Improved Naive Bayesian Modeling of Numerical Data for Absorption, Distribution, Metabolism and Excretion (ADME) Property Prediction.

Klon, Anthony E.; Lowrie, Jeffrey F.; Diller, David J.

doi:10.1002/chin.200649215

Cited by 26 publications

(37 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Laplacian-corrected Bayesian classifier models were generated using Discovery Studio (version 3.0; Accelrys, San Diego, CA, USA) [19][20][21] . Bayesian categorization model is a statistical classification method, which use knowledge of probability and statistics based on Bayes' theorem (Eq 1):…”

Section: Modeling Methodsmentioning

confidence: 99%

Novel Bayesian classification models for predicting compounds blocking hERG potassium channels

Lü

Yin

et al. 2014

Acta Pharmacol Sin

View full text Add to dashboard Cite

Aim: A large number of drug-induced long QT syndromes are ascribed to blockage of hERG potassium channels. The aim of this study was to construct novel computational models to predict compounds blocking hERG channels. Methods: Doddareddy's hERG blockage data containing 2644 compounds were used, which divided into training (2389) and test (255) sets. Laplacian-corrected Bayesian classification models were constructed using Discovery Studio. The models were internally validated with the training set of compounds, and then applied to the test set for validation. Doddareddy's experimentally validated dataset with 60 compounds was used for external test set validation. Results: A Bayesian classification model considering the effects of four molecular properties (M w , PPSA, ALogP and pK a _basic) as well as extended-connectivity fingerprints (ECFP_14) exhibited a global accuracy (91%), parameter sensitivity (90%) and specificity (92%) in the test set validation, and a global accuracy (58%), parameter sensitivity (61%) and specificity (57%) in the external test set validation. Conclusion: The novel model is better than those in the literatures for predicting compounds blocking hERG channels, and can be used for large-scale prediction.

show abstract

Section: Modeling Methodsmentioning

confidence: 99%

Novel Bayesian classification models for predicting compounds blocking hERG potassium channels

Lü

Yin

et al. 2014

Acta Pharmacol Sin

View full text Add to dashboard Cite

show abstract

“…Laplacian-corrected Bayesian classifier models were generated using Discovery Studio (version 2.5.5; Accelrys, San Diego, CA). This approach uses a machine learning method with two-dimensional descriptors [as described previously for other applications (Rogers et al, 2005;Hassan et al, 2006;Klon et al, 2006;Bender et al, 2007;Prathipati et al, 2008)] to distinguish between compounds that are DILI-positive and those that are DILI-negative. Preliminary work evaluated separately different functional class fingerprint (FCFP) (of size 0 -20) descriptors alongside interpretable descriptors.…”

Section: Methodsmentioning

confidence: 99%

A Predictive Ligand-Based Bayesian Model for Human Drug-Induced Liver Injury

Ekins

Williams²,

Xu³

2010

Drug Metab Dispos

109

View full text Add to dashboard Cite

ABSTRACT:Drug-induced liver injury (DILI) is one of the most important reasons for drug development failure at both preapproval and postapproval stages. There has been increased interest in developing predictive in vivo, in vitro, and in silico models to identify compounds that cause idiosyncratic hepatotoxicity. In the current study, we applied machine learning, a Bayesian modeling method with extended connectivity fingerprints and other interpretable descriptors. The model that was developed and internally validated (using a training set of 295 compounds) was then applied to a large test set relative to the training set (237 compounds) for external validation. The resulting concordance of 60%, sensitivity of 56%, and specificity of 67% were comparable to results for internal validation. The Bayesian model with extended connectivity functional class fingerprints of maximum diameter 6 (ECFC_6) and interpretable descriptors suggested several substructures that are chemically reactive and may also be important for DILI-causing compounds, e.g., ketones, diols, and ␣-methyl styrene type structures. Using Smiles Arbitrary Target Specification (SMARTS) filters published by several pharmaceutical companies, we evaluated whether such reactive substructures could be readily detected by any of the published filters. It was apparent that the most stringent filters used in this study, such as the Abbott alerts, which captures thiol traps and other compounds, may be of use in identifying DILI-causing compounds (sensitivity 67%). A significant outcome of the present study is that we provide predictions for many compounds that cause DILI by using the knowledge we have available from previous studies. These computational models may represent cost-effective selection criteria before in vitro or in vivo experimental studies.

show abstract

“…Recently, computational models have been applied in the area of drug development such as studies modeling thermodynamic proxies , drug solubility simulation in human intestinal fluid (Fagerberg et al 2015), stability prediction in mouse liver microsomes (Perryman et al 2016), auto-oxidation predictions (Lienard et al 2015), sites of CYP2C9 metabolism prediction (Kingsley et al 2015), human skin permeability prediction (Baba et al 2015), blood-brain barrier penetration , and estimates of skin concentration levels after dermal exposure (Hatanaka et al 2015). Additionally, the absorption, distribution, metabolism, excretion, and toxicity (ADME/Tox) properties of molecules have been modeled by applying a variety of machine learning algorithms such as Bayesian modeling, (Klon et al 2006), Gaussian processes (Obrezanova et al 2007), and support vector machines (Zheng et al 2009). Predicting interactions with drug metabolizing enzymes such as CYP450s and transporters as well as predicting other ADME/Tox properties have been made possible by applying computational machine learning models and those studies have produced an increasing amounts of large data through the extensive use of combinatorial chemistry and high-throughput screening (Clark et al 2015).…”

Section: Drug Developmentmentioning

confidence: 99%

Deep learning: from chemoinformatics to precision medicine

Kim

2017

Journal of Pharmaceutical Investigation

View full text Add to dashboard Cite

Improved Naive Bayesian Modeling of Numerical Data for Absorption, Distribution, Metabolism and Excretion (ADME) Property Prediction.

Abstract: ChemInform is a weekly Abstracting Service, delivering concise information at a glance that was extracted from about 200 leading journals. To access a ChemInform Abstract, please click on HTML or PDF.

Cited by 26 publications

References 1 publication

Novel Bayesian classification models for predicting compounds blocking hERG potassium channels

Novel Bayesian classification models for predicting compounds blocking hERG potassium channels

A Predictive Ligand-Based Bayesian Model for Human Drug-Induced Liver Injury

Deep learning: from chemoinformatics to precision medicine

Contact Info

Product

Resources

About