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

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

Modeling attention and binding in the brain through bidirectional recurrent gating.

Nature communications·2026

Same author

Brain-wide representations of prior information in mouse decision-making.

Nature·2025

Same author

TissueFormer: a neural network for labeling tissue from grouped single-cell RNA profiles.

bioRxiv : the preprint server for biology·2025

Same author

Encoding innate ability through a genomic bottleneck.

Proceedings of the National Academy of Sciences of the United States of America·2024

Same author

A role for cortical interneurons as adversarial discriminators.

PLoS computational biology·2023

Same author

Catalyzing next-generation Artificial Intelligence through NeuroAI.

Nature communications·2023

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

Search research articles

Related Experiment Video

Updated: Jun 6, 2026

In Vitro Cultivation Techniques for Modeling Liver Organogenesis, Building Assembloids, and Designing Synthetic Tissues using Human Cell Lines

In Vitro Cultivation Techniques for Modeling Liver Organogenesis, Building Assembloids, and Designing Synthetic Tissues using Human Cell Lines

Published on: April 18, 2025

Tissueformer: extending single-cell foundation models to predict population-level phenotypes.

Ari S Benjamin¹, Anthony Zador²

¹Cold Spring Harbor Laboratory, Cold Spring Harbor, NY, 11724, USA. benjami@cshl.edu.

BMC Bioinformatics

|June 4, 2026

Summary

This summary is machine-generated.

TissueFormer, a novel Transformer model, analyzes groups of single-cell RNA profiles to predict sample-level traits like disease severity and brain region identity, outperforming existing methods.

Keywords:

AI for biology Brain annotation Sample-level diagnostics Single-cell foundation models Spatial transcriptomics Tissue labeling

More Related Videos

Modeling Breast Cancer in Human Breast Tissue using a Microphysiological System

Modeling Breast Cancer in Human Breast Tissue using a Microphysiological System

Published on: April 23, 2021

In Vivo Modeling of the Morbid Human Genome using Danio rerio

In Vivo Modeling of the Morbid Human Genome using Danio rerio

Published on: August 24, 2013

Related Experiment Videos

Last Updated: Jun 6, 2026

In Vitro Cultivation Techniques for Modeling Liver Organogenesis, Building Assembloids, and Designing Synthetic Tissues using Human Cell Lines

In Vitro Cultivation Techniques for Modeling Liver Organogenesis, Building Assembloids, and Designing Synthetic Tissues using Human Cell Lines

Published on: April 18, 2025

Modeling Breast Cancer in Human Breast Tissue using a Microphysiological System

Modeling Breast Cancer in Human Breast Tissue using a Microphysiological System

Published on: April 23, 2021

In Vivo Modeling of the Morbid Human Genome using Danio rerio

In Vivo Modeling of the Morbid Human Genome using Danio rerio

Published on: August 24, 2013

Area of Science:

Computational biology
Genomics
Neuroscience

Background:

Single-cell RNA sequencing (scRNA-seq) provides deep insights into gene expression, aiding diagnostics and tissue annotation.
Current computational methods often analyze individual cells, neglecting crucial cellular composition information for sample-level phenotypes.
Understanding cellular composition is vital for accurate tissue identity and phenotype inference.

Purpose of the Study:

To introduce TissueFormer, a Transformer-based neural network designed to infer population-level labels from scRNA-seq data.
To overcome the limitations of single-cell analysis by incorporating cellular composition.
To develop a method that retains single-cell resolution while predicting sample-level phenotypes.

Main Methods:

Developed TissueFormer, a Transformer-based neural network architecture.
Applied TissueFormer to predict COVID-19 severity from blood scRNA-seq data.
Utilized TissueFormer for predicting cortical area identity from mouse brain spatial transcriptomic data.

Main Results:

TissueFormer successfully predicted COVID-19 severity and mouse cortical area identity.
TissueFormer demonstrated superior performance compared to single-cell foundation models.
The model outperformed machine learning methods applied to pseudobulk and cell type composition data.

Conclusions:

TissueFormer offers enhanced accuracy for diagnostics and automated high-resolution brain region mapping.
The model quantifies neuroanatomical differences, as shown in mice with altered visual input.
TissueFormer provides a versatile framework for predicting population-level phenotypes influenced by cellular diversity and tissue organization.