Abstract
Background: Quantitative Structure Activity Relationship (QSAR) methods based on machine learning play a vital role in predicting biological effect.
Objective: Considering the characteristics of the binding interface between ligands and the inhibitory neurotransmitter Gamma-Aminobutyric Acid A(GABAA) receptor, we built a QSAR model of ligands that bind to the human GABAA receptor.
Methods: After feature selection with Mean Decrease Impurity, we selected 53 from 1,286 docked ligand molecular descriptors. Three QSAR models are built using a gradient boosting regression tree algorithm based on the different combinations of docked ligand molecular descriptors and ligand receptor interaction characteristics.
Results: The features of the optimal QSAR model contain both the docked ligand molecular descriptors and ligand-receptor interaction characteristics. The Leave-One-Out-Cross-Validation (Q2 LOO) of the optimal QSAR model is 0.8974, the Coefficient of Determination (R2) for the testing set is 0.9261, the Mean Square Error (MSE) is 0.1862. We also used this model to predict the pIC50 of two new ligands, the differences between the predicted and experimental pIC50 are -0.02 and 0.03, respectively.
Conclusion: We found the BELm2, BELe2, MATS1m, X5v, Mor08v, and Mor29m are crucial features, which can help to build the QSAR model more accurately.
Keywords: QSAR, GABAA, GBRT, mean decrease impurity, random forests, ligand-receptor interaction characteristics, pIC50.
Current Computer-Aided Drug Design
Title:The Quantitative Structure-Activity Relationships between GABAA Receptor and Ligands based on Binding Interface Characteristic
Volume: 17 Issue: 6
Author(s): Shu Cheng and Yanrui Ding*
Affiliation:
- School of Science, Jiangnan University, Wuxi, Jiangsu, 214122,China
Keywords: QSAR, GABAA, GBRT, mean decrease impurity, random forests, ligand-receptor interaction characteristics, pIC50.
Abstract:
Background: Quantitative Structure Activity Relationship (QSAR) methods based on machine learning play a vital role in predicting biological effect.
Objective: Considering the characteristics of the binding interface between ligands and the inhibitory neurotransmitter Gamma-Aminobutyric Acid A(GABAA) receptor, we built a QSAR model of ligands that bind to the human GABAA receptor.
Methods: After feature selection with Mean Decrease Impurity, we selected 53 from 1,286 docked ligand molecular descriptors. Three QSAR models are built using a gradient boosting regression tree algorithm based on the different combinations of docked ligand molecular descriptors and ligand receptor interaction characteristics.
Results: The features of the optimal QSAR model contain both the docked ligand molecular descriptors and ligand-receptor interaction characteristics. The Leave-One-Out-Cross-Validation (Q2 LOO) of the optimal QSAR model is 0.8974, the Coefficient of Determination (R2) for the testing set is 0.9261, the Mean Square Error (MSE) is 0.1862. We also used this model to predict the pIC50 of two new ligands, the differences between the predicted and experimental pIC50 are -0.02 and 0.03, respectively.
Conclusion: We found the BELm2, BELe2, MATS1m, X5v, Mor08v, and Mor29m are crucial features, which can help to build the QSAR model more accurately.
