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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Design, synthesis, and biological evaluation of novel selenium-matrine hybrid compounds as topo I -targeted anticancer agents.

Bioorganic chemistry·2026
Same author

Rotational strip peanut/cereal intercropping systems improve soil quality and crop yields in aeolian sandy soil.

BMC plant biology·2026
Same author

Armadillo-inspired active morphing skeletons for soft machines.

Science advances·2026
Same author

Comparative evaluation of gene selection approaches in transcriptomics: bias correction and visualization with TransPro.

GigaScience·2026
Same author

Dissecting epigenetic heterogeneity in single-cell DNA methylomes with a unified framework.

Nature communications·2026
Same author

CSFeatures improves the identification of cell-type-specific differential features in single-cell and spatial omics data.

Journal of advanced research·2026

Related Experiment Video

Updated: Jun 11, 2025

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.2K

scCrab: A Reference-Guided Cancer Cell Identification Method based on Bayesian Neural Networks.

Heyang Hua1, Wenxin Long1, Yan Pan2

  • 1School of Mathematical Sciences and LPMC, Nankai University, Tianjin, 300071, China.

Interdisciplinary Sciences, Computational Life Sciences
|September 30, 2024
PubMed
Summary

scCrab is a new computational method for identifying cancer cells using single-cell RNA sequencing data. It improves accuracy by incorporating reference data and uses an ensemble learning approach for robust cancer cell detection.

Keywords:
Bayesian neural networkCancer cell identificationReference-guided methodSelf-attention mechanism

More Related Videos

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions
10:08

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions

Published on: February 24, 2021

5.8K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.7K

Related Experiment Videos

Last Updated: Jun 11, 2025

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.2K
Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions
10:08

Co-culture of Glioblastoma Stem-like Cells on Patterned Neurons to Study Migration and Cellular Interactions

Published on: February 24, 2021

5.8K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.7K

Area of Science:

  • Computational Biology
  • Genomics
  • Cancer Research

Background:

  • Early cancer detection significantly improves patient outcomes.
  • Single-cell RNA sequencing (scRNA-seq) enables high-resolution analysis of cellular heterogeneity.
  • Current computational methods for cancer cell identification using scRNA-seq data have limitations in performance and incorporating prior knowledge.

Purpose of the Study:

  • To develop a novel reference-guided computational method for automatic cancer cell identification.
  • To enhance the accuracy and reliability of cancer cell detection from scRNA-seq data.
  • To leverage external reference data for improved cancer cell identification.

Main Methods:

  • scCrab employs ensemble learning, combining a Bayesian neural network (BNN) with multi-head self-attention and a linear regression model.
  • The method is designed to be reference-guided, utilizing prior biological information.
  • Validation was performed using diverse scRNA-seq datasets.

Main Results:

  • scCrab demonstrated superior performance in both intra- and inter-dataset cancer cell identification.
  • The method showed robustness against variations in dropout rates and sample sizes.
  • Ablation studies confirmed the significant contribution of each component within the scCrab model.

Conclusions:

  • scCrab offers a significant advancement in automated cancer cell identification from scRNA-seq data.
  • The reference-guided approach and ensemble learning contribute to its high accuracy and robustness.
  • scCrab effectively captures biologically relevant cancer signatures, aiding in cancer diagnosis.