Abstract
It is not always possible to build predictive Quantitative Structure-Activity Relationships (QSAR) models for a given chemical dataset. In this work, we propose several statistical criteria, which can with high confidence answer a question, whether it is possible to build a predictive model for a dataset prior to actual modeling, i.e. to establish, whether the dataset is modelable. Calculation of these criteria is fast, and using them in QSAR studies could dramatically reduce modelers’ time and efforts, as well as computational resources necessary to build QSAR models for at least some datasets, especially for those which are not modelable. The calculation of modelability criteria is based on the k-nearest neighbors approach. For all datasets, as modelability criteria we have proposed dataset diversity (MODI_DIV) and new activity cliff indices (MODI_ACI). For datasets with binary end points, as modelability criteria we have proposed the correct classification rate (MODI_CCR) CCR = 0.5(sensitivity + specificity) for leave-one-out (LOO) cross-validation in the entire descriptor space, and correct classification rate for similarity search (MODI_ssCCR) in the entire descriptor space with leave 20 %-out (five-fold) cross-validation. For binary datasets, all these modelability criteria were tested on 42 datasets with previously generated QSAR models. Two latter criteria (MODI_CCR and MODI_ssCCR) were found to have high correlation with the predictivity of QSAR models (QSAR_CCR) and were additionally tested on 60 ToxCast end points with QSAR modeling results published recently (Thomas RS, Black MB, Li L, Healy E, Chu T-M, Bao W, Andersen MD, Wolfinger RD. Toxicol Sci: Off JSoc Toxicol 128(2):398–417, 2012). These modelability criteria can be used to classify many datasets as modelable or non-modelable. These criteria can be generalized to datasets with compounds belonging to more than two categories or classes. Additionally, criteria which take into account errors of prediction MODI_CAT i and MODI_CLASS i were proposed for datasets with compounds belonging to more than two (i > 2) categories or classes and continuous end points, divided into i > 2 bins. For continuous end points, LOO cross-validation q 2 for similarity search with different numbers of nearest neighbors in the entire descriptor space (MODI_q 2), and similarity search coefficient of determination (MODI_ssR 2) in the entire descriptor space were proposed as modelability criteria. Our preliminary studies demonstrated high correlation between the external predictivity of QSAR models (QSAR_R 2) and each of the MODI_q 2 and MODI_ssR 2. On the other hand, for datasets with any binary or continuous response variable, MODI_DIVs and MODI_ACIs were found to be less useful to establish dataset modelability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dragon Descriptors. http://www.talete.mi.it/products/dragon_description.htm. Accessed 21 Aug 2012
Molecular Operating Environment (MOE). http://www.chemcomp.com/software.htm. Accessed 21 Aug 2012
Molconn-Z descriptors. http://www.edusoft-lc.com/molconn. Accessed 08 Sept 2013
Mold2 descriptors. http://www.fda.gov/ScienceResearch/BioinformaticsTools/Mold2/default.htm. Accessed 08 Sept 2013
CDK Descriptor Calculator. http://pele.farmbio.uu.se/nightly/dnames.html. Accessed 08 Sept 2013
Volsurf Descriptors. http://www.moldiscovery.com/soft_volsurf.php. Accessed 08 Sept 2013
Adriana Descriptors. http://molecular-networks.com/node/45. Accessed 08 Sept 2013
