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
-
Regulation of Cell Growth by Estrogen Signaling and Potential Targets in Thyroid Cancer
Current Cancer Drug Targets Potential Use of Polymeric Nanoparticles for Drug Delivery Across the Blood-Brain Barrier
Current Medicinal Chemistry Protein Kinases as Tumor Biomarkers and Therapeutic Targets
Current Pharmaceutical Design Castration Resistant Prostate Cancer: From Emerging Molecular Pathways to Targeted Therapeutic Approaches
Clinical Cancer Drugs Tubulin-Independent Tau in Alzheimer’s Disease and Cancer: Implications for Disease Pathogenesis and Treatment
Current Alzheimer Research Novel VEGF-independent Strategies Targeting Tumor Vasculature: Clinical Aspects
Current Pharmaceutical Design Adult Neurogenic and Antidepressant Effects of Adiponectin: A Potential Replacement for Exercise
CNS & Neurological Disorders - Drug Targets Viral-Mediated Gene Transfer for Cancer Treatment
Current Pharmaceutical Biotechnology Editorial [Hot Topic: Cancer and Stem Cells (Guest Editor: Eiichi Tahara)]
Current Cancer Therapy Reviews Anticancer Drugs Targeting the Apoptotic Pathway
Medicinal Chemistry Reviews - Online (Discontinued) Prospects of miRNA-Based Therapy for Pancreatic Cancer
Current Drug Targets New Dehydroepiandrosterone-triazole Derivatives Identified as Inhibitors of 17β-Hydroxysteroid Dehydrogenase Enzyme in the Prostate
Current Enzyme Inhibition Natural Compounds with Proteasome Inhibitory Activity for Cancer Prevention and Treatment
Current Protein & Peptide Science Beneficial Extracardiac Effects of Cardiovascular Medications
Current Cardiology Reviews Experimental Research on Nitric Oxide and the Therapy of Alzheimer Disease: A Challenging Bridge
CNS & Neurological Disorders - Drug Targets Towards the Molecular Imaging of Prostate Cancer Biomarkers Using Protein-based MRI Contrast Agents
Current Protein & Peptide Science The Ubiquitin-Proteasome Pathway and Resistance Mechanisms Developed Against the Proteasomal Inhibitors in Cancer Cells
Current Drug Targets The Role of Macrophage Migration Inhibitory Factor in Critical Illness
Mini-Reviews in Medicinal Chemistry The Pim Kinases: New Targets for Drug Development
Current Drug Targets Is Small Really Beautiful? Nanosensors and Low Abundance Biomarkers for Personalized Medicine
Current Pharmacogenomics and Personalized Medicine