Abstract
Despite being identified as the most potent receptor related to vasoconstriction, human urotensin-II receptor (hUT) has not been fully explored as a target for the treatment of cardiovascular diseases. In view of this and with an aim to identify precise structural requirements for binding of hUT antagonists, we endeavoured to develop, for the first time, multivariate QSAR models using chemometric methods like partial least squares (PLS) and feed-forward neural network (FFNN). A set of 48 pyrrolidine derivatives having hUT binding affinity was used for multivariate model development. The accuracy and predictability of the developed models was evaluated using crossvalidation. The PLS model showed good correlation between selected descriptors and Ki values (r2 =0.745 and r2 (CV) =0.773). However, the predictive performance of FFNN was better than the PLS technique with r2 =0.810. The study clearly suggests the role of lipophilic and steric descriptors in the ligand-hUT interactions. The QSAR models generated can be successfully extended to predict the binding affinities and for the effective design of novel hUT antagonists.
Keywords: QSAR, urotensin-II, PLS, FFNN, descriptors, TSAR.
Current Computer-Aided Drug Design
Title:Use of Diverse Chemometric and Validation Methods to Accurately Predict Human Urotensin-II Receptor Antagonist Activity
Volume: 11 Issue: 4
Author(s): Anubhuti Pandey, Sarvesh Paliwal, Rakesh Yadav and Shailendra Paliwal
Affiliation:
Keywords: QSAR, urotensin-II, PLS, FFNN, descriptors, TSAR.
Abstract: Despite being identified as the most potent receptor related to vasoconstriction, human urotensin-II receptor (hUT) has not been fully explored as a target for the treatment of cardiovascular diseases. In view of this and with an aim to identify precise structural requirements for binding of hUT antagonists, we endeavoured to develop, for the first time, multivariate QSAR models using chemometric methods like partial least squares (PLS) and feed-forward neural network (FFNN). A set of 48 pyrrolidine derivatives having hUT binding affinity was used for multivariate model development. The accuracy and predictability of the developed models was evaluated using crossvalidation. The PLS model showed good correlation between selected descriptors and Ki values (r2 =0.745 and r2 (CV) =0.773). However, the predictive performance of FFNN was better than the PLS technique with r2 =0.810. The study clearly suggests the role of lipophilic and steric descriptors in the ligand-hUT interactions. The QSAR models generated can be successfully extended to predict the binding affinities and for the effective design of novel hUT antagonists.
Export Options
About this article
Cite this article as:
Pandey Anubhuti, Paliwal Sarvesh, Yadav Rakesh and Paliwal Shailendra, Use of Diverse Chemometric and Validation Methods to Accurately Predict Human Urotensin-II Receptor Antagonist Activity, Current Computer-Aided Drug Design 2015; 11 (4) . https://dx.doi.org/10.2174/1874609809666151223093650
DOI https://dx.doi.org/10.2174/1874609809666151223093650 |
Print ISSN 1573-4099 |
Publisher Name Bentham Science Publisher |
Online ISSN 1875-6697 |
- 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
-
Prediction and Diagnosis of Post Transplant Diabetes
Current Diabetes Reviews Cell-Penetrating Peptides as a Potential Drug Delivery System for Effective Treatment of Diabetes
Current Pharmaceutical Design Neutrophil Gelatinase-Associated Lipocalin (NGAL) as a Biomarker for Acute Kidney Injury
Recent Patents on Biomarkers Novel Treatments in Diabetic Nephropathy
Current Hypertension Reviews Emerging Roles for Metabolic Engineering - Understanding Primitive and Complex Metabolic Models and Their Relevance to Healthy and Diseased Kidney Podocytes
Current Chemical Biology Aldose Reductase as a Drug Target for Treatment of Diabetic Nephropathy: Promises and Challenges
Protein & Peptide Letters Hypertension and Diabetes: Emphasis on the Renin-Angiotensin System in Atherosclerosis
Current Hypertension Reviews Atherogenesis in Renal Patients: A Model of Vascular Disease?
Current Vascular Pharmacology New Insights into Redox-Modulated Cell Signaling
Current Pharmaceutical Design Vitamin D Therapy in Cardiac Hypertrophy and Heart Failure
Current Pharmaceutical Design Insulin Resistance, Non-alcoholic Fatty Liver Disease and Hepatitis C Virus Infection
Reviews on Recent Clinical Trials An Updated Review for the Diabetic Wound Healing Systems
Current Drug Targets Pharmacotherapy in Systemic Lupus Erythematosus
Current Rheumatology Reviews Cardiovascular Drug Development Using Radiopharmaceuticals
Current Pharmaceutical Design Cerebrovascular Complications of Diabetes: SGLT-2 Inhibitors as a Promising Future Therapeutics
Current Drug Targets Curcumin: Not So Spicy After All
Mini-Reviews in Medicinal Chemistry Adverse Effects of Statins - Mechanisms and Consequences
Current Drug Safety Low Baseline Urine Creatinine Excretion Rate Predicts Poor Outcomes among Critically Ill Acute Stroke Patients
Current Neurovascular Research Early Occurrence Cases of Diabetes Mellitus: Clinical Picture in Two Major Tertiary Care Hospitals in India
Current Diabetes Reviews In Vivo Treatment Efficacy of Essential Oil Isolated from Seeds of <i>Momordica charantia</i> in Streptozotocin-Induced Diabetes Mellitus
Recent Patents on Biotechnology