Martin TM, Harten P, Venkatapathy R, Das S, Young DM (2008) A hierarchical clustering methodology for the estimation of toxicity. Toxicol Mech Method 18(2–3):251–266
Kuz’min VE, Artemenko AG, Muratov EN (2008) Hierarchical QSAR technology based on the simplex representation of molecular structure. J Comput Aided Mol Des 22(6–7):403–421
Isida Fragments. http://infochim.u-strasbg.fr/recherche/Download/FragmentorNomenclature_of_ISIDA_fragments_2011.pdf. Accessed 08 Sept 2013
Adams MJ (2004) Chemometrics in analytical spectroscopy. Royal Society of Chemistry, Cambridge, UK
Wold S, Sjöström M, Eriksson L (2001) PLS-regression: a basic tool of chemometrics. Chemometrics Intel Lab Syst 58(2):109–130
Zheng W, Tropsha A (2000) Novel variable selection quantitative structure–property relationship approach based on the k-nearest-neighbor principle. J Chem Inf Comput Sci 40(1):185–194
Vapnik VN (1995) The nature of statistical learning theory. Springer, New York
Quinlan JR (1986) Induction of decision trees. Mach Learn 1(1):81–106
Breiman L, Friedman JH, Olshen RA, Stone CJ (1998) Classification and regression trees. Chapman & Hall/CRC, New York
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Breiman L, Cutler A. Random forests. http://www.stat.berkeley.edu/~breiman/andomForests/. Accessed 08 Sept 2013
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
Chirico N, Gramatica P (2012) Real external predictivity of QSAR models. Part 2. New intercomparable thresholds for different validation criteria and the need for scatter plot inspection. J Chem Inf Model 52(8):2044–2058
Kovatcheva A, Golbraikh A, Oloff S, Feng J, Zheng W, Tropsha A (2005) QSAR modeling of datasets with enantioselective compounds using chirality sensitive molecular descriptors. SAR QSAR Environ Res 16(1–2):93–102
Tropsha A, Golbraikh A (2010) Predictive quantitative structure–activity relationships modeling: development and validation of QSAR models. In: Faulon J-L, Bender A (eds) Handbook of chemoinformatics algorithms. Chapman & Hall/CRC, London, pp 213–233
Kovatcheva A, Golbraikh A, Oloff S, Xiao Y-D, Zheng W, Wolschann P, Buchbauer G, Tropsha A (2004) Combinatorial QSAR of ambergris fragrance compounds. J Chem Inf Comput Sci 44(2):582–595
de Cerqueira Lima P, Golbraikh A, Oloff S, Xiao Y-D, Tropsha A (2006) Combinatorial QSAR modeling of P-glycoprotein substrates. J Chem Inf Model 46(3):1245–1254
ToxCastTM. http://epa.gov/ncct/toxcast. Accessed 11 Jan 2012
U.E.-N.C. for C. Toxicology, Computational Toxicology Research Program (CompTox). http://www.epa.gov/ncct/toxrefdb/. Accessed 08 Sept 2013
Thomas RS, Black MB, Li L, Healy E, Chu T-M, Bao W, Andersen MD, Wolfinger RD (2012) A comprehensive statistical analysis of predicting in vivo hazard using high-throughput in vitro screening. Toxicol Sci: Off J Soc Toxicol 128(2):398–417
Veber DF, Johnson SR, Cheng H-Y, Smith BR, Ward KW, Kopple KD (2002) Molecular properties that influence the oral bioavailability of drug candidates. J Med Chem 45(12):2615–2623
Shen M, LeTiran A, Xiao Y-D, Golbraikh A, Kohn H, Tropsha A (2002) Quantitative structure-activity relationship analysis of functionalized amino acid anticonvulsant agents using k nearest neighbor and simulated annealing PLS methods. J Med Chem 45(13):2811–2823
Goret M, Wang-Bell M, Golbraikh A, Tropsha A (2006) QSAR analysis of a dataset of 91 functionalized amino acids anticonvulsant agents using k nearest neighbor. Unpublished results
