Abstract
In this research an efficient gene selection method called Discriminant Mutual Information (DMI) algorithm is proposed. The DMI algorithm sequentially induces discrimination and relevance to identify the most significant genes for tumor classification. In particular, in the first step the entire gene population is decorrelated by the formation of gene-sets such that the genes with similar characteristics form a single gene-set. The mutual information criterion is further employed to identify the most representative gene of each gene-set. Extensive experiments have been conducted on six publicly available databases where the proposed DMI algorithm has shown good results compared to a number of state-of-the-art approaches. Extensive computational analysis clearly reflects the computational efficiency of the proposed approach, typically it requires only a few seconds for experimentation on standard microarray datasets.
Keywords: Gene selection, microarray data, tumor classification.
Current Bioinformatics
Title:A Novel Information Theoretic Approach to Gene Selection for Cancer Classification Using Microarray Data
Volume: 10 Issue: 4
Author(s): Imran Naseem, Roberto Togneri and Mohammed Bennamoun
Affiliation:
Keywords: Gene selection, microarray data, tumor classification.
Abstract: In this research an efficient gene selection method called Discriminant Mutual Information (DMI) algorithm is proposed. The DMI algorithm sequentially induces discrimination and relevance to identify the most significant genes for tumor classification. In particular, in the first step the entire gene population is decorrelated by the formation of gene-sets such that the genes with similar characteristics form a single gene-set. The mutual information criterion is further employed to identify the most representative gene of each gene-set. Extensive experiments have been conducted on six publicly available databases where the proposed DMI algorithm has shown good results compared to a number of state-of-the-art approaches. Extensive computational analysis clearly reflects the computational efficiency of the proposed approach, typically it requires only a few seconds for experimentation on standard microarray datasets.
Export Options
About this article
Cite this article as:
Naseem Imran, Togneri Roberto and Bennamoun Mohammed, A Novel Information Theoretic Approach to Gene Selection for Cancer Classification Using Microarray Data, Current Bioinformatics 2015; 10 (4) . https://dx.doi.org/10.2174/157489361004150922145751
DOI https://dx.doi.org/10.2174/157489361004150922145751 |
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
-
Adhesion Molecules in Lung Cancer: Implications in the Pathogenesis and Management
Current Pharmaceutical Design Multipotent, Permeable Drug ASS234 Inhibits Aβ Aggregation, Possesses Antioxidant Properties and Protects from Aβ-induced Apoptosis In Vitro
Current Alzheimer Research Epigenetic Evaluation of N-(2-hydroxyphenyl)-2-Propylpentanamide, a Valproic Acid Aryl Derivative with Activity Against HeLa Cells
Current Molecular Pharmacology Development of PET Probes for Cancer Imaging
Current Topics in Medicinal Chemistry Exosomes: A Role for Naturally Occurring Nanovesicles in Cancer Growth, Diagnosis and Treatment
Current Gene Therapy Novel Nucleic Acid-Based Agents: siRNAs and miRNAs
Central Nervous System Agents in Medicinal Chemistry Nitric Oxide Control of Proliferation in Nerve Cells and in Tumor Cells of Nervous Origin
Current Pharmaceutical Design Thirty Years of Polyamine-Related Approaches to Cancer Therapy. Retrospect and Prospect. Part 1. Selective Enzyme Inhibitors
Current Drug Targets Roles of Natural Compounds from Medicinal Plants in Cancer Treatment: Structure and Mode of Action at Molecular Level
Medicinal Chemistry Altered Arginine Metabolism in Cells Transfected with Human Wild-Type Beta Amyloid Precursor Protein (βAPP)
Current Alzheimer Research Regulation and Function of DNA and Histone Methylations
Current Pharmaceutical Design Synthetic and Natural Coumarins as Cytotoxic Agents
Current Medicinal Chemistry - Anti-Cancer Agents Neurotoxicity of β-Amyloid Protein: Oligomerization, Channel Formation and Calcium Dyshomeostasis
Current Pharmaceutical Design Anticancer Actions of Omega-3 Fatty Acids - Current State and Future Perspectives
Anti-Cancer Agents in Medicinal Chemistry Biologically Active Peptides Interacting with the G Protein-Coupled Formylpeptide Receptors
Protein & Peptide Letters The Clinical Characteristics and Survival Profiles of Wilms Tumor in the United Arab Emirates: A Single-center Retrospective Analysis
New Emirates Medical Journal Neglected Aspects of Drug Discovery - Microbiological Aspects
Current Clinical Pharmacology Pharmacological Properties and Therapeutic Potential of Naringenin: A Citrus Flavonoid of Pharmaceutical Promise
Current Pharmaceutical Design Intercellular Crosstalk Via Extracellular Vesicles in Tumor Milieu as Emerging Therapies for Cancer Progression
Current Pharmaceutical Design Molecular Mechanisms, Biological Actions, and Neuropharmacology of the Growth-Associated Protein GAP-43
Current Neuropharmacology