Abstract
It is important to understand the cause of amyloid illnesses by predicting the short protein fragments capable of forming amyloid-like fibril motifs aiding in the discovery of sequence-targeted anti-aggregation drugs. It is extremely desirable to design computational tools to provide affordable in silico predictions owing to the limitations of molecular techniques for their identification. In this research article, we tried to study, from a machine learning perspective, the performance of several machine learning classifiers that use heterogenous features based on biochemical and biophysical properties of amino acids to discriminate between amyloidogenic and non-amyloidogenic regions in peptides. Four conventional machine learning classifiers namely Support Vector Machine, Neural network, Decision tree and Random forest were trained and tested to find the best classifier that fits the problem domain well. Prior to classification, novel implementations of two biologically-inspired feature optimization techniques based on evolutionary algorithms and methodologies that mimic social life and a multivariate method based on projection are utilized in order to remove the unimportant and uninformative features. Among the dimenionality reduction algorithms considered under the study, prediction results show that algorithms based on evolutionary computation is the most effective. SVM best suits the problem domain in its fitment among the classifiers considered. The best classifier is also compared with an online predictor to evidence the equilibrium maintained between true positive rates and false positive rates in the proposed classifier. This exploratory study suggests that these methods are promising in providing amyloidogenity prediction and may be further extended for large-scale proteomic studies.
Keywords: Amyloid fibrils, ant colony optimization, biophysiochemical properties, decision tree, memetic algorithm, neural network, principal component analysis, random forest, support vector machine
Protein & Peptide Letters
Title:Machine Learning Study of Classifiers Trained with Biophysiochemical Properties of Amino Acids to Predict Fibril Forming Peptide Motifs
Volume: 19 Issue: 9
Author(s): Smitha Sunil Kumaran Nair, N. V. Subba Reddy and K. S. Hareesha
Affiliation:
Keywords: Amyloid fibrils, ant colony optimization, biophysiochemical properties, decision tree, memetic algorithm, neural network, principal component analysis, random forest, support vector machine
Abstract: It is important to understand the cause of amyloid illnesses by predicting the short protein fragments capable of forming amyloid-like fibril motifs aiding in the discovery of sequence-targeted anti-aggregation drugs. It is extremely desirable to design computational tools to provide affordable in silico predictions owing to the limitations of molecular techniques for their identification. In this research article, we tried to study, from a machine learning perspective, the performance of several machine learning classifiers that use heterogenous features based on biochemical and biophysical properties of amino acids to discriminate between amyloidogenic and non-amyloidogenic regions in peptides. Four conventional machine learning classifiers namely Support Vector Machine, Neural network, Decision tree and Random forest were trained and tested to find the best classifier that fits the problem domain well. Prior to classification, novel implementations of two biologically-inspired feature optimization techniques based on evolutionary algorithms and methodologies that mimic social life and a multivariate method based on projection are utilized in order to remove the unimportant and uninformative features. Among the dimenionality reduction algorithms considered under the study, prediction results show that algorithms based on evolutionary computation is the most effective. SVM best suits the problem domain in its fitment among the classifiers considered. The best classifier is also compared with an online predictor to evidence the equilibrium maintained between true positive rates and false positive rates in the proposed classifier. This exploratory study suggests that these methods are promising in providing amyloidogenity prediction and may be further extended for large-scale proteomic studies.
Export Options
About this article
Cite this article as:
Sunil Kumaran Nair Smitha, V. Subba Reddy N. and S. Hareesha K., Machine Learning Study of Classifiers Trained with Biophysiochemical Properties of Amino Acids to Predict Fibril Forming Peptide Motifs, Protein & Peptide Letters 2012; 19 (9) . https://dx.doi.org/10.2174/092986612802084429
DOI https://dx.doi.org/10.2174/092986612802084429 |
Print ISSN 0929-8665 |
Publisher Name Bentham Science Publisher |
Online ISSN 1875-5305 |

- Author Guidelines
- Bentham Author Support Services (BASS)
- 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
-
Editorial [Hot Topic:Applications of Angiotensin Converting Enzyme Inhibitors and of Angiotensin II Receptor Blockers in Pharmacology and Therapy: An Update (Executive Editor: Agostino Molteni)]
Current Pharmaceutical Design Gene Expression Profiling as a Tool for Positional Cloning of Genes- Shortcut or the Longest Way Round
Current Genomics The Emerging Role of MicroRNA in Schizophrenia
CNS & Neurological Disorders - Drug Targets Nanoparticle-Based Gene Therapy Intervention for Stroke Treatment: A Systematic Review
Current Gene Therapy Programmed Symptoms: Disparate Effects United by Purpose
Current Rheumatology Reviews Avian Cytokines - An Overview
Current Pharmaceutical Design Using an Ancient Tool for Igniting and Propagating Immune Tolerance: IDO as an Inducer and Amplifier of Regulatory T Cell Functions
Current Medicinal Chemistry Why should We Bother? Ethical and Social Issues in Individualized Medicine
Current Drug Targets Classical Neurotransmitters and Neuropeptides Involved in Parkinson's Disease: Focus on Anti-Parkinsonian Drugs
Current Drug Therapy Intracellular Signaling and Approaches to the Treatment of Schizophrenia and Associated Cognitive Impairment
Current Pharmaceutical Design Naturally Occurring NF-κB Inhibitors
Mini-Reviews in Medicinal Chemistry Editorial (Thematic Issue: Prevention Strategies Targeting Different Preclinical Stages of Alzheimer’s Disease)
Current Alzheimer Research Defining and Regulating Acute Inflammatory Lesion Formation during the Pathogenesis of Multiple Sclerosis and Experimental Autoimmune Encephalomyelitis
CNS & Neurological Disorders - Drug Targets Role of Connexins and Pannexins in Ischemic Stroke
Current Medicinal Chemistry Schizophrenia: From Dopamine to Glutamate and Back
Current Medicinal Chemistry Association between <i>Toxoplasma gondii</i> Infection and Headache: A Systematic Review and Meta-Analysis
Infectious Disorders - Drug Targets The Identification and Characterization of Excitotoxic Nerve-endings in Alzheimer Disease
Current Alzheimer Research Adrenomedullin-RAMP2 System in Cardiovascular Development and Homeostasis
Current Hypertension Reviews Glutamate Binding-Site Ligands of NMDA Receptors
Current Medicinal Chemistry Oxidative Stress in the Hypothalamus: the Importance of Calcium Signaling and Mitochondrial ROS in Body Weight Regulation
Current Neuropharmacology