Boyd WA, McBride SJ, Rice JR, Snyder DW, Freedman JH (2010) A high-throughput method for assessing chemical toxicity using a Caenorhabditis elegans reproduction assay. Toxicol Appl Pharmacol 245(2):153–159
Sedykh A, Zhu H, Tang H, Zhang L, Richard A, Rusyn I, Tropsha A (2011) Use of in vitro HTS-derived concentration-response data as biological descriptors improves the accuracy of QSAR models of in vivo toxicity. Environ Health Persp 119(3):364–370
Tropsha A, Golbraikh A (2007) Predictive QSAR modeling workflow, model applicability domains, and virtual screening. Curr Pharm Des 13(34):3494–3504
Golbraikh A (2000) Molecular dataset diversity indices and their applications to comparison of chemical databases and QSAR analysis. J Chem Inf Comput Sci 40(2):414–425
Fourches D, Muratov E, Tropsha A (2010) Trust, but verify: on the importance of chemical structure curation in cheminformatics and QSAR modeling research. J Chem Inf Model 50(7):1189–1204
Guha R, Van Drie JH (2008) Structure–activity landscape index: identifying and quantifying activity cliffs. J Chem Inf Model 48(3):646–658
Zhang L, Sedykh A, Tripathi A, Zhu H, Afantitis A, Mouchlis VD, Melagraki G, Rusyn I, Tropsha A (2013) Identification of putative estrogen receptor-mediated endocrine disrupting chemicals using qsar- and structure-based virtual screening approaches. Toxicol Appl Pharmacol 23. doi:pii: S0041-008X(13)00216-0. 10.1016/j.taap.2013.04.032. Epub ahead of print
ChemBL databases. https://www.ebi.ac.uk/chembl/. Accessed 08 Sept 2013
PDSP database. http://pdsp.med.unc.edu/indexR.html. Accessed 08 Sept 2013
USEPA ECOTOX database (2008). http://cfpub.epa.gov/ecotox. Accessed 08 Sept 2013
U.E.-N.C. for C. Toxicology, Computational Toxicology Research Program (CompTox). http://www.epa.gov/ncct/toxcast/. Accessed 08 Sept 2013
CDK Descriptor Names. http://pele.farmbio.uu.se/nightly/dnames.html. Accessed 08 Sept 2013
R: Classification and Regression with Random Forest. http://rss.acs.unt.edu/Rdoc/library/randomForest/html/randomForest.html. 08 Sept 2013
Polishchuk PG, Muratov EN, Artemenko AG, Kolumbin OG, Muratov NN, Kuz’min VE (2009) Application of random forest approach to QSAR prediction of aquatic toxicity. J Chem Inf Model 49(11):2481–2488
Zhu H, Tropsha A, Fourches D, Varnek A, Papa E, Gramatica P, Ӧberg T, Phuong D, Cherkasov A, Tetko IV (2008) Combinatorial QSAR modeling of chemical toxicants tested against Tetrahymena pyriformis. J Chem Inf Model 48(4):766–784
Schultz TW (1997) TETRATOX: Tetrahymena pyriformis population growth impairment endpoint – a surrogate for fish lethality read more. http://informahealthcare.com/doi/abs/10.1080/105172397243079. Toxicol Mech Method 7(4):289–309
Schultz TW, Netzeva TI (2004) Development and evaluation of QSARs for ecotoxic endpoints: the benzene response-surface model for Tetrahymena toxicity. In: Cronin MTD, Livingstone DJ (eds) Modeling environmental fate and toxicity. CRC Press, Boca Raton
Schultz TW, TETRATOX. http://www.vet.utk.edu/TETRATOX/index.php. Accessed 08 June 2013
ChemiDplus Advanced Database National Library of Medicine 2011 (NLM). http://chem.sis.nlm.nih.gov/chemidplus/. Accessed 24 Feb 2011
USEPA, User’s Guide for T.E.S.T. (Toxicity Estimation Software Tool). http://www.epa.gov/ORD/NRMRL/std/cppb/qsar/testuserguide.pdf. Accessed 27 Oct 2009
Zhu H, Martin TM, Ye L, Sedykh A, Young DM, Tropsha A (2009) Quantitative structure-activity relationship modeling of rat acute toxicity by oral exposure. Chem Res Toxicol 22(12):1913–1921
