Abstract
Protein-protein interactions (PPIs) are becoming highly attractive targets for drug discovery. Motivated by the rapid accumulation of PPI data in public database and the success stories concerning the targeting of PPIs, a machine-learning method based on sequence and structure properties was developed to access the druggability of PPIs. Here, a comprehensive non-redundant set of 34 druggable and 122 less druggable PPIs were firstly presented from the perspective of pockets. When tested by outer 5-fold cross-validation, the most representative model in discriminating the druggable PPIs from the less-druggable ones yielded an average accuracy of 88.24% (sensitivity of 82.38% and specificity of 92.00%). Moreover, a promising result was also obtained for the independent test set. Compared to other methods, the method gives a comparative performance, which is most likely due to the construction of a training set that encompasses less druggable PPIs and also the information of active pockets that have evolved to bind a natural ligand.
Keywords: Active pockets, druggability, protein-protein interactions, sequence features, structure features, support vector machine.
Current Pharmaceutical Design
Title:Predicting the Druggability of Protein-Protein Interactions Based on Sequence and Structure Features of Active Pockets
Volume: 21 Issue: 21
Author(s): Xu Dai, RunYu Jing, Yanzhi Guo, YongCheng Dong, YueLong Wang, Yuan Liu, XueMei Pu and Menglong Li
Affiliation:
Keywords: Active pockets, druggability, protein-protein interactions, sequence features, structure features, support vector machine.
Abstract: Protein-protein interactions (PPIs) are becoming highly attractive targets for drug discovery. Motivated by the rapid accumulation of PPI data in public database and the success stories concerning the targeting of PPIs, a machine-learning method based on sequence and structure properties was developed to access the druggability of PPIs. Here, a comprehensive non-redundant set of 34 druggable and 122 less druggable PPIs were firstly presented from the perspective of pockets. When tested by outer 5-fold cross-validation, the most representative model in discriminating the druggable PPIs from the less-druggable ones yielded an average accuracy of 88.24% (sensitivity of 82.38% and specificity of 92.00%). Moreover, a promising result was also obtained for the independent test set. Compared to other methods, the method gives a comparative performance, which is most likely due to the construction of a training set that encompasses less druggable PPIs and also the information of active pockets that have evolved to bind a natural ligand.
Export Options
About this article
Cite this article as:
Dai Xu, Jing RunYu, Guo Yanzhi, Dong YongCheng, Wang YueLong, Liu Yuan, Pu XueMei and Li Menglong, Predicting the Druggability of Protein-Protein Interactions Based on Sequence and Structure Features of Active Pockets, Current Pharmaceutical Design 2015; 21 (21) . https://dx.doi.org/10.2174/1381612821666150309143106
DOI https://dx.doi.org/10.2174/1381612821666150309143106 |
Print ISSN 1381-6128 |
Publisher Name Bentham Science Publisher |
Online ISSN 1873-4286 |
- 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
-
Riluzole Inhibits Proliferation, Migration and Cell Cycle Progression and Induces Apoptosis in Tumor Cells of Various Origins
Anti-Cancer Agents in Medicinal Chemistry Coenzyme Q10 Reduction with Statins: Another Pleiotropic Effect
Current Drug Therapy Ewing’s Sarcoma Cancer Stem Cell Targeted Therapy
Current Stem Cell Research & Therapy HER-2 Positive Breast Cancer: What Else Beyond Trastuzumab-Based Therapy?
Anti-Cancer Agents in Medicinal Chemistry Natural Products as Anticancer Agents
Current Drug Targets Metal Containing Cytostatics and Their Interaction with Cellular Thiol Compounds Causing Chemoresistance
Anti-Cancer Agents in Medicinal Chemistry Chest Pain in Children
Current Pediatric Reviews WT1 Peptide Vaccine as a Paradigm for “Cancer Antigen-Derived Peptide”-Based Immunotherapy for Malignancies: Successful Induction of Anti-Cancer Effect by Vaccination with a Single Kind of WT1 Peptide
Anti-Cancer Agents in Medicinal Chemistry Designing Novel Therapies Against Sarcomas in the Era of Personalized Medicine and Economic Crisis
Current Pharmaceutical Design Targeting the Atypical Chemokine Receptor ACKR3/CXCR7: Phase 1 - Phage Display Peptide Identification and Characterization
Current Topics in Medicinal Chemistry Acyclonucleosides, Modified Seco-Nucleosides, and Salicyl- or Catechol- Derived Acyclic 5-Fluorouracil O,N-Acetals: Antiproliferative Activities, Cellular Differentiation and Apoptosis
Current Medicinal Chemistry (Iso)Flav(an)ones, Chalcones, Catechins, and Theaflavins as Anticarcinogens: Mechanisms, Anti-Multidrug Resistance and QSAR Studies
Current Medicinal Chemistry Recent Advances in Improving Sub-Unit Vaccine Efficacy Using Cytokines as more Specific Immune Inducing Adjuvants
Anti-Inflammatory & Anti-Allergy Agents in Medicinal Chemistry Editorial (Thematic Issue: Embryonic Signaling Pathways as Potential Targets for the Treatment of Rhabdomyosarcoma)
Current Drug Targets Gene Directed Enzyme Prodrug Therapy for Ovarian Cancer: Could GDEPT Become a Promising Treatment Against Ovarian Cancer?
Anti-Cancer Agents in Medicinal Chemistry Targeting Sarcomas: Novel Biological Agents and Future Perspectives
Current Drug Targets Irreversible LSD1 Inhibitors: Application of Tranylcypromine and Its Derivatives in Cancer Treatment
Current Topics in Medicinal Chemistry Anti-Tumor Activity and Underlying Mechanism of Phomoxanthone B in MCF7 Cells
Anti-Cancer Agents in Medicinal Chemistry Subject Index Volume 6
Mini-Reviews in Medicinal Chemistry FOXO Transcription Factors and their Role in Disorders of the Female Reproductive Tract
Current Drug Targets