Abstract
Background: Cancer threatens human health seriously. Diagnosing cancer via gene expression analysis is a hot topic in cancer research.
Objective: The study aimed to diagnose the accurate type of lung cancer and discover the pathogenic genes.
Methods: In this study, Affinity Propagation (AP) clustering with similarity score was employed to each type of lung cancer and normal lung. After grouping genes, sparse group lasso was adopted to construct four binary classifiers and the voting strategy was used to integrate them.
Results: This study screened six gene groups that may associate with different lung cancer subtypes among 73 genes groups, and identified three possible key pathogenic genes, KRAS, BRAF and VDR. Furthermore, this study achieved improved classification accuracies at minority classes SQ and COID in comparison with other four methods.
Conclusion: We propose the AP clustering based sparse group lasso (AP-SGL), which provides an alternative for simultaneous diagnosis and gene selection for lung cancer.
Keywords: Lung cancer, gene selection, affinity propagation clustering, sparse group lasso, multi-classification, miRNA.
Graphical Abstract
Current Bioinformatics
Title:Lung Cancer Classification and Gene Selection by Combining Affinity Propagation Clustering and Sparse Group Lasso
Volume: 15 Issue: 7
Author(s): Juntao Li*, Mingming Chang, Qinghui Gao, Xuekun Song and Zhiyu Gao
Affiliation:
- College of Mathematics and Information Science, Henan Normal University, Xinxiang, 453007,China
Keywords: Lung cancer, gene selection, affinity propagation clustering, sparse group lasso, multi-classification, miRNA.
Abstract:
Background: Cancer threatens human health seriously. Diagnosing cancer via gene expression analysis is a hot topic in cancer research.
Objective: The study aimed to diagnose the accurate type of lung cancer and discover the pathogenic genes.
Methods: In this study, Affinity Propagation (AP) clustering with similarity score was employed to each type of lung cancer and normal lung. After grouping genes, sparse group lasso was adopted to construct four binary classifiers and the voting strategy was used to integrate them.
Results: This study screened six gene groups that may associate with different lung cancer subtypes among 73 genes groups, and identified three possible key pathogenic genes, KRAS, BRAF and VDR. Furthermore, this study achieved improved classification accuracies at minority classes SQ and COID in comparison with other four methods.
Conclusion: We propose the AP clustering based sparse group lasso (AP-SGL), which provides an alternative for simultaneous diagnosis and gene selection for lung cancer.
Export Options
About this article
Cite this article as:
Li Juntao *, Chang Mingming, Gao Qinghui, Song Xuekun and Gao Zhiyu, Lung Cancer Classification and Gene Selection by Combining Affinity Propagation Clustering and Sparse Group Lasso, Current Bioinformatics 2020; 15 (7) . https://dx.doi.org/10.2174/1574893614666191017103557
DOI https://dx.doi.org/10.2174/1574893614666191017103557 |
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
-
Novel One-pot Synthesis of Pyranocarbazole Derivatives via an Isocyanidebased Three-component Reaction
Letters in Organic Chemistry Recent Advances in the Diagnosis and Therapy of Primary Adrenal Insufficiency
Current Medicinal Chemistry - Immunology, Endocrine & Metabolic Agents GRAPHICAL ABSTRACTS
Letters in Drug Design & Discovery Synergism from Combination of Cisplatin and Multicentred Platinums Coded as DH6Cl and TH1 in the Human Ovarian Tumour Models
Medicinal Chemistry Role of Tyrosine Kinase Inhibitors in Lung Cancer
Anti-Cancer Agents in Medicinal Chemistry Peroxisome Proliferator-Activated Receptors and their Ligands in Cancer Drug- Resistance: Opportunity or Challenge
Anti-Cancer Agents in Medicinal Chemistry Insect Peptides – Perspectives in Human Diseases Treatment
Current Medicinal Chemistry Targeting Cancer Cells by an Oxidant-Based Therapy
Current Molecular Pharmacology Aromatherapy and the Central Nerve System (CNS): Therapeutic Mechanism and its Associated Genes
Current Drug Targets Contrast Enhanced Ultrasonography for Focal Liver Lesions Characterization: Clinical Perspective
Current Medical Imaging Crosstalk between IGF-1R and other Tumor Promoting Pathways
Current Pharmaceutical Design Newer Insights in Personalized and Evidence Based Medicine- the Role of MicroRNAs
Current Pharmacogenomics and Personalized Medicine Overview of Naphthalimide Analogs as Anticancer Agents
Current Medicinal Chemistry Current Role of Proteomics in Pancreatic Cancer Biomarkers Research
Current Proteomics Melatonin and Melatoninergic Drugs as Therapeutic Agents: Ramelteon and Agomelatine, the Two Most Promising Melatonin Receptor Agonists
Recent Patents on Endocrine, Metabolic & Immune Drug Discovery (Discontinued) Apoptosis Induction by Ultrasound and Microbubble Mediated Drug Delivery and Gene Therapy
Current Molecular Medicine Adrenomedullin: A Tumor Progression Factor via Angiogenic Control
Current Cancer Drug Targets AMPK Regulation of Glucose, Lipid and Protein Metabolism: Mechanisms and Nutritional Significance
Current Protein & Peptide Science Aptamers Overview: Selection, Features and Applications
Current Topics in Medicinal Chemistry Development of Method for Three-Point Data Estimation and SVR-QSAR Model to Screen Anti Cancer Leads
Combinatorial Chemistry & High Throughput Screening