Zhu H, Ye L, Richard A, Golbraikh A, Wright FA, Rusyn I, Tropsha A (2009) A novel two-step hierarchical quantitative structure-activity relationship modeling work flow for predicting acute toxicity of chemicals in rodents. Environ Health Persp 117(8):1257–1264
Martin TM, Harten P, Young DM, Muratov EN, Golbraikh A, Zhu H, Tropsha A (2012) Does rational selection of training and test sets improve the outcome of QSAR modeling? J Chem Inf Model 52(10):2570–2578
Hamelink JL (1977) Current bioconcentration test methods and theory. In: Mayer FL, Hamelink JL (eds) Aquatic toxicology and hazard evaluation. ASTM STP 634, American Society for Testing and Materials, Baltimore, pp 149–161
OEHHA Toxicity Criteria Database. http://www.oehha.ca.gov/risk/ChemicalDB/index.asp. Accessed 08 May 2013
Regional Screening Levels | Region 9: Superfund | US EPA. http://www.epa.gov/region9/superfund/prg/. Accessed 08 May 2013
O. US EPA, Integrated Risk Information System (IRIS). http://www.epa.gov/iris/. Accessed 08 May 2013
O. of P.P. US EPA, Pesticide Reregistration Status | Pesticides | US EPA. http://www.epa.gov/oppsrrd1/reregistration/status.htm. Accessed 08 May 2013
Pharmaceutical Press. Martindale: the complete drug reference, 37th edn. http://www.pharmpress.com/product/9780853699330/martindale. Accessed 08 July 2013
U.E.-N.C. for C. Toxicology, Computational Toxicology Research Program (CompTox). http://www.epa.gov/ncct/dsstox/sdf_fdamdd.html. Accessed 08 Sept 2013
Tang H, Wang XS, Huang X-P, Roth X-P, Butler KV, Kozikowski AP, Jung M, Tropsha A (2009) Novel inhibitors of human histone deacetylase (HDAC) identified by QSAR modeling of known inhibitors, virtual screening, and experimental validation. J Chem Inf Model 49(2):461–476
Kennard RW, Stone L (1969) Computer aided design of experiments. Technometrics 11(1):137–148
Golbraikh A, Shen M, Xiao Z, Xiao Y-D, Lee K-H, Tropsha A (2003) Rational selection of training and test sets for the development of validated QSAR models. J Comput Aided Mol Des 17(2–4):241–253
Kuz’min VE, Artemenko AG, Muratov EN, Volineckaya IL, Makarov VA, Riabova OB, Wutzler P, Schmidtke M (2007) Quantitative structure-activity relationship studies of [(biphenyloxy)propyl]isoxazole derivatives. Inhibitors of human rhinovirus 2 replication. J Med Chem 50(17):4205–4213
Golbraikh A, Muratov E, Fourches D, Tropsha A. Data set modelability by QSAR. J Chem Inf Model. 8 Jan 2014 [Epub ahead of print]
Acknowledgements
The authors are thankful to Dr. Guiyu Zhao (AstraZeneca, Shanghai, China) for providing QSAR modeling results for 34 GPCRome datasets, Dr. Jessica Wignall (University of North Carolina at Chapel Hill) for providing the QSAR modeling results for 10 regulatory information datasets, and Dr. Jonathan Freedman (National Institute of Environmental Health Science, Research Triangle Park, NC) and Dr. Ruchir Shah (SciOme, LLC, Research Triangle Park, NC) for providing experimental results for C. Elegans datasets.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this chapter
Cite this chapter
Golbraikh, A., Fourches, D., Sedykh, A., Muratov, E., Liepina, I., Tropsha, A. (2014). Modelability Criteria: Statistical Characteristics Estimating Feasibility to Build Predictive QSAR Models for a Dataset. In: Leszczynski, J., Shukla, M. (eds) Practical Aspects of Computational Chemistry III. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-7445-7_7
Download citation
DOI: https://doi.org/10.1007/978-1-4899-7445-7_7
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4899-7444-0
Online ISBN: 978-1-4899-7445-7
eBook Packages: Chemistry and Materials ScienceChemistry and Material Science (R0)