Abstract
Identification of potential druggable targets utilizing protein-protein interactions network (PPIN) has been emerging as a hotspot in drug discovery and development research. However, it remains unclear whether the currently used PPIN topological properties are enough to discriminate the drug targets from non-drug targets. In this study, three-step classification models using different network topological properties were designed and implemented using support vector machine (SVM) to compare the enrichment of known drug targets from non-targets. Surprisingly, none of the models was able to identify more than 75% of the true targets in the test set. It appears that the currently used simple PPIN topological properties are not likely robust enough for prediction of potential drug targets with high confidence, which also echoes similarly unsatisfying prediction data reported previously. However, we proposed that quality and quantity improvement of the protein-protein interactions (PPI) data for model training will help increasing the prediction accuracy.
Keywords: Drug targets, protein-protein interactions network, support vector machine, network topological properties.
Combinatorial Chemistry & High Throughput Screening
Title:Are Topological Properties of Drug Targets Based on Protein-Protein Interaction Network Ready to Predict Potential Drug Targets?
Volume: 19 Issue: 2
Author(s): Shiliang Li, Xiaojuan Yu, Chuanxin Zou, Jiayu Gong and Xiaofeng Liu
Affiliation:
Keywords: Drug targets, protein-protein interactions network, support vector machine, network topological properties.
Abstract: Identification of potential druggable targets utilizing protein-protein interactions network (PPIN) has been emerging as a hotspot in drug discovery and development research. However, it remains unclear whether the currently used PPIN topological properties are enough to discriminate the drug targets from non-drug targets. In this study, three-step classification models using different network topological properties were designed and implemented using support vector machine (SVM) to compare the enrichment of known drug targets from non-targets. Surprisingly, none of the models was able to identify more than 75% of the true targets in the test set. It appears that the currently used simple PPIN topological properties are not likely robust enough for prediction of potential drug targets with high confidence, which also echoes similarly unsatisfying prediction data reported previously. However, we proposed that quality and quantity improvement of the protein-protein interactions (PPI) data for model training will help increasing the prediction accuracy.
Export Options
About this article
Cite this article as:
Li Shiliang, Yu Xiaojuan, Zou Chuanxin, Gong Jiayu and Liu Xiaofeng, Are Topological Properties of Drug Targets Based on Protein-Protein Interaction Network Ready to Predict Potential Drug Targets?, Combinatorial Chemistry & High Throughput Screening 2016; 19 (2) . https://dx.doi.org/10.2174/1386207319666151110122145
DOI https://dx.doi.org/10.2174/1386207319666151110122145 |
Print ISSN 1386-2073 |
Publisher Name Bentham Science Publisher |
Online ISSN 1875-5402 |
- 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
-
Curcumin: Structure-Activity Relationship Towards its Role as a Versatile Multi-Targeted Therapeutics
Mini-Reviews in Organic Chemistry Vitamin D Intervention Trials in Critical Illness
Inflammation & Allergy - Drug Targets (Discontinued) Nitric Oxide: State of the Art in Drug Design
Current Medicinal Chemistry Simultaneous And Extended Delivery Of Stavudine, Lamivudine And Nevirapine In Fixed Dose Combination Using Sandwiched Osmotic Tablets For Hiv Therapy
Current Drug Delivery From 2D to 3D - a New Dimension for Modelling the Effect of Natural Products on Human Tissue
Current Pharmaceutical Design The Effects of Nanoencapsulated Curcumin-Fe3O4 on Proliferation and hTERT Gene Expression in Lung Cancer Cells
Anti-Cancer Agents in Medicinal Chemistry Pharmacophore Modeling Methods in Focused Library Selection – Applications in the Context of a New Classification Scheme
Combinatorial Chemistry & High Throughput Screening Caring for HIV-Infected Patients in the ICU in The Highly Active Antiretroviral Therapy Era
Current HIV Research Subject Index To Volume 12
Current Pharmaceutical Design Dendritic Cells: A Double-Edge Sword in Atherosclerotic Inflammation
Current Pharmaceutical Design Maternal Sepsis: Current Approaches to Recognition and Clinical Management
Current Women`s Health Reviews Targeting the Human Thioredoxin System by Diverse Strategies to Treat Cancer and Other Pathologies
Recent Patents on DNA & Gene Sequences Natural Product-Derived Small Molecule Activators of Hypoxia-Inducible Factor-1 (HIF-1)
Current Pharmaceutical Design Prolyl Oligopeptidase: A Rising Star on the Stage of Neuroinflammation Research
CNS & Neurological Disorders - Drug Targets Visual and Quantitative Assessment of COVID-19 Pneumonia on Chest CT: The Relationship with Disease Severity and Clinical Findings
Current Medical Imaging Asthma and High Altitude: Is It Safe to Be and Work?
Current Respiratory Medicine Reviews Atherosclerosis as an Inflammatory Disease
Current Pharmaceutical Design Traditional Chinese Medicine - Sea Urchin
Mini-Reviews in Medicinal Chemistry Tachykinins and Neuropsychiatric Disorders
Current Drug Targets Editorial (Thematic Issue: From Nuisance to State-of-the-Art: FDG-PET/CT Imaging of Infection and Inflammation)
Current Molecular Imaging (Discontinued)