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

Stemness and Survival: CD117<sup>+</sup>/CD133<sup>+</sup> Subpopulations Sustain PI3K Signaling and Drive Imatinib Resistance in Head and Neck Mucosal Melanoma.

Cells·2026
Same author

Molecular Changes Induced by Carbon Dioxide Laser in Hailey-Hailey Disease: A Potential Mechanism Underlying Treatment Efficacy.

International journal of dermatology·2026
Same author

Balancing Early Detection and Overtreatment in Prostate Cancer: The Emerging Role of EpihTERT.

Cancers·2025
Same author

Exploring a flexible and cytotoxic drug carrier of cisplatin and 5-fluorouracil for a multitarget therapeutic approach in colorectal cancer.

Journal of materials chemistry. B·2025
Same author

Spatial-Temporal Forecasting of Air Pollution in Saudi Arabian Cities Based on a Deep Learning Framework Enabled by AI.

Toxics·2025
Same author

Inhibition of PCSK9 Attenuates Liver Endothelial Cell Activation Induced by Colorectal Cancer Stem Cells During Liver Metastasis.

Cancers·2025

Related Experiment Video

Updated: Sep 30, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.7K

Triku: a feature selection method based on nearest neighbors for single-cell data.

Alex M Ascensión1,2, Olga Ibáñez-Solé1,2, Iñaki Inza3

  • 1Biodonostia Health Research Institute, Computational Biology and Systems Biomedicine Group, Paseo Dr. Begiristain, s/n, Donostia-San Sebastian, 20014, Spain.

Gigascience
|March 12, 2022
PubMed
Summary
This summary is machine-generated.

Triku is a novel feature selection method for single-cell RNA sequencing data. It identifies genes crucial for defining cell populations, overcoming biases in current methods for better biological insights.

Keywords:
Pythonbioinformaticsfeature selectionmachine learningsc-RNAseq

More Related Videos

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues
10:12

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues

Published on: January 10, 2019

18.7K
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

7.1K

Related Experiment Videos

Last Updated: Sep 30, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.7K
Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues
10:12

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues

Published on: January 10, 2019

18.7K
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

7.1K

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • Feature selection is critical for analyzing single-cell RNA sequencing (scRNA-seq) data.
  • Current methods often select highly expressed genes, missing those defining specific cell populations.
  • This bias stems from reliance on general univariate descriptors like dispersion or zero percentages.

Purpose of the Study:

  • To introduce Triku, a new feature selection method for scRNA-seq data.
  • To address the limitations of existing methods in identifying cell-population-specific genes.
  • To improve the biological relevance of selected gene sets.

Main Methods:

  • Triku selects genes based on their expression in neighboring cells within a k-nearest neighbor graph.
  • It prioritizes genes with higher-than-random expression in cell clusters.
  • Performance is evaluated using adjusted Rand index, normalized mutual information, supervised classification, and silhouette coefficient.

Main Results:

  • Triku effectively recovers cell populations in both artificial and biological datasets.
  • Gene sets selected by Triku show higher relevance to Gene Ontology terms.
  • Triku reduces the selection of non-informative ribosomal and mitochondrial genes.

Conclusions:

  • Triku offers a more biologically relevant approach to feature selection in scRNA-seq.
  • The method successfully identifies key genes that define distinct cell populations.
  • Triku is available as an open-source Python 3 package.