published on: October 31, 2025

Validated the framework on a colorectal cancer sample using 10x Visium (55 µm), Visium HD (8 µm and 16 µm), and Xenium (single-cell resolution) platforms.

Compared SpatialCell AI against existing morphology-guided methods (iStar, SpaHDmap) and raw baseline data.

Main Results:

SpatialCell AI achieved the highest expression correlation (r=0.791) against a single-cell reference on Visium HD 8 µm input among all tested methods.
SpatialCell AI HD variants led in the majority of six distribution-based validation metrics on a 408-gene panel.
A head-to-head comparison showed SpatialCell AI's training-free approach improves with finer input resolution, outperforming trained morphology-guided methods on Visium HD.

Conclusions:

SpatialCell AI offers a significant advancement in spatial transcriptomics analysis, providing per-cell resolution from spot-level data.
The framework demonstrates superior performance, particularly on high-resolution Visium HD data, outperforming existing computational methods.
SpatialCell AI transforms spot-based transcriptomic data into spatially resolved, per-cell expression profiles, a capability not offered by raw spot measurements.