Conformal prediction to define applicability domain – A case study on predicting ER and AR binding

References

• OECD 2004. Available at http://www.oecd.org/env/ehs/risk-assessment/validationofqsarmodels.htm.
   Google Scholar
• Joint Meeting of the Chemicals Committee and Working Party on Chemicals, Pesticides and Biotechnology, 2004. Available at http://www.oecd.org/env/ehs/risk-assessment/37849783.pdf.
   Google Scholar
• Joint Meeting of the Chemicals Committee and Working Party on Chemicals, Pesticides and Biotechnology, 2007. Available at http://www.oecd.org/officialdocuments/displaydocument/?doclanguage=en&cote=env/jm/mono(2007)2.
   Google Scholar
• J. Li and P. Gramatica, QSAR classification of estrogen receptor binders and pre-screening of potential pleiotropic EDCs, SAR QSAR Environ. Res. 21 (2010), pp. 657–669.
   PubMed Web of Science ®Google Scholar
• A. Golbraikh, M. Shen, Z. Xiao, Y.-D. Xiao, K.-H. Lee, and A. Tropsha, Rational selection of training and test sets for the development of validated QSAR models, J. Comput.-Aid. Mol. Des. 17 (2003), pp. 241–253.
   PubMed Web of Science ®Google Scholar
• R.P. Sheridan, Using random forest to model the domain applicability of another random forest model, J. Chem. Inf. Model. 53 (2013), pp. 2837–2850.
   PubMed Web of Science ®Google Scholar
• N. Fechner, A. Jahn, G. Hinselmann, and A. Zell, Estimation of the applicability domain of kernel-based machine learning models for virtual screening, J. Cheminf. 2 (2010), p. 2.
   PubMed Web of Science ®Google Scholar
• E. Diamanti-Kandarakis, J.-P. Bourguignon, L.C. Giudice, R. Hauser, G.S. Prins, A.M. Soto, R.T. Zoeller, and A.C. Gore, Endocrine-disrupting chemicals: An endocrine society scientific statement, Endocrine Rev. 30 (2009), pp. 293–342.
   PubMed Web of Science ®Google Scholar
• WHO/UNEP report, State of the Science of Endocrine Disrupting Chemicals – 2012. Available at http://www.who.int/ceh/publications/endocrine/en/.
   Google Scholar
• OECD Work Related to Endocrine Disrupters. Available at http://www.oecd.org/env/ehs/testing/oecdworkrelatedtoendocrinedisrupters.htm.
   Google Scholar
• D. Ding, L. Xu, H. Fang, H. Hong, R. Perkins, S. Harris, E.D. Bearden, L. Shi, and W. Tong, The EDKB: An established knowledge base for endocrine disrupting chemicals, BMC Bioinforma. 11(Suppl. 6) (2010), p. S5.
   PubMed Web of Science ®Google Scholar
• G. Klopman and S.K. Chakravarti, Structure-activity relationship study of a diverse set of estrogen receptor ligands (I) using MultiCASE expert system, Chemosphere 51 (2003), pp. 445–459.
   PubMed Web of Science ®Google Scholar
• H. Hong, W. Tong, Q. Xie, H. Fang, and R. Perkins, An in silico ensemble method for lead discovery: Decision forest, SAR QSAR Environ. Res. 16 (2005), pp. 339–347.
   PubMed Web of Science ®Google Scholar
• W. Tong, Q. Xie, H. Hong, L. Shi, H. Fang, and R. Perkins, Assessment of prediction confidence and domain extrapolation of two structure-activity relationship models for predicting estrogen receptor binding activity, Environ. Health Perspect. 112 (2004), pp. 1249–1125.
   PubMed Web of Science ®Google Scholar
• S.P. Korhonen, K. Tuppurainen, R. Laatikainen, and M. Peraekylae, Comparing the performance of FLUFF-BALL to SEAL-CoMFA with a large diverse estrogen data set: From relevant superpositions to solid predictions, J. Chem. Inf. Model. 45 (2005), pp. 1874–1883.
   PubMed Web of Science ®Google Scholar
• T. Ghafourian and M.T.D. Cronin, The effect of variable selection on the non-linear modelling of oestrogen receptor binding, QSAR Comb. Sci. 25 (2006), pp. 824–835.
   Google Scholar
• H. Liu, E. Papa, and P. Gramatica, QSAR Prediction of estrogen activity for a large set of diverse chemicals under the guidance of OECD principles, Chem. Res. Toxicol. 19 (2006), pp. 1540–1548.
   PubMed Web of Science ®Google Scholar
• L. Ji, X.D. Wang, S. Luo, L. Qin, X.S. Yang, L. Liu, S. Shu, and L.S. Wang, QSAR study on estrogenic activity of structurally diverse compounds using generalized regression neural network, Sci. China, Ser. B: Chem. 51 (2008), pp. 677–683.
   Google Scholar
• L. Ji, X.D. Wang, X.S. Yang, L. Liu, S. Shu, and L.S. Wang, Back-propagation network improved by conjugate gradient based on genetic algorithm in QSAR study on endocrine disrupting chemicals, Chin. Sci. Bull. 53 (2008), pp. 33–39.
   Google Scholar
• N. Stojic, S. Eric, and I. Kuzmanovski, Prediction of toxicity and data exploratory analysis of estrogen-active endocrine disruptors using counter-propagation artificial neural networks, J. Mol. Graph. Model. 29 (2010), pp. 450–460.
   PubMed Web of Science ®Google Scholar
• L. Zhang, A