Export Options
About this article
Cite this article as:
Cheng Shu and Ding Yanrui *, The Quantitative Structure-Activity Relationships between GABAA Receptor and Ligands based on Binding Interface Characteristic, Current Computer-Aided Drug Design 2021; 17 (6) . https://dx.doi.org/10.2174/1573409916666200724153240
| DOI https://dx.doi.org/10.2174/1573409916666200724153240 |
Print ISSN 1573-4099 |
| Publisher Name Bentham Science Publisher |
Online ISSN 1875-6697 |
Call for Papers in Thematic Issues
Artificial Intelligence in Biomedical Research: Enhancing Data Analysis for Drug Discovery and Development
This thematic issue highlights the transformative impact of Artificial Intelligence (AI), with a particular focus on Machine Learning (ML) and Deep Learning (DL) techniques, in advancing biomedical research. As a result of these cutting-edge AI methodologies, drug discovery and development are revolutionizing data analysis. Rapid advances in artificial intelligence technologies ...read more
Computational Design of Plant-Based Therapeutics
Plant-based therapeutics have a long history of use in traditional medicine and are gaining renewed interest due to their potential for treating various diseases, including cancer, diabetes, and neurodegenerative disorders. However, the traditional approach to plant-based drug discovery is often time-consuming and resource-intensive. Computational methods offer a powerful and efficient ...read more
Computer-Aided Drug Discoveries for Emerging Diseases
Computer-aided drug design is a rapidly growing research field that continues to gain momentum, attracting increasing interest from the scientific community. This trend is largely driven by the growing utilization of machine learning and artificial intelligence in drug design and discovery. Artificial Intelligence has proven efficacy across various applications, including ...read more
Computer-aided Endoscopy and Colonoscopy Diagnostics (CAD) for Medical Instruments: Data Insights for Prediction and Classification in Medical Imaging
The increasing prevalence of gastrointestinal diseases, particularly colorectal cancer, highlights the critical role of endoscopy and colonoscopy in early detection and diagnosis. These procedures rely on the ability to interpret real-time visual and diagnostic data accurately and efficiently. However, the growing complexity of medical imaging data, coupled with the need ...read more
- Author Guidelines
- Bentham Author Support Services (BASS)
- 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
-
Safety and Efficacy of Levetiracetam for the Management of Levodopa- Induced Dyskinesia in Patients with Parkinson’s Disease: A Systematic Review
CNS & Neurological Disorders - Drug Targets Intracranial Non-traumatic Aneurysms in Children and Adolescents
Current Pediatric Reviews Exploring Cancer Therapeutics with Natural Products from African Medicinal Plants, Part II: Alkaloids, Terpenoids and Flavonoids
Anti-Cancer Agents in Medicinal Chemistry Structure-Based Design of Benzimidazole Sugar Conjugates: Synthesis, SAR and In Vivo Anti-inflammatory and Analgesic Activities
Medicinal Chemistry Management of Incidental Findings in the Era of Next-generation Sequencing
Current Genomics Evaluating a Child with Partial Developmental Delay (ParDD), Global Developmental Delay (GDD)/Mental Retardation (MR): Clinical Expertise Based or Evidence-Based?
Current Pediatric Reviews Recent Patents and Discovery of Anti-inflammatory Agents from Marine Source
Recent Patents on Inflammation & Allergy Drug Discovery Synthesis, Anticonvulsant Evaluation of 2,3,4,5-Tetrahydro-7-alkoxy-1H-2-benzazepin-1-ones
Letters in Drug Design & Discovery <i>Ajuga</i> L.: A Systematic Review on Chemical Composition, Phytopharmacological and Biological Potential
Current Bioactive Compounds Asymmetric Dimethylarginine: Clinical Significance and Novel Therapeutic Approaches
Current Medicinal Chemistry Pharmacogenetics of Drug Transporters and Its Impact on the Pharmacotherapy
Current Topics in Medicinal Chemistry CSF as a Surrogate for Assessing CNS Exposure: An Industrial Perspective
Current Drug Metabolism Preface:
Current Topics in Medicinal Chemistry Identification of Novel Anti-inflammatory Agents from Ayurvedic Medicine for Prevention of Chronic Diseases: “Reverse Pharmacology” and “Bedside to Bench” Approach
Current Drug Targets Novel Therapeutic Targets in Neuropsychiatric Disorders: The Neuroepigenome
Current Pharmaceutical Design Immune Responses to Adeno-Associated Virus Vectors
Current Gene Therapy Molecular Recognisation of 3a, 4-Dihydro-3-H-Indeno [1, 2-C] Pyrazole-2- Carboxamide/Carbothioamide Anticonvulsant Analogues Towards GABA-Aminotransferase- An in Silico Approach
Central Nervous System Agents in Medicinal Chemistry New Insights into the Roles of Endolysosomal Cathepsins in the Pathogenesis of Alzheimers Disease: Cathepsin Inhibitors as Potential Therapeutics
CNS & Neurological Disorders - Drug Targets Targeting Cytokines for Morphine Tolerance: A Narrative Review
Current Neuropharmacology GPCR Allosteric Modulators: Mechanistic Advantages and Therapeutic Applications
Current Topics in Medicinal Chemistry






