Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jan 9, 2026

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

7.3K

Scaling transformers to high-dimensional sparse data: a Reformer-BERT approach for large-scale classification.

Wanxuan Li1,2, Xinhua Li3, Weihang Guo1

  • 1Department of Urology, Inner Mongolia People's Hospital, Inner Mongolia Urological Institute, Hohhot, China.

Frontiers in Artificial Intelligence
|December 3, 2025
PubMed
Summary

Related Concept Videos

Survival Tree01:19

Survival Tree

374
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
374

You might also read

Related Articles

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

Sort by
Same author

Microplastics and tire wear particles in aquatic environment: A comparative review on generation, characteristics and environmental behavior.

NanoImpact·2026
Same author

Pulsatilla Saponin B4 Ameliorates LPS-Induced Inflammatory Response by Inhibiting IL-17RA and MAPK/NF-κB Signaling in Bovine Mammary Epithelial Cells and Mastitis Mouse Model.

Veterinary sciences·2026
Same author

Chromium propionate enhanced the production performance of yellow-feathered broilers under chronic heat stress exposure by improving intestinal health.

Stress biology·2026
Same author

Temporal and qualitative analysis of injured decomposed skin tissues using ATR-FTIR combined with chemometrics.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026
Same author

Facilitators and barriers to physical activity in middle-aged and older adult(s) HIV infected persons: a systematic review of qualitative studies.

Frontiers in public health·2026
Same author

RNA-binding protein ZMAT3 protects against MASLD by regulating SEPT11 mRNA stability.

Cellular signalling·2026
This summary is machine-generated.

This study introduces scReformer-BERT, a novel AI model for automated cell type classification using single-cell RNA sequencing data. It accurately identifies major cell categories, improving efficiency and precision in biological research.

Area of Science:

  • Genomics and Bioinformatics
  • Computational Biology
  • Molecular Biology

Background:

  • Accurate human cell type identification is crucial for biological research.
  • Manual annotation of single-cell RNA sequencing (scRNA-seq) data is challenging due to high dimensionality.
  • Automated methods are needed to efficiently and precisely classify cell types.

Purpose of the Study:

  • To develop and evaluate a robust, large-scale pre-trained model for automated cell type classification.
  • To focus on classifying major human cell categories using scRNA-seq data.
  • To improve the efficiency and precision of cellular identification in high-throughput genomic studies.

Main Methods:

  • Developed scReformer-BERT, integrating BERT architecture with Reformer encoders.
Keywords:
cell typeclassificationgene expressionmajor cell categoriesscRNA-seq

Related Experiment Videos

Last Updated: Jan 9, 2026

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
12:27

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

7.3K
  • Performed self-supervised pre-training on large scRNA-seq datasets.
  • Utilized supervised fine-tuning, five-fold cross-validation, ablation studies, and SHAP analysis for optimization and interpretation.

    • Main Results:

    • The scReformer-BERT model demonstrated superior efficacy in classifying major cell categories.
    • Performance was evaluated on scRNA-seq data against established baseline methods.
    • The model showed significant improvements compared to existing approaches and inherent field challenges.

    Conclusions:

    • The scReformer-BERT model offers a potent, effective, and interpretable solution for automated cell type classification from scRNA-seq data.
    • The model's performance highlights its utility in enhancing cellular identification in genomic research.
    • This approach advances automated analysis of complex biological datasets.