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 Videos

Semisupervised learning for molecular profiling.

Cesare Furlanello1, Maria Serafini, Stefano Merler

  • 1ITC-irst, via Sommarive 18, I-38050 Povo (Trento), Italy. furlan@itc.it

IEEE/ACM Transactions on Computational Biology and Bioinformatics
|October 19, 2006
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

Effectiveness of screening protocols to reduce MRSA colonization in a pediatric hospital.

International journal of infectious diseases : IJID : official publication of the International Society for Infectious Diseases·2026
Same author

Why almost all ML models for medicine are wrong-and what we need for evidence-based medical AI.

International journal of medical informatics·2026
Same author

Scenario analysis for potential community spread of Andes virus (ANDV).

Euro surveillance : bulletin Europeen sur les maladies transmissibles = European communicable disease bulletin·2026
Same author

Assessing the annual burden of tick-borne encephalitis virus infections, north-east Italy, 2017 to 2024.

Euro surveillance : bulletin Europeen sur les maladies transmissibles = European communicable disease bulletin·2026
Same author

Barriers, Perceptions, and Predictors for Utilizing Health-Related Technology Among Individuals Receiving Radiation Oncology Care.

Cureus·2026
Same author

Implications for distancing measures on in-person school and work attendance from Italian post-pandemic social contact data.

Communications medicine·2026
Same journal

circ2DGNN: circRNA-Disease Association Prediction via Transformer-Based Graph Neural Network.

IEEE/ACM transactions on computational biology and bioinformatics·2024
Same journal

Hierarchical Hypergraph Learning in Association- Weighted Heterogeneous Network for miRNA- Disease Association Identification.

IEEE/ACM transactions on computational biology and bioinformatics·2024
Same journal

Discriminative Domain Adaption Network for Simultaneously Removing Batch Effects and Annotating Cell Types in Single-Cell RNA-Seq.

IEEE/ACM transactions on computational biology and bioinformatics·2024
Same journal

MLW-BFECF: A Multi-Weighted Dynamic Cascade Forest Based on Bilinear Feature Extraction for Predicting the Stage of Kidney Renal Clear Cell Carcinoma on Multi-Modal Gene Data.

IEEE/ACM transactions on computational biology and bioinformatics·2024
Same journal

An End-to-End Knowledge Graph Fused Graph Neural Network for Accurate Protein-Protein Interactions Prediction.

IEEE/ACM transactions on computational biology and bioinformatics·2024
Same journal

Generative Biomedical Event Extraction With Constrained Decoding Strategy.

IEEE/ACM transactions on computational biology and bioinformatics·2024
See all related articles

This study introduces a semisupervised approach for discovering molecular subtypes in microarray data by analyzing sample-tracking profiles. This method helps identify outliers and subtypes, improving gene expression analysis.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning in Genomics

Background:

  • Class prediction and feature selection in microarray analysis are prone to selection bias.
  • Complex validation is needed to avoid optimistic accuracy estimates and incorrect gene selections.

Purpose of the Study:

  • To introduce a semisupervised pattern discovery approach for molecular profiling.
  • To study patterns of single sample responses (sample-tracking profiles) during gene selection.

Main Methods:

  • Sample-tracking profiles generated from aggregated off-training evaluations of Support Vector Machine (SVM) models.
  • Gene ranking using entropy-based recursive feature elimination (E-RFE).
  • Dynamic Time Warping (DTW) algorithm for metric definition between sample-tracking profiles.

Related Experiment Videos

  • Unsupervised clustering based on DTW metric for outlier and subtype discovery.

    • Main Results:

    • Demonstrated application on synthetic data.
    • Successfully applied to two gene expression studies.
    • Automated discovery of outliers and molecular subtypes.

    Conclusions:

    • The semisupervised approach effectively utilizes validation by-products for pattern discovery.
    • Sample-tracking profiles and DTW clustering offer a robust method for identifying molecular subtypes.
    • This method enhances the analysis of gene expression data by mitigating selection bias.