Abstract
Information of protein quaternary structure can help to understand the biological functions of proteins. Because wet-lab experiments are both time-consuming and costly, we adopt a novel computational approach to assign proteins into 10 kinds of quaternary structures. By coding each protein using its biochemical and physicochemical properties, feature selection was carried out using Incremental Feature Selection (IFS) method. The thus obtained optimal feature set consisted of 97 features, with which the prediction model was built. As a result, the overall prediction success rate is 74.90% evaluated by Jackknife test, much higher than the overall correct rate of a random guess 10% (1/10). The further feature analysis indicates that protein secondary structure is the most contributed feature in the prediction of protein quaternary structure.
Keywords: Biochemical properties, Incremental Feature Selection;, Maximum Relevance, Minimum Redundancy, Physicochemical properties, Protein quaternary structure, Jackknife test, SVM, FDOD, NNA, mRMR, MaxRel feature, Predator, PredAcc, Peng's study
Protein & Peptide Letters
Title: Prediction of Protein Quaternary Structure with Feature Selection and Analysis Based on Protein Biological Features
Volume: 19 Issue: 1
Author(s): Le-Le Hu, Kai-Yan Feng, Lei Gu and Xiao-Jun Liu
Affiliation:
Keywords: Biochemical properties, Incremental Feature Selection;, Maximum Relevance, Minimum Redundancy, Physicochemical properties, Protein quaternary structure, Jackknife test, SVM, FDOD, NNA, mRMR, MaxRel feature, Predator, PredAcc, Peng's study
Abstract: Information of protein quaternary structure can help to understand the biological functions of proteins. Because wet-lab experiments are both time-consuming and costly, we adopt a novel computational approach to assign proteins into 10 kinds of quaternary structures. By coding each protein using its biochemical and physicochemical properties, feature selection was carried out using Incremental Feature Selection (IFS) method. The thus obtained optimal feature set consisted of 97 features, with which the prediction model was built. As a result, the overall prediction success rate is 74.90% evaluated by Jackknife test, much higher than the overall correct rate of a random guess 10% (1/10). The further feature analysis indicates that protein secondary structure is the most contributed feature in the prediction of protein quaternary structure.
Export Options
About this article
Cite this article as:
Hu Le-Le, Feng Kai-Yan, Gu Lei and Liu Xiao-Jun, Prediction of Protein Quaternary Structure with Feature Selection and Analysis Based on Protein Biological Features, Protein & Peptide Letters 2012; 19 (1) . https://dx.doi.org/10.2174/092986612798472866
DOI https://dx.doi.org/10.2174/092986612798472866 |
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
-
Possible Targets of Herbals for Type 3 Diabetes: A Review
Current Traditional Medicine Design and Structure of Peptide and Peptidomimetic Antagonists of Protein- Protein Interaction
Current Protein & Peptide Science Nucleic Acid Aptamers Against Protein Kinases
Current Medicinal Chemistry Adsorptive Stripping Voltammetry of Environmental Carcinogens
Current Analytical Chemistry New Chemoenzymatic Synthesis of (±)-N-(2-hydroxyethyl)-N,N-dime thyl- 2,3-bis(tetradecyloxy)-1-propanammonium Bromide (DMRIE)
Letters in Organic Chemistry Evaluation of Alkylating and Intercalating Properties of Mannich Bases for Cytotoxic Activity
Letters in Drug Design & Discovery Piperine: Medicinal, Analytical and Therapeutics perspective
Current Bioactive Compounds Biological Activities of Natural and Engineered Cyclotides, a Novel Molecular Scaffold for Peptide-Based Therapeutics
Current Molecular Pharmacology A SELDI-TOF-MS Study in Lacunar Stroke with Subsequent Haptoglobin Phenotyping
Current Neurovascular Research Miniaturized Spectrophotometric Method for Quantification of Tannins in Pomegranate (Punica granatum L.) Fruit Peel Dried Extracts
Current Analytical Chemistry Recent Advances of Metallocenes for Medicinal Chemistry
Mini-Reviews in Medicinal Chemistry Guanine-Quadruplexes Studied by Fluorescence Techniques
Current Analytical Chemistry A Review on Phytochemistry and Pharmacology of Medicinal as well as Poisonous Mushrooms
Mini-Reviews in Medicinal Chemistry Recent Progress in the Development of Quinoline Derivatives for the Exploitation of Anti-Cancer Agents
Anti-Cancer Agents in Medicinal Chemistry Glycosylated Antitumor Ether Lipids: Activity and Mechanism of Action
Anti-Cancer Agents in Medicinal Chemistry Spectral Methods of Characterizing the Conformational Changes of Glycated Goat Liver Cystatin
Current Proteomics Bcl-2 Family Proteins as Therapeutic Targets
Current Pharmaceutical Design Quantifying Gp96/Grp94 Complexes Preparations for Vaccines: a Key Step Often Inaccurate
Current Medicinal Chemistry Green Synthesis of Phosphoryl-2-Oxo-2H-Pyran via Three Component Reaction of Trialkyl Phosphites
Combinatorial Chemistry & High Throughput Screening An Update on the Synthesis and Applications of Bis(Naphthoquinones): An Important Class of Molecules against Infectious Diseases and other Conditions
Current Topics in Medicinal Chemistry