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: Jun 16, 2026

mirMachine: A One-Stop Shop for Plant miRNA Annotation
06:16

mirMachine: A One-Stop Shop for Plant miRNA Annotation

Published on: May 1, 2021

SFSSClass: an integrated approach for miRNA based tumor classification.

Ramkrishna Mitra1, Sanghamitra Bandyopadhyay, Ujjwal Maulik

  • 1Machine Intelligence Unit, Indian Statistical Institute, Kolkata, India. rmitra_t@isical.ac.in

BMC Bioinformatics
|February 4, 2010
PubMed
Summary
This summary is machine-generated.

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

RSTG: Robust Generation of High Quality Spatial Transcriptomics Data using Beta Divergence Based AutoEncoder.

IEEE journal of biomedical and health informatics·2026
Same author

Optimizing genomics-aware clinical agents in precision oncology.

NPJ systems biology and applications·2026
Same author

Immunological and prognostic impact of NRF2 in high grade serous ovarian cancer.

Genes and immunity·2026
Same author

Altered chromatin accessibility and nucleosome positioning landscape upon HDAC and LSD1 inhibition in cancer cell.

bioRxiv : the preprint server for biology·2026
Same author

IFNγ-induced antigen loss in chimeric antigen receptor-T cell therapy.

Frontiers in immunology·2026
Same author

Accurate prediction of cohesin and RNA Polymerase II-associated chromatin interactions using convolutional neural networks.

Nucleic acids research·2026

A new method, SFSSClass, improves tumor classification using microRNA (miRNA) expression data by integrating biclustering for feature and sample selection with a cancer-miRNA network. This approach enhances diagnostic accuracy for various cancers.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Genomics

Background:

  • MicroRNA (miRNA) expression profiling is crucial for cancer research, aiding diagnosis and prognosis.
  • Existing tumor classification methods using miRNA data often neglect valuable literature-based experimental knowledge.
  • Integrating literature knowledge with miRNA and sample selection can enhance tumor classification accuracy.

Purpose of the Study:

  • To develop a novel classification technique, SFSSClass, for improved tumor classification.
  • To integrate biclustering for simultaneous miRNA and sample selection with a curated cancer-miRNA network and a classifier.
  • To evaluate SFSSClass performance on classifying multiple tumor types and cell lines, including challenging poorly differentiated tumors.

Main Methods:

More Related Videos

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma
09:58

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

Published on: June 6, 2025

Related Experiment Videos

Last Updated: Jun 16, 2026

mirMachine: A One-Stop Shop for Plant miRNA Annotation
06:16

mirMachine: A One-Stop Shop for Plant miRNA Annotation

Published on: May 1, 2021

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma
09:58

DNA-barcode-based Multiplex Immunofluorescence Imaging to Analyze FFPE Specimens from Genetically Reprogrammed Murine Melanoma

Published on: June 6, 2025

  • Developed SFSSClass, integrating the SAMBA biclustering technique for simultaneous feature (miRNA) and sample (tissue) selection (SFSS).
  • Incorporated a cancer-miRNA network derived from experimentally verified relationships mined from literature.
  • Utilized the uncorrelated shrunken centroid (USC) classifier within the SFSSClass framework.

    • Main Results:

    • SFSSClass demonstrated superior performance in classifying multiple tumor types and cancer cell lines compared to existing methods.
    • Achieved approximately 82.3% accuracy in classifying poorly differentiated tumors (PDT), outperforming the literature benchmark of ~76.5%.
    • SFSSClass consistently outperformed the USC classifier alone, highlighting the benefit of integrating biclustering and the cancer-miRNA network.

    Conclusions:

    • The SFSSClass algorithm effectively integrates biclustering, a cancer-miRNA network, and a classifier for improved tumor classification.
    • This novel integration of experimental knowledge and computational tools enables efficient selection of relevant features with high intra-class and low inter-class similarity.
    • SFSSClass shows significantly improved performance over existing approaches, offering a more accurate tool for cancer research and diagnostics.