Abstract
The transport of the molecules inside cells is a very important topic, especially in Drug Metabolism. The experimental testing of the new proteins for the transporter molecular function is expensive and inefficient due to the large amount of new peptides. Therefore, there is a need for cheap and fast theoretical models to predict the transporter proteins. In the current work, the primary structure of a protein is represented as a molecular Star graph, characterized by a series of topological indices. The dataset was made up of 2,503 protein chains, out of which 413 have transporter molecular function and 2,090 have no transporter function. These indices were used as input to several classification techniques to find the best Quantitative Structure Activity Relationship (QSAR) model that can evaluate the transporter function of a new protein chain. Among several feature selection techniques, the Support Vector Machine Recursive Feature Elimination allows us to obtain a classification model based on 20 attributes with a true positive rate of 83% and a false positive rate of 16.7%.
Keywords: QSAR, Star Graph, topological indices, transport protein, Support Vector Machine.
Current Topics in Medicinal Chemistry
Title:Kernel-Based Feature Selection Techniques for Transport Proteins Based on Star Graph Topological Indices
Volume: 13 Issue: 14
Author(s): Carlos Fernandez-Lozano, Marcos Gestal, Nieves Pedreira-Souto, Lucian Postelnicu, Julian Dorado and Cristian Robert Munteanu
Affiliation:
Keywords: QSAR, Star Graph, topological indices, transport protein, Support Vector Machine.
Abstract: The transport of the molecules inside cells is a very important topic, especially in Drug Metabolism. The experimental testing of the new proteins for the transporter molecular function is expensive and inefficient due to the large amount of new peptides. Therefore, there is a need for cheap and fast theoretical models to predict the transporter proteins. In the current work, the primary structure of a protein is represented as a molecular Star graph, characterized by a series of topological indices. The dataset was made up of 2,503 protein chains, out of which 413 have transporter molecular function and 2,090 have no transporter function. These indices were used as input to several classification techniques to find the best Quantitative Structure Activity Relationship (QSAR) model that can evaluate the transporter function of a new protein chain. Among several feature selection techniques, the Support Vector Machine Recursive Feature Elimination allows us to obtain a classification model based on 20 attributes with a true positive rate of 83% and a false positive rate of 16.7%.
Export Options
About this article
Cite this article as:
Fernandez-Lozano Carlos, Gestal Marcos, Pedreira-Souto Nieves, Postelnicu Lucian, Dorado Julian and Munteanu Robert Cristian, Kernel-Based Feature Selection Techniques for Transport Proteins Based on Star Graph Topological Indices, Current Topics in Medicinal Chemistry 2013; 13 (14) . https://dx.doi.org/10.2174/15680266113139990119
DOI https://dx.doi.org/10.2174/15680266113139990119 |
Print ISSN 1568-0266 |
Publisher Name Bentham Science Publisher |
Online ISSN 1873-4294 |
Call for Papers in Thematic Issues
Medicinal Chemistry Advancement in Life-Threatening Diseases
The current issue will highlight concise reports that specify ground-breaking insights, including the novel discovery of drug targets and their action mechanism or drugs of novel classes. These are projected to encourage medicinal chemistry future efforts to address the most challenging medical needs. The current issue highlights further efforts to ...read more
- 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
- Announcements
Related Articles
-
Preparation of Tiagabine HCl/2-HPβCD Complex Pellets by Extrusion-Spheronization Using Glycerol Monostearate as Pellet-Aid
Letters in Drug Design & Discovery Long-Term Benzodiazepine Use and Mortality: Are we Doing the Right Studies?
Current Drug Safety Herbal Medicine for Anxiety, Depression and Insomnia
Current Neuropharmacology MicroRNA Therapeutics in Neurological Disease
Current Pharmaceutical Design Abnormalities of Cortical Thickness in Pediatric Mesial Temporal Lobe Epilepsy with Hippocampal Sclerosis
Current Medical Imaging Nutraceuticals against Neurodegeneration: A Mechanistic Insight
Current Neuropharmacology Pharmacogenetics of Opioids for the Treatment of Acute Maternal Pain During Pregnancy and Lactation
Current Drug Metabolism Apoptosis in the Dentate Nucleus Following Kindling-induced Seizures in Rats
CNS & Neurological Disorders - Drug Targets Molecular Mechanisms Underlying Specificity of Excitotoxic Signaling in Neurons
Current Molecular Medicine Relevance of Excitable Media Theory and Retinal Spreading Depression Experiments in Preclinical Pharmacological Research
Current Neuropharmacology A Systematic Review of Plant-Derived Natural Compounds for Anxiety Disorders
Current Topics in Medicinal Chemistry GABAA Receptors in Normal Development and Seizures: Friends or Foes?
Current Neuropharmacology The Role of Spiritual Health Experience with Intensity and Duration of Labor Pain While Childbearing and Postpartum
Current Women`s Health Reviews Preface
Current Drug Targets - CNS & Neurological Disorders Melatonin, A Natural Programmed Cell Death Inducer in Cancer
Current Medicinal Chemistry Phytochemical and Biological Activities of five Turanecio Hamzaoglu (Asteraceae) Species from Turkey
Current Enzyme Inhibition Modulators of Networks: Molecular Targets of Arterial Calcification Identified in Man and Mice
Current Pharmaceutical Design Acid-Sensing Ion Channels Structural Aspects, Pathophysiological Importance and Experimental Mutational Data Available Across Various Species to Target Human ASIC1
Current Drug Targets Cardiac ATP-Sensitive Potassium Channels: A Potential Target for an Anti-Ischaemic Pharmacological Strategy
Cardiovascular & Hematological Agents in Medicinal Chemistry Antidepressant Brain Stimulation Techniques
Current Psychiatry Reviews