Abstract
Study of interactions between drugs and target proteins is an essential step in genomic drug discovery. It is very hard to determine the compound-protein interactions or drug-target interactions by experiment alone. As supplementary, effective prediction model using machine learning or data mining methods can provide much help. In this study, a prediction method based on Nearest Neighbor Algorithm and a novel metric, which was obtained by combining compound similarity and functional domain composition, was proposed. The target proteins were divided into the following groups: enzymes, ion channels, G protein-coupled receptors, and nuclear receptors. As a result, four predictors with the optimal parameters were established. The overall prediction accuracies, evaluated by jackknife cross-validation test, for four groups of target proteins are 90.23%, 94.74%, 97.80%, and 97.51%, respectively, indicating that compound similarity and functional domain composition are very effective to predict drug-target interaction networks.
Keywords: Compound similarity, drug-target interaction network, functional domain composition, jackknife cross-validation test, Matthew's correlation coefficient, nearest neighbor algorithm, SMILES, MACC, SBASE-A
Medicinal Chemistry
Title: Using Compound Similarity and Functional Domain Composition for Prediction of Drug-Target Interaction Networks
Volume: 6 Issue: 6
Author(s): Lei Chen, Zhi-Song He, Tao Huang and Yu-Dong Cai
Affiliation:
Keywords: Compound similarity, drug-target interaction network, functional domain composition, jackknife cross-validation test, Matthew's correlation coefficient, nearest neighbor algorithm, SMILES, MACC, SBASE-A
Abstract: Study of interactions between drugs and target proteins is an essential step in genomic drug discovery. It is very hard to determine the compound-protein interactions or drug-target interactions by experiment alone. As supplementary, effective prediction model using machine learning or data mining methods can provide much help. In this study, a prediction method based on Nearest Neighbor Algorithm and a novel metric, which was obtained by combining compound similarity and functional domain composition, was proposed. The target proteins were divided into the following groups: enzymes, ion channels, G protein-coupled receptors, and nuclear receptors. As a result, four predictors with the optimal parameters were established. The overall prediction accuracies, evaluated by jackknife cross-validation test, for four groups of target proteins are 90.23%, 94.74%, 97.80%, and 97.51%, respectively, indicating that compound similarity and functional domain composition are very effective to predict drug-target interaction networks.
Export Options
About this article
Cite this article as:
Chen Lei, He Zhi-Song, Huang Tao and Cai Yu-Dong, Using Compound Similarity and Functional Domain Composition for Prediction of Drug-Target Interaction Networks, Medicinal Chemistry 2010; 6 (6) . https://dx.doi.org/10.2174/157340610793563983
DOI https://dx.doi.org/10.2174/157340610793563983 |
Print ISSN 1573-4064 |
Publisher Name Bentham Science Publisher |
Online ISSN 1875-6638 |
Call for Papers in Thematic Issues
Carbohydrates in Computational and Medicinal Chemistry
Carbohydrates are the most essential organic molecules and are involved in the maintenance of various physiological and metabolic processes in living organisms. Carbohydrate-based compounds have come to the attention of researchers because of their significant contributions to biological functions, such as cell development and cell proliferation, connections between several cells, ...read more
Recent Advances in the Medicinal Chemistry of Cancer
Scope of the Thematic Issue: Correlation between structure and function is one of the important aspects of the success of anti-cancer compounds associated with their structure-activity interactions, physiology, biochemical, molecular, and genetic processes. Overcoming these obstacles is key to obtaining further insights into developments in rational drug design, bioorganic chemistry, ...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
Related Articles
-
Current State of the Art of New Tubulin Inhibitors in the Clinic
Current Clinical Pharmacology Biomarkers in Molecularly Targeted Therapy for Cancer
Recent Patents on Biomarkers Detection of Hepatitis B Virus-associated Hepatocellular Carcinoma Disease Using Hybrid Hierarchical k-Means Clustering and SVM Algorithm
Current Bioinformatics Current Understanding of the Potential of Proteomics and Metabolomics Approaches in Cancer Chemoresistance: A Focus on Multiple Myeloma
Current Topics in Medicinal Chemistry Role of Cellular Biomolecules in Screening, Diagnosis and Treatment of Colorectal Cancer
Current Drug Metabolism The Rb Pathway and Cancer Therapeutics
Current Drug Targets VEGF Inhibitors and Prostate Cancer Therapy
Current Molecular Pharmacology The Rational Design of Anticancer Platinum Complexes: The Importance of the Structure-Activity Relationship
Current Medicinal Chemistry Biomarkers to Assess the Targeting of DNA Repair Pathways to Augment Tumor Response to Therapy
Current Molecular Medicine Notch Signaling Proteins: Legitimate Targets for Cancer Therapy
Current Protein & Peptide Science Colorectal Cancer Microenvironment: Among Nutrition, Gut Microbiota, Inflammation and Epigenetics
Current Pharmaceutical Design Current, New and Future Therapeutic Targets in Inflammatory Bowel Disease: A Systematic Review
Current Pharmaceutical Design Points of Therapeutic Intervention Along the Wnt Signaling Pathway in Hepatocellular Carcinoma
Anti-Cancer Agents in Medicinal Chemistry Editorial [Hot topic: QSAR and Complex Networks in Pharmaceutical Design, Microbiology, Parasitology, Toxicology, Cancer and Neurosciences (Executive Editor: Humberto Gonzalez-Diaz)]
Current Pharmaceutical Design Hepatocyte Growth Factor Signaling in Cancer Metastasis
Current Signal Transduction Therapy Crystal Structures and Cytotoxicity of Ortho-Xylene Linked Bis-benzimidazolium Salts
Medicinal Chemistry Quality Survival with Fertility after Gynaecological and other Cancers
Current Women`s Health Reviews Challenges and Opportunities from Basic Cancer Biology for Nanomedicine for Targeted Drug Delivery
Current Cancer Drug Targets Structure-Based Design of Novel Anti-Cancer Agents TargetingAurora Kinases
Current Medicinal Chemistry - Anti-Cancer Agents Fucose Specific Lectins in Cancer Research and Diagnosis
Drug Design Reviews - Online (Discontinued)