Abstract
The identification of endocrine-disrupting chemicals (EDCs) is one of the important goals of environmental chemical hazard screening. The adverse health effects of EDCs in humans have been demonstrated to involve the developmental, reproductive, neurological, cardiovascular, metabolic, and immune systems.
The present study reports QSAR classification studies on a large database comprising 8,212 compounds collected from the Estrogenic Activity Database and National Center for Biotechnology Information Database. In this study, four classification models (Bayesian Categorization Model with molecular fingerprints or molecular descriptors as an input and Neural Classification Models with and without Bayesian regularization) were used. Evaluation of these binomial classification methods indicated that the Bayesian method (Bayesian QSAR) works as an excellent method for prediction with fingerprints used as input. In the case of the multilayer perceptron with molecular descriptors as inputs, changing the training mode by introducing a Bayesian regularization algorithm significantly improved ANNs’ predictive power. Our goal was to test two popular classification methods suitable for processing large data sets. Such datasets were required to ensure the prediction performances and applicability of the models as a virtual screening tool for an extensive database.
Keywords: ANN, bayesian categorization model, endocrine disruptor, endocrine disruptors knowledge base, molecular fingerprints, QSAR, virtual screening, molecular descriptors.
Combinatorial Chemistry & High Throughput Screening
Title:ANN and Bayesian Classification Models for Virtual Screening of Endocrine-Disrupting Chemicals
Volume: 17 Issue: 5
Author(s): Piotr Nowicki, Jolanta Klos and Zenon Kokot
Affiliation:
Keywords: ANN, bayesian categorization model, endocrine disruptor, endocrine disruptors knowledge base, molecular fingerprints, QSAR, virtual screening, molecular descriptors.
Abstract: The identification of endocrine-disrupting chemicals (EDCs) is one of the important goals of environmental chemical hazard screening. The adverse health effects of EDCs in humans have been demonstrated to involve the developmental, reproductive, neurological, cardiovascular, metabolic, and immune systems.
The present study reports QSAR classification studies on a large database comprising 8,212 compounds collected from the Estrogenic Activity Database and National Center for Biotechnology Information Database. In this study, four classification models (Bayesian Categorization Model with molecular fingerprints or molecular descriptors as an input and Neural Classification Models with and without Bayesian regularization) were used. Evaluation of these binomial classification methods indicated that the Bayesian method (Bayesian QSAR) works as an excellent method for prediction with fingerprints used as input. In the case of the multilayer perceptron with molecular descriptors as inputs, changing the training mode by introducing a Bayesian regularization algorithm significantly improved ANNs’ predictive power. Our goal was to test two popular classification methods suitable for processing large data sets. Such datasets were required to ensure the prediction performances and applicability of the models as a virtual screening tool for an extensive database.
Export Options
About this article
Cite this article as:
Nowicki Piotr, Klos Jolanta and Kokot Zenon, ANN and Bayesian Classification Models for Virtual Screening of Endocrine-Disrupting Chemicals, Combinatorial Chemistry & High Throughput Screening 2014; 17 (5) . https://dx.doi.org/10.2174/1386207317666140219115635
DOI https://dx.doi.org/10.2174/1386207317666140219115635 |
Print ISSN 1386-2073 |
Publisher Name Bentham Science Publisher |
Online ISSN 1875-5402 |

- 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
Related Articles
-
Epigenetic Regulation of ABCB1 Transporter Expression and Function
Current Pharmacogenomics and Personalized Medicine Biological Role of Formaldehyde, and Cycles Related to Methylation, Demethylation, and Formaldehyde Production
Mini-Reviews in Medicinal Chemistry Synthesis of Novel and Highly Functionalized 4-hydroxycoumarin Chalcone and their Pyrazoline Derivatives as Anti-Tuberculosis Agents
Letters in Drug Design & Discovery A Study on Identification of Nutraceutical Value of New Imidazolone Schiff Base Analogues
Letters in Drug Design & Discovery Formamide Derivatives of Resveratrol: Synthesis, Characterization and Cytotoxicity
Letters in Drug Design & Discovery Combinatorial Nanoparticles for Cancer Diagnosis and Therapy
Current Medicinal Chemistry Prediction of Activities of BRAF (V600E) Inhibitors by SW-MLR and GA-MLR Methods
Current Computer-Aided Drug Design Electrochemical Evaluation of the Total Antioxidant Capacity of Yam Food Samples on a Polyglycine-Glassy Carbon Modified Electrode
Current Analytical Chemistry Topical Use of Sucralfate in Epithelial Wound Healing: Clinical Evidence and Molecular Mechanisms of Action
Recent Patents on Inflammation & Allergy Drug Discovery Paclitaxel Formulations: Challenges and Novel Delivery Options
Current Drug Delivery Antioxidant Properties of Hydroxycinnamic Acids: A Review of Structure- Activity Relationships
Current Medicinal Chemistry Colorectal Cancer – Increased Multidimensional Understanding of the Molecular Genesis
Current Cancer Therapy Reviews Understanding Heterogeneity in Supplementation Effects of Selenium in Men: A Study of Stratification Variables and Human Genetics in a Prospective Sample from New Zealand
Current Pharmacogenomics and Personalized Medicine Synthesis and Cytotoxicity Studies on Novel Piperazinylacetamides
Letters in Drug Design & Discovery Sodium Benzenesulfinates: Novel and Effective Organo Catalyst for Three Component Synthesis 5,6,7,8-Tetrahydro-4H-chromene Derivatives Under Ultrasound Irradiation
Letters in Organic Chemistry Arsenic Remediation Enhancement Techniques: A World Over Scenario
Current Environmental Engineering Modifications of Isoalantolactone Leading to Effective Anti-bacterial and Anti-viral Compounds
Letters in Drug Design & Discovery Elucidation of Cellular Metabolism Via Metabolomics and Stable-Isotope Assisted Metabolomics
Current Pharmaceutical Biotechnology Molecular Imaging Strategies for In Vivo Tracking of MicroRNAs: A Comprehensive Review
Current Medicinal Chemistry Differential Gene Expression of <i>ASUN, NEMF, PTPRC</i> and <i>DHX29</i>: Candidate Biomarkers for the Diagnosis of Active and Latent Tuberculosis
Infectious Disorders - Drug Targets