Abstract
The focuses of this work are: to propose a novel method for building an ensemble of classifiers for peptide classification based on substitution matrices; to show the importance to select a proper set of the parameters of the classifiers that build the ensemble of learning systems. The HIV-1 protease cleavage site prediction problem is here studied. The results obtained by a blind testing protocol are reported, the comparison with other state-of-the-art approaches, based on ensemble of classifiers, allows to quantify the performance improvement obtained by the systems proposed in this paper. The simulation based on experimentally determined protease cleavage data has demonstrated the success of these new ensemble algorithms. Particularly interesting it is to note that also if the HIV-1 protease cleavage site prediction problem is considered linearly separable we obtain the best performance using an ensemble of non-linear classifiers.
Keywords: Machine learning, ensembles of classifiers, substitution matrices, HIV-1 protease prediction
Protein & Peptide Letters
Title: A Further Step Toward an Optimal Ensemble of Classifiers for Peptide Classification, a Case Study: HIV Protease
Volume: 16 Issue: 2
Author(s): Loris Nanni and Alessandra Lumini
Affiliation:
Keywords: Machine learning, ensembles of classifiers, substitution matrices, HIV-1 protease prediction
Abstract: The focuses of this work are: to propose a novel method for building an ensemble of classifiers for peptide classification based on substitution matrices; to show the importance to select a proper set of the parameters of the classifiers that build the ensemble of learning systems. The HIV-1 protease cleavage site prediction problem is here studied. The results obtained by a blind testing protocol are reported, the comparison with other state-of-the-art approaches, based on ensemble of classifiers, allows to quantify the performance improvement obtained by the systems proposed in this paper. The simulation based on experimentally determined protease cleavage data has demonstrated the success of these new ensemble algorithms. Particularly interesting it is to note that also if the HIV-1 protease cleavage site prediction problem is considered linearly separable we obtain the best performance using an ensemble of non-linear classifiers.
Export Options
About this article
Cite this article as:
Nanni Loris and Lumini Alessandra, A Further Step Toward an Optimal Ensemble of Classifiers for Peptide Classification, a Case Study: HIV Protease, Protein & Peptide Letters 2009; 16 (2) . https://dx.doi.org/10.2174/092986609787316199
DOI https://dx.doi.org/10.2174/092986609787316199 |
Print ISSN 0929-8665 |
Publisher Name Bentham Science Publisher |
Online ISSN 1875-5305 |
- 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
-
20th National Congress and Conference Abstracts
Endocrine, Metabolic & Immune Disorders - Drug Targets Treatment Approaches for COVID-19: A Critical Review
Mini-Reviews in Medicinal Chemistry Review of QSAR for DNA Polymerase Inhibitors and New Models for Heterogeneous Series of Compounds
Current Computer-Aided Drug Design Artificial Membrane Assays to Assess Permeability
Current Drug Metabolism Anticancer Drug Design Using Scaffolds of β-Lactams, Sulfonamides, Quinoline, Quinoxaline and Natural Products. Drugs Advances in Clinical Trials
Current Medicinal Chemistry AI in Health Science: A Perspective
Current Pharmaceutical Biotechnology Oxidative Status in Multiple Sclerosis and Off-Targets of Antioxidants: The Case of Edaravone
Current Medicinal Chemistry Immunoproteasome-Selective Inhibitors: A Promising Strategy to Treat Hematologic Malignancies, Autoimmune and Inflammatory Diseases
Current Medicinal Chemistry Pre-Admission Beta-Blocker Therapy and Outcomes of Coronavirus Disease 2019 (COVID-19): A Systematic Review, Meta-Analysis, and Meta-Regression
Cardiovascular & Hematological Disorders-Drug Targets Computer-aided Drug Design against Emerging Viruses: Part I
Current Topics in Medicinal Chemistry Pathophysiology and Prevention of Bronchopulmonary Dysplasia
Current Pediatric Reviews Chagas Disease Chemotherapy: What Do We Know So Far?
Current Pharmaceutical Design Medicinal Research Progress of Natural Coumarin and its Derivatives
The Natural Products Journal Human Multidrug Transporter ABCG2, a Target for Sensitizing Drug Resistance in Cancer Chemotherapy
Current Medicinal Chemistry State of the Art on Carbonic Anhydrase Modulators for Biomedical Purposes
Current Medicinal Chemistry Alkaloids as Important Scaffolds in Therapeutic Drugs for the Treatments of Cancer, Tuberculosis, and Smoking Cessation
Current Topics in Medicinal Chemistry Imidazoles as Promising Scaffolds for Antibacterial Activity: A Review
Mini-Reviews in Medicinal Chemistry Synthetic Sphingosine 1-Phosphate Receptor Modulators - Opportunities and Potential Pitfalls
Current Topics in Medicinal Chemistry Measurement of Scientific Productivity in R&D Sector: Changing paradigm
Recent Patents on Biotechnology Mucormycosis in India: Pathophysiology and Perspectives on Treatment and Management
Infectious Disorders - Drug Targets