Skip to main content
SpringerLink
Log in

On the Development and Validation of QSAR Models

  • Protocol
  • First Online:
Computational Toxicology

Part of the book series: Methods in Molecular Biology ((MIMB,volume 930))

Abstract

The fundamental and more critical steps that are necessary for the development and validation of QSAR models are presented in this chapter as best practices in the field. These procedures are discussed in the context of predictive QSAR modelling that is focused on achieving models of the highest statistical quality and with external predictive power. The most important and most used statistical parameters needed to verify the real performances of QSAR models (of both linear regression and classification) are presented. Special emphasis is placed on the validation of models, both internally and externally, as well as on the need to define model applicability domains, which should be done when models are employed for the prediction of new external compounds.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Protocol
USD 49.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 169.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. REACH (2007) http://ec.europa.eu/environment/chemicals/reach/reach_intro.htm

  2. OECD Guidelines (2004) http://www.oecd.org/dataoecd/33/37/37849783.pdf

  3. Fourches D, Muratov E, Tropsha A (2010) Trust, but verify: on the importance of chemical structure curation in chemoinformatics and QSAR modelling research. J Chem Inf Model 50:1189–1204

    Article  PubMed  CAS  Google Scholar 

  4. Tropsha A (2010) Best practices for QSAR model development. Validation, and Exploitation Mol Inform 29:476–488

    CAS  Google Scholar 

  5. http://www.netsci.org/Resources/Software/Modeling/CADD/adapt.html

  6. http://oasis-lmc.org

  7. Katritzky AR, Karelson M, Petrukhin R CODESSA PRO, University of Florida 2001–2005. http://www.codessa-pro.com/

  8. MolConnZ (2003) Ver. 4.05, Hall Ass. Consult., Quincy, MA. http://www.edusoft-lc.com/molconn/

  9. DRAGON—Software for the calculation of molecular descriptors. Talete srl, Milan, Italy. (http://www.talete.mi.it/products/dragon_description.htm)

  10. http://openmopac.net/

  11. Todeschini R, Consonni V (2009) Molecular descriptors for chemoinformatics. Wiley-VCH, Weinheim

    Book  Google Scholar 

  12. (2002) HyperChem 7.03 Hypercube, Inc., Florida, USA. www.hyper.com

  13. Jackson JE (1991) A user’s guide to principal components. Wiley, New York

    Book  Google Scholar 

  14. Todeschini R, Consonni V, Maiocchi A (1999) The K correlation index: theory development and its application in chemometrics. Chemom Int Lab Syst 46:13–29

    Article  CAS  Google Scholar 

  15. Leardi R, Boggia R, Terrile M (1992) Genetic algorithms as a strategy for feature selection. J Chemom 6:267–281

    Article  CAS  Google Scholar 

  16. Kubinyi H (1996) Evolutionary variable selection in regression and PLS analyses. J Chemom 10:119–133

    Article  CAS  Google Scholar 

  17. Gramatica P, Pilutti P, Papa E (2004) Validated QSAR prediction of OH tropospheric degradability: splitting into training-test set and consensus modelling. J Chem Inf Comp Sci 44:1794–1802

    Article  CAS  Google Scholar 

  18. Papa E, Villa F, Gramatica P (2005) Statistically validated QSARs and theoretical descriptors for the modelling of the aquatic toxicity of organic chemicals in Pimephales promelas (Fathead Minnow). J Chem Inf Model 45:1256–1266

    Article  PubMed  CAS  Google Scholar 

  19. Liu H, Papa E, Gramatica P (2006) QSAR prediction of estrogen activity for a large set of diverse chemicals under the guidance of OECD principles. Chem Res Toxicol 19:1540–1548

    Article  PubMed  CAS  Google Scholar 

  20. Gramatica P, Giani E, Papa E (2007) Statistical external validation and consensus modeling, A QSPR case study for Koc prediction. J Mol Graph Model 25:755–766

    Article  PubMed  CAS  Google Scholar 

  21. Gramatica P (2009) Chemometric methods and theoretical molecular descriptors in predictive QSAR modeling of the environmental behaviour of organic pollutants. In: Puzyn T, Leszczynski J, Cronin MTD (eds) Recent advances in QSAR studies. Springer, New York

    Google Scholar 

  22. Bhhatarai B, Gramatica P (2010) Per- and poly-fluoro toxicity (LC50 inhalation) study in rat and mouse using QSAR modeling. Chem Res Toxicol 23:528–539

    Article  PubMed  CAS  Google Scholar 

  23. Eriksson L, Jaworska J, Worth A et al (2003) Methods for reliability, uncertainty assessment, and applicability evaluations of regression based and classification QSARs. Environ Health Perspect 111:1361–1375

    Article  PubMed  CAS  Google Scholar 

  24. Hawkins DM (2004) The problem of overfitting. J Chem Inf Comput Sci 44:1–12

    Article  PubMed  CAS  Google Scholar 

  25. Golbraikh A, Tropsha A (2002) Beware of q2. J Mol Graph Model 20:269–276

    Article  PubMed  CAS  Google Scholar 

  26. Tropsha A, Gramatica P, Gombar VK (2003) The importance of being earnest: validation is the absolute essential for successful application and interpretation of QSPR models. QSAR Comb Sci 22:69–77

    Article  CAS  Google Scholar 

  27. Gramatica P (2007) Principles of QSAR models validation: internal and external. QSAR Comb Sci 26:694–701

    Article  CAS  Google Scholar 

  28. Efron B (1979) Bootstrap methods, another look at the jackknife. Ann Stat 7:1–26

    Article  Google Scholar 

  29. Marengo E, Todeschini R (1992) A new algorithm for optimal distance-based experimental design. Chemom Int Lab Syst 16:37–44

    Article  CAS  Google Scholar 

  30. Golbraikh A, Tropsha A (2002) Predictive QSAR modeling based on diversity sampling of experimental datasets for the training and test set selection. J Comput Aid Mol Des 16:357–369

    Article  CAS  Google Scholar 

  31. Gasteiger J, Zupan J (1993) Neural networks in chemistry. Angew Chem Int Ed Engl 32(503):527

    Google Scholar 

  32. Shi LM, Fang H, Tong W et al (2001) QSAR models using a large diverse set of estrogens. J Chem Inf Comput Sci 41:186–195

    Article  PubMed  CAS  Google Scholar 

  33. Schuurmann G, Ebert RU, Chen J et al (2008) External validation and prediction employing the predictive squared correlation coefficients test set activity mean vs training set activity mean. J Chem Inf Model 48:2140–2145

    Article  PubMed  Google Scholar 

  34. Roy PP, Somnath P, Indrani M et al (2009) On two novel parameters for validation of predictive QSAR models. Molecules 14:1660–1701

    Article  PubMed  CAS  Google Scholar 

  35. Consonni V, Ballabio D, Todeschini R (2009) Comments on the definition of the Q2 parameter for QSAR validation. J Chem Inf Model 49:1669–1678

    Article  PubMed  CAS  Google Scholar 

  36. Consonni V, Ballabio D, Todeschini R (2010) Evaluation of model predictive ability by external validation techniques. J Chemom 24:194–201

    Article  CAS  Google Scholar 

  37. Nicola Chirico N, Gramatica P (2011) Real external predictivity of QSAR models: how to evaluate it? Comparison of different validation criteria and proposal of using the concordance correlation coefficient. J Chem Inf Model 51(9):2320–2335

    Article  PubMed  Google Scholar 

  38. Chirico N, Papa E, Kovarich S, Cassani S, Gramatica P (2011) QSARINS, software for QSAR MLR model calculation and validation, 2008–2012 University of Insubria, Varese, Italy. http://www.qsar.it

  39. Breiman L, Friedman JH, Olshen RA et al (1998) Classification and regression trees. Chapman & Hall, Boca Raton

    Google Scholar 

  40. Sharaf MA, Illman DL, Kowalski BR (1986) Chemometrics. Wiley Interscience, New York

    Google Scholar 

  41. Li J, Gramatica P (2010) Classification and identification of androgen receptor antagonists with various methods and consensus approach. J Chem Inf Mod 50:861–874

    Article  CAS  Google Scholar 

  42. Zhu H, Tropsha A, Fourches D et al (2008) Combinational QSAR modeling of chemical toxicants tested against Tetrahymena pyriformis. J Chem Inf Model 48:766–784

    Article  PubMed  CAS  Google Scholar 

  43. Netzeva TI, Worth AP, Aldenberg T et al (2005) Current status of methods for defining the applicability domain of (quantitative) structure–activity relationships. ATLA 33:155–173

    PubMed  CAS  Google Scholar 

  44. Atkinson AC (1985) Plots, transformations and regression. Clarendon, Oxford

    Google Scholar 

Download references

Acknowledgments

I wish to thank Dr. Nicola Chirico for his collaboration in preparing the Tables and Figures and for the implementation of QSARINS software.

Author information

Authors and Affiliations

  1. QSAR Research Unit in Environmental Chemistry and Ecotoxicology, Theoretical and Applied Sciences, University of Insubria, via Dunant 3, Varese, Italy

    Paola Gramatica

Authors
  1. Paola Gramatica
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Paola Gramatica .

Editor information

Editors and Affiliations

  1. School of Biomedical Engineering, Chemical & Biological Engineering, Colorado State University, Campus Delivery 1370, Fort Collins, 80523-1370, Colorado, USA

    Brad Reisfeld

  2. , Chemical & Biological Engineering, Colorado State University, Campus Delivery 1370, Fort Collins, 80523-1370, Colorado, USA

    Arthur N. Mayeno

Rights and permissions

Reprints and permissions

Copyright information

© 2013 Springer Science+Business Media, LLC

About this protocol

Cite this protocol

Gramatica, P. (2013). On the Development and Validation of QSAR Models. In: Reisfeld, B., Mayeno, A. (eds) Computational Toxicology. Methods in Molecular Biology, vol 930. Humana Press, Totowa, NJ. https://doi.org/10.1007/978-1-62703-059-5_21

Download citation

  • DOI: https://doi.org/10.1007/978-1-62703-059-5_21

  • Published:

  • Publisher Name: Humana Press, Totowa, NJ

  • Print ISBN: 978-1-62703-058-8

  • Online ISBN: 978-1-62703-059-5

  • eBook Packages: Springer Protocols

Publish with us

Policies and ethics

Search

Navigation