Abstract
The aim of many microarray experiments is to build discriminatory diagnosis and prognosis models. A large number of supervised methods have been proposed in literature for microarray-based classification. Model comparison, which is based on the classification error estimation, is a critical issue. Previous studies have shown that error estimation is unreliable in high-dimensional small-sample settings. This leads naturally to questioning the validity of classificationrule comparison approaches being used in the literature. In this paper we present a brief review of the different comparison methods used in bioinformatics. Then, we test these methods on a set of simulations based on both synthetic and real data. These simulations include different feature-label distributions, classification rules, error estimators and variance estimators. The results show that none of these methods can provide reliable comparison across a wide spectrum of feature-label distributions and classification rules.
Keywords: Microarray classification, error estimation, classifier comparison, variance study
Current Bioinformatics
Title: On the Comparison of Classifiers for Microarray Data
Volume: 5 Issue: 1
Author(s): Blaise Hanczar and Edward R. Dougherty
Affiliation:
Keywords: Microarray classification, error estimation, classifier comparison, variance study
Abstract: The aim of many microarray experiments is to build discriminatory diagnosis and prognosis models. A large number of supervised methods have been proposed in literature for microarray-based classification. Model comparison, which is based on the classification error estimation, is a critical issue. Previous studies have shown that error estimation is unreliable in high-dimensional small-sample settings. This leads naturally to questioning the validity of classificationrule comparison approaches being used in the literature. In this paper we present a brief review of the different comparison methods used in bioinformatics. Then, we test these methods on a set of simulations based on both synthetic and real data. These simulations include different feature-label distributions, classification rules, error estimators and variance estimators. The results show that none of these methods can provide reliable comparison across a wide spectrum of feature-label distributions and classification rules.
Export Options
About this article
Cite this article as:
Hanczar Blaise and Dougherty R. Edward, On the Comparison of Classifiers for Microarray Data, Current Bioinformatics 2010; 5 (1) . https://dx.doi.org/10.2174/157489310790596376
DOI https://dx.doi.org/10.2174/157489310790596376 |
Print ISSN 1574-8936 |
Publisher Name Bentham Science Publisher |
Online ISSN 2212-392X |
- Author Guidelines
- Graphical Abstracts
- Fabricating and Stating False Information
- Research Misconduct
- Post Publication Discussions and Corrections
- Publishing Ethics and Rectitude
- Increase Visibility of Your Article
- Archiving Policies
- Peer Review Workflow
- Order Your Article Before Print
- Promote Your Article
- Manuscript Transfer Facility
- Editorial Policies
- Allegations from Whistleblowers
Related Articles
-
Irradiation Toxicity and Inflammatory Bowel Diseases (IBD): Review
Reviews on Recent Clinical Trials Metabolic Basis of Sporadic Alzeimer’s Disease. Role of Hormones Related to Energy Metabolism
Current Pharmaceutical Design The PTEN/PI3K/AKT Signalling Pathway in Cancer, Therapeutic Implications
Current Cancer Drug Targets An Uncommon Case of Symptomatic Multiple Meningiomas with Bilateral Compressive Optic Neuropathy Rapidly Induced under Cyprotero ne Acetate Treatment
Current Drug Safety The Ubiquitin-Proteasome System as a Prospective Molecular Target for Cancer Treatment and Prevention
Current Protein & Peptide Science Thapsigargin, Origin, Chemistry, Structure-Activity Relationships and Prodrug Development
Current Pharmaceutical Design Review on Triggered Liposomal Drug Delivery with a Focus on Ultrasound
Current Cancer Drug Targets Pathophysiology and Treatment of Nonfamilial Hyperparathyroidism
Recent Patents on CNS Drug Discovery (Discontinued) COVID-19 and Autoimmune Diseases: A Systematic Review of Reported Cases
Current Rheumatology Reviews Monitoring T Cell Responses to Cancer Immunotherapy: Can We Now Identify Biomarkers Predicting Patients Who will be Responders
Current Cancer Therapy Reviews Multitargeted Molecular Docking Study of Natural-Derived Alkaloids on Breast Cancer Pathway Components
Current Computer-Aided Drug Design Tumor Targeting with RGD Peptide Ligands-Design of New Molecular Conjugates for Imaging and Therapy of Cancers
Anti-Cancer Agents in Medicinal Chemistry Effects of Nanoscale Confinement on the Functionality of Nucleic Acids: Implications for Nanomedicine
Current Medicinal Chemistry Drug Target Strategies in Breast Cancer Treatment: Recent Developments
Anti-Cancer Agents in Medicinal Chemistry Design of Cathepsin K Inhibitors for Osteoporosis
Current Topics in Medicinal Chemistry Experimental Research on Nitric Oxide and the Therapy of Alzheimer Disease: A Challenging Bridge
CNS & Neurological Disorders - Drug Targets A Better Platinum-Based Anticancer Drug Yet to Come?
Anti-Cancer Agents in Medicinal Chemistry Adiposity and the Gut - The Role of Gut Hormones
Current Nutrition & Food Science Focal Adhesion Kinase as a Cancer Therapy Target
Anti-Cancer Agents in Medicinal Chemistry Natural and Synthetic Retinoids in Prostate Cancer
Current Pharmaceutical Design