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: May 20, 2026

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection

Published on: July 6, 2022

From histology to spatial transcriptomics: establishing a lightweight single-patch baseline.

Hyungyum Jang¹, Hyunsoo Shin², Hawon Lee³

¹Department of Applied Artificial Intelligence, Hansung University, Samseongyo-ro 16-gil 116, Seongbuk-gu, Seoul, 02876, South Korea.

BMC Bioinformatics

|May 19, 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

Impact of an Updated Climate Database on Model Performance and Niche Variability in Species Distribution Modeling.

Ecology and evolution·2026

Same author

Radiation-Induced Skin Toxicity Risk in Breast Cancer Patients With Atopic or Allergic Conditions.

Clinical and experimental allergy : journal of the British Society for Allergy and Clinical Immunology·2026

Same author

A tool based on objective data to identify patients at elevated risk of hospital-onset <i>Staphylococcus aureus</i> bacteremia: a nested case-control study.

Antimicrobial stewardship & healthcare epidemiology : ASHE·2026

Same author

Micro-Texturized and Ultra-Soft Dry Electrode for Motion-Artifact Tolerant and Long-Term Stable Wearable Electrophysiological Monitoring.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

Cold atmospheric plasma degrades methylene blue and shifts bacterial inactivation during photodynamic therapy.

Scientific reports·2026

Same author

The genus <i>Tinginotum</i> Kirkaldy, 1902 (Hemiptera, Miridae, Mirinae) with description of a new species from Vietnam and additional notes on Southeast Asian materials.

ZooKeys·2026

Same journal

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026

Same journal

NAP: an open source pipeline for cross-domain microbiome profiling using Nanopore sequencing-derived amplicon data.

BMC bioinformatics·2026

Same journal

SurvGME: an R package for survival analysis with graphical and measurement error models.

BMC bioinformatics·2026

Same journal

SimMapNet: a Bayesian framework for gene regulatory network inference using gene ontology similarities as external hint.

BMC bioinformatics·2026

Same journal

Dual channel drug-drug interactions extraction based on cross attention.

BMC bioinformatics·2026

Same journal

FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron-sulfur proteins.

BMC bioinformatics·2026

See all related articles

This summary is machine-generated.

This study establishes a baseline for predicting spatial gene expression from single tissue image patches, showing EfficientNet-B0 excels in performance and efficiency. The findings highlight histology

Area of Science:

Computational pathology
Spatial transcriptomics
Bioinformatics

Background:

Predicting spatial gene expression from H&E-stained histology is challenging.
The performance of single-tissue patch models is largely unexplored, hindering evaluation of spatial context benefits.

Purpose of the Study:

Establish a lightweight, efficient, and reproducible baseline for single-patch gene expression prediction.
Provide a standardized foundation for future computational pathology research.
Assess cross-tissue generalizability of single-patch models.

Main Methods:

Trained pre-trained convolutional architectures (EfficientNet, ResNet, DenseNet) on human liver Visium data.
Utilized full fine-tuning and morphology-preserving augmentation.

Keywords:

Bioinformatics Computational pathology Deep learning EfficientNet H& E histology Spatial transcriptomics

More Related Videos

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

Related Experiment Videos

Last Updated: May 20, 2026

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection

Spatial Profiling of Protein and RNA Expression in Tissue: An Approach to Fine-Tune Virtual Microdissection

Published on: July 6, 2022

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 on an independent breast cancer spatial transcriptomics dataset.

Main Results:

EfficientNet-B0 achieved a PCC of 0.310 for highly expressed genes in liver tissue, outperforming prior single-patch methods.
EfficientNet-B0 predicted 50 genes with PCC ≥ 0.30 using significantly fewer parameters than a ResNet-50 baseline.
Demonstrated stable cross-tissue generalization on breast cancer data, with EfficientNet-B0 achieving top performance.

Conclusions:

The study provides a robust baseline for single-patch gene expression prediction.
Model performance is driven by spatial organization in H&E histology, not just transcript abundance.
This work offers a reference for evaluating future spatial transcriptomics models.