Abstract
In this review, we have discussed the class-prediction and discovery methods that are applied to gene expression data, along with the implications of the findings. We attempted to present a unified approach that considers both class-prediction and class-discovery. We devoted a substantial part of this review to an overview of pattern classification/recognition methods and discussed important issues such as preprocessing of gene expression data, curse of dimensionality, feature extraction/selection, and measuring or estimating classifier performance. We discussed and summarized important properties such as generalizability (sensitivity to overtraining), built-in feature selection, ability to report prediction strength, and transparency (ease of understanding of the operation) of different class-predictor design approaches to provide a quick and concise reference. We have also covered the topic of biclustering, which is an emerging clustering method that processes the entries of the gene expression data matrix in both gene and sample directions simultaneously, in detail.
Keywords: cDNA microarrays, Fisher's Linear Discriminant Analysis (FLDA), Artificial Neural Networks, multidimensional scaling, cross-validation (CV), Super-Paramagnetic Clustering algorithm
Current Bioinformatics
Title: Gene Expression Profile Classification: A Review
Volume: 1 Issue: 1
Author(s): Musa H. Asyali, Dilek Colak, Omer Demirkaya and Mehmet S. Inan
Affiliation:
Keywords: cDNA microarrays, Fisher's Linear Discriminant Analysis (FLDA), Artificial Neural Networks, multidimensional scaling, cross-validation (CV), Super-Paramagnetic Clustering algorithm
Abstract: In this review, we have discussed the class-prediction and discovery methods that are applied to gene expression data, along with the implications of the findings. We attempted to present a unified approach that considers both class-prediction and class-discovery. We devoted a substantial part of this review to an overview of pattern classification/recognition methods and discussed important issues such as preprocessing of gene expression data, curse of dimensionality, feature extraction/selection, and measuring or estimating classifier performance. We discussed and summarized important properties such as generalizability (sensitivity to overtraining), built-in feature selection, ability to report prediction strength, and transparency (ease of understanding of the operation) of different class-predictor design approaches to provide a quick and concise reference. We have also covered the topic of biclustering, which is an emerging clustering method that processes the entries of the gene expression data matrix in both gene and sample directions simultaneously, in detail.
Export Options
About this article
Cite this article as:
Asyali H. Musa, Colak Dilek, Demirkaya Omer and Inan S. Mehmet, Gene Expression Profile Classification: A Review, Current Bioinformatics 2006; 1 (1) . https://dx.doi.org/10.2174/157489306775330615
DOI https://dx.doi.org/10.2174/157489306775330615 |
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
-
Pharmacological Overview and Future Perspectives of Cholinergic Therapy in Alzheimers Disease
Current Drug Therapy The Cannabinoid CB2 Receptor as a Target for Inflammation-Dependent Neurodegeneration
Current Neuropharmacology Anticancer Potential of Thiazole Derivatives: A Retrospective Review
Mini-Reviews in Medicinal Chemistry The Renin-angiotensin System as a Target of Novel Anticancer Therapy
Current Pharmaceutical Design Top-Down Versus Bottom-Up Nanoengineering Routes to Design Advanced Oropharmacological Products
Current Pharmaceutical Design Nitric Oxide-Derived Oxidants with a Focus on Peroxynitrite: Molecular Targets,Cellular Responses and Therapeutic Implications
Current Pharmaceutical Design ROS1 Kinase Inhibitors for Molecular-Targeted Therapies
Current Medicinal Chemistry ABC Transporters in the Development of Multidrug Resistance in Cancer Therapy
Current Pharmaceutical Design Genetic and Modifying Factors that Determine the Risk of Brain Tumors
Central Nervous System Agents in Medicinal Chemistry A hypothesis for the role of RECK in angiogenesis
Current Vascular Pharmacology Pharmacological Modulation of p53 Function in Cancer Therapy
Current Signal Transduction Therapy Disodium Phosphate of Novel Pyrazole-Linked Norcantharidin Analogs:Design, Synthesis and their Anticancer Evaluation
Letters in Drug Design & Discovery RANKL/RANK/OPG: Key Therapeutic Target in Bone Oncology
Current Drug Discovery Technologies Protein Arginine Methyltransferase 1 and its Dynamic Regulation Associated with Cellular Processes and Diseases
Protein & Peptide Letters RECKing MMP: Relevance of Reversion-inducing Cysteine-rich Protein with Kazal Motifs as a Prognostic Marker and Therapeutic Target for Cancer (A Review)
Anti-Cancer Agents in Medicinal Chemistry The Roles of Chromatin Remodeling Proteins in Cancer
Current Protein & Peptide Science Cordycepin Suppresses Integrin/FAK Signaling and Epithelial-Mesenchymal Transition in Hepatocellular Carcinoma
Anti-Cancer Agents in Medicinal Chemistry Organ Preference of Cancer Metastasis and Metastasis-Related Cell Adhesion Molecules Including Carbohydrates
Cardiovascular & Hematological Disorders-Drug Targets Agonists of the Tissue-Protective Erythropoietin Receptor in the Treatment of Parkinson’s Disease
Current Topics in Medicinal Chemistry Magnetic Nanoparticles: New Players in Antimicrobial Peptide Therapeutics.
Current Protein & Peptide Science