Best Practices for QSAR Model Development, Validation, and Exploitation

Tropsha, Alexander

doi:10.1002/minf.201000061

Cited by 1,589 publications

(1,282 citation statements)

References 67 publications

Supporting

Mentioning

1,214

Contrasting

Unclassified

Order By: Relevance

“…The most common internal validation techniques used in (Q)SAR studies are least squares fit (R2), chi-squared ( 2), root-mean squared error (RMSE), leave-one-out or leave-many-out cross validation, bootstrapping and Yrandomization (Veerasamy, et al). The use of external validation techniques, not in place of but alongside internal validation methods, is increasingly being recommended by researchers (Gramatica, 2007;Tropsha, 2010;Veerasamy, et al, 2011) andauthorities (OECD, 2007) for the assessment of (Q)SAR model reliability in the best possible and trustworthy way. Moreover, it is always beneficial to use more than one validation metrics to quantitatively measure the accuracy of the model prediction.…”

Section: Support Vector Machines (Svm)mentioning

confidence: 99%

(Q)SAR modelling of nanomaterial toxicity: A critical review

et al. 2015

View full text Add to dashboard Cite

There is an increasing recognition that nanomaterials pose a risk to human health, and that the novel engineered nanomaterials (ENMs) in the nanotechnology industry and their increasing industrial usage poses the most immediate problem for hazard assessment, as many of them remain untested. The large number of materials and their variants (different sizes and coatings for instance) that require testing and ethical pressure towards non-animal testing means that expensive animal bioassay is precluded, and the use of (quantitative) structure activity relationships ((Q)SAR) models as an alternative source of hazard information should be explored.(Q)SAR modelling can be applied to fill the critical knowledge gaps by making the best use of existing data, prioritize physicochemical parameters driving toxicity, and provide practical solutions to the risk assessment problems caused by the diversity of ENMs. This paper covers the core components required for successful application of (Q)SAR technologies to ENMs toxicity prediction, and summarizes the published nano-(Q)SAR studies and outlines the challenges ahead for nano-(Q)SAR modelling. It provides a critical review of (1) the present status of the availability of ENMs characterization/toxicity data, (2) the characterization of nanostructures that meets the need of (Q)SAR analysis, (3) the summary of published nano-(Q)SAR studies and their limitations, (4) the in silico tools for (Q)SAR screening of nanotoxicity and (5) the prospective directions for the development of nano-(Q)SAR models.

show abstract

Section: Support Vector Machines (Svm)mentioning

confidence: 99%

(Q)SAR modelling of nanomaterial toxicity: A critical review

et al. 2015

View full text Add to dashboard Cite

show abstract

“…However, several challenging issues remain, such as water-mediated protein-ligand interactions [42] and protein flexibility [43] . Currently, docking-guided QSAR models are widely used for lead optimization, whereas protein flexibility has not been taken into account in most studies [44] . In this work, an ensemble docking-guided 3D-QSAR approach is proposed for the EGFR TK, in an effort to avoid the disadvantages of the single structure-guided QSAR models.…”

Section: Discussionmentioning

confidence: 99%

Structure-based ensemble-QSAR model: a novel approach to the study of the EGFR tyrosine kinase and its inhibitors

Sun

Chen

et al. 2013

Acta Pharmacol Sin

View full text Add to dashboard Cite

Aim: To develop a novel 3D-QSAR approach for study of the epidermal growth factor receptor tyrosine kinase (EGFR TK) and its inhibitors. Methods: One hundred thirty nine EGFR TK inhibitors were classified into 3 clusters. Ensemble docking of these inhibitors with 19 EGFR TK crystal structures was performed. Three protein structures that showed the best recognition of each cluster were selected based on the docking results. Then, a novel QSAR (ensemble-QSAR) building method was developed based on the ligand conformations determined by the corresponding protein structures. Results: Compared with the 3D-QSAR model, in which the ligand conformations were determined by a single protein structure, ensemble-QSAR exhibited higher R2 (0.87) and Q2 (0.78) values and thus appeared to be a more reliable and better predictive model. Ensemble-QSAR was also able to more accurately describe the interactions between the target and the ligands. Conclusion: The novel ensemble-QSAR model built in this study outperforms the traditional 3D-QSAR model in rationality, and provides a good example of selecting suitable protein structures for docking prediction and for building structure-based QSAR using available protein structures.

show abstract

“…These guidelines have been summarized as best practices for QSAR [8]. In addition to these guidelines, in our previous research we pointed out the importance of the proper validation of QSAR models in VS conditions [9].…”

Section: Introductionmentioning

confidence: 99%

<strong>Virtual screening tailored ensembles of QSAR models for the discovery of dual A<sub>2A</sub> Adenosine Receptor Antagonists / Monoamine Oxidase B Inhibitors</strong>

Helguera

Pérez-Castillo

Cordeiro

et al. 2015

Proceedings of MOL2NET, International Conference on Multidisciplinary Sciences

View full text Add to dashboard Cite

Virtual Screening methodologies have emerged as efficient alternatives for the discovery of new drug candidates. At the same time, ensemble methods are nowadays frequently used to overcome the limitations of employing a single model in ligand-based drug design. However, many applications of ensemble methods to this area do not consider important aspects related to both virtual screening and the modeling process. During the application of ensemble methods to virtual screening the proper validation of the models in virtual screening conditions is often neglected. Frequently no analysis is performed of the diversity of the ensemble members or no considerations regarding the applicability domain of the base model are made. In this research we propose a method employing genetic algorithms optimization for the generation of virtual SciForum Mol2Net, 2015, 1(Section B), pages 1-10, Proceedings 2 http://sciforum.net/conference/mol2net-1 screening tailored ensembles that address problems in the current applications of ensemble methods to virtual screening. The proposed methodology is successfully applied to the generation of ensemble models for the ligand-based virtual screening of dual target A2A adenosine receptor antagonists and MAO-B inhibitors as potential Parkinson's disease therapeutics. .

show abstract

Best Practices for QSAR Model Development, Validation, and Exploitation

Cited by 1,589 publications

References 67 publications

(Q)SAR modelling of nanomaterial toxicity: A critical review

(Q)SAR modelling of nanomaterial toxicity: A critical review

Structure-based ensemble-QSAR model: a novel approach to the study of the EGFR tyrosine kinase and its inhibitors

<strong>Virtual screening tailored ensembles of QSAR models for the discovery of dual A<sub>2A</sub> Adenosine Receptor Antagonists / Monoamine Oxidase B Inhibitors</strong>

Contact Info

Product

Resources

About