Abstract
Protein and peptide sequences contain clues for functional prediction. A challenge is to predict sequences that show low or no homology to proteins or peptides of known function. A machine learning method, support vector machines (SVM), has recently been explored for predicting functional class of proteins and peptides from sequence-derived properties irrespective of sequence similarity, which has shown impressive performance for predicting a wide range of protein and peptide classes including certain low- and non- homologous sequences. This method serves as a new and valuable addition to complement the extensively-used alignment-based, clustering-based, and structure-based functional prediction methods. This article evaluates the strategies, current progresses, reported prediction performances, available software tools, and underlying difficulties in using SVM for predicting the functional class of proteins and peptides.
Keywords: Machine learning method, peptide, peptide function, protein family, protein function, protein function prediction, protein sequence, support vector machine
Current Protein & Peptide Science
Title: Homology-Free Prediction of Functional Class of Proteins and Peptides by Support Vector Machines
Volume: 9 Issue: 1
Author(s): Y. Z. Chen, F. Zhu, L. Y. Han, X. Chen, H. H. Lin, S. Ong, B. Xie and H. L. Zhang
Affiliation:
Keywords: Machine learning method, peptide, peptide function, protein family, protein function, protein function prediction, protein sequence, support vector machine
Abstract: Protein and peptide sequences contain clues for functional prediction. A challenge is to predict sequences that show low or no homology to proteins or peptides of known function. A machine learning method, support vector machines (SVM), has recently been explored for predicting functional class of proteins and peptides from sequence-derived properties irrespective of sequence similarity, which has shown impressive performance for predicting a wide range of protein and peptide classes including certain low- and non- homologous sequences. This method serves as a new and valuable addition to complement the extensively-used alignment-based, clustering-based, and structure-based functional prediction methods. This article evaluates the strategies, current progresses, reported prediction performances, available software tools, and underlying difficulties in using SVM for predicting the functional class of proteins and peptides.
Export Options
About this article
Cite this article as:
Chen Z. Y., Zhu F., Han Y. L., Chen X., Lin H. H., Ong S., Xie B. and Zhang L. H., Homology-Free Prediction of Functional Class of Proteins and Peptides by Support Vector Machines, Current Protein & Peptide Science 2008; 9 (1) . https://dx.doi.org/10.2174/138920308783565697
DOI https://dx.doi.org/10.2174/138920308783565697 |
Print ISSN 1389-2037 |
Publisher Name Bentham Science Publisher |
Online ISSN 1875-5550 |
- 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
-
Patents on Enhancing the Potency and Longevity of Highly Valuable Protein Hormones
Recent Patents on Endocrine, Metabolic & Immune Drug Discovery Advanced Tools of Regenerative Medicine for Neurodegenerative Diseases
Recent Patents on Regenerative Medicine The Potential of Trace Amines and Their Receptors for Treating Neurological and Psychiatric Diseases
Reviews on Recent Clinical Trials The Role of Protein Kinase C-alpha (PKC-α) in Cancer and its Modulation by the Novel PKC-α-Specific Inhibitor Aprinocarsen
Current Pharmaceutical Design Cancer-related Fatigue, Inflammation and Thyrotropin-releasing Hormone
Current Aging Science Angiopoietin-2 Axis Inhibitors: Current Status and Future Considerations for Cancer Therapy
Current Angiogenesis (Discontinued) Targeting NO Signaling for the Treatment of Osteoporosis
Current Medicinal Chemistry Anti-Angiogenic Drugs and Biomarkers in Non-Small-Cell Lung Cancer: 'A Hard Days Night'
Current Pharmaceutical Design Reactive Oxygen Species in Pathogenesis of Atherosclerosis
Current Pharmaceutical Design Aurora B Kinase and Passenger Proteins as Targets for Cancer Therapy
Current Enzyme Inhibition P2X Receptors and Inflammation
Current Medicinal Chemistry A Combination of Pharmacophore and In silico Approaches for Identification of Potential Transthyretin Amyloidosis Inhibitors
Letters in Drug Design & Discovery Exploiting HPV-Induced Carcinogenesis for a Rational Drug Development in Cervical Cancer
Current Cancer Drug Targets Off-Label Use of Sunitinib in Patients with Advanced, Epithelial Thyroid Cancer: A Retrospective Analysis
Recent Patents on Endocrine, Metabolic & Immune Drug Discovery The Alteration of Coagulation in Patients with Thyroid Dysfunction
Recent Patents on Endocrine, Metabolic & Immune Drug Discovery The Caveolin-1 Connection to Cell Death and Survival
Current Molecular Medicine Chemokines and their Receptors in Gut Homeostasis and Disease
Current Immunology Reviews (Discontinued) Cachexia and Herbal Medicine: Perspective
Current Pharmaceutical Design Glucose Transport and Metabolism in Sertoli Cell: Relevance for Male Fertility
Current Chemical Biology Biological and Pharmacological Roles of N6-Isopentenyladenosine: An Emerging Anticancer Drug
Anti-Cancer Agents in Medicinal Chemistry