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

A comparative study on feature selection and classification methods using gene expression profiles and proteomic

Huiqing Liu1, Jinyan Li, Limsoon Wong

  • 1Laboratories for Information Technology, 21 Heng Mui Keng Terr, 119613 Singapore. huiqing@lit.a-star.edu.sg

Genome Informatics. International Conference on Genome Informatics
|October 23, 2003
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

PRMT9 Aggravated Dopaminergic Neurodegeneration in Parkinson's Disease Model by Facilitating the Degradation of DUSP26 and Inducing Mitochondrial Dysfunction.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Analysis of the current situation and influencing factors of emotional labor among pediatric nurses: A cross-sectional study.

PloS one·2026
Same author

Synergy antibacterial effects of lytic phage vB_AbaA_LLY and levofloxacin against KL2 and KL160 Acinetobacter baumannii.

European journal of clinical microbiology & infectious diseases : official publication of the European Society of Clinical Microbiology·2026
Same author

CEMUSA: a graph-based integrative metric for evaluating clusters in spatial transcriptomics.

Bioinformatics (Oxford, England)·2026
Same author

Molecular Recognition-Based Detection: Antibody Dipsticks for Cyclic Organochlorine Chemicals.

Analytical chemistry·2026
Same author

Zinc-catalyzed dehydrogenative coupling of primary alcohols and secondary/benzyl phosphine oxides for alkene synthesis.

Organic & biomolecular chemistry·2026
Same journal

Linear regression models predicting strength of transcriptional activity of promoters.

Genome informatics. International Conference on Genome Informatics·2012
Same journal

Sign: large-scale gene network estimation environment for high performance computing.

Genome informatics. International Conference on Genome Informatics·2012
Same journal

Docking-calculation-based method for predicting protein-RNA interactions.

Genome informatics. International Conference on Genome Informatics·2012
Same journal

Mechanism of cell cycle disruption by multiple p53 pulses.

Genome informatics. International Conference on Genome Informatics·2012
Same journal

Database for crude drugs and Kampo medicine.

Genome informatics. International Conference on Genome Informatics·2012
Same journal

A dynamic programming algorithm to predict synthesis processes of tree-structured compounds with graph grammar.

Genome informatics. International Conference on Genome Informatics·2011
See all related articles

Feature selection is crucial for accurate classification. This study shows that selecting the right features improves the performance of classification algorithms for both leukemia and ovarian cancer patient data.

Area of Science:

  • Biomedical Informatics
  • Machine Learning in Healthcare
  • Bioinformatics

Background:

  • Accurate classification of patient data is essential for diagnosis and treatment.
  • Gene expression profiles and proteomic patterns are complex datasets requiring effective analysis.
  • Feature selection is a critical preprocessing step in machine learning for high-dimensional biological data.

Purpose of the Study:

  • To compare the effectiveness of six different feature selection heuristics.
  • To evaluate the impact of feature selection on classification accuracy using real-world patient data.
  • To demonstrate the importance of feature selection in classifying Acute Lymphoblastic Leukemia (ALL) and ovarian cancer.

Main Methods:

  • Applied six feature selection heuristics to two distinct biological datasets.

Related Experiment Videos

  • Utilized gene expression profiles from Acute Lymphoblastic Leukemia (ALL) patients.
  • Analyzed proteomic patterns from ovarian cancer patients.
  • Calculated error rates of various classification algorithms based on selected features.

    • Main Results:

    • The choice of feature selection method significantly impacted classification error rates.
    • Effective feature selection led to more accurate classification of both ALL and ovarian cancer samples.
    • Demonstrated a clear improvement in predictive accuracy when appropriate features were identified.

    Conclusions:

    • Feature selection is indispensable for achieving high classification accuracy in biomedical applications.
    • The study highlights the utility of heuristic-based feature selection for complex biological datasets.
    • Optimized feature selection enhances the reliability of machine learning models for patient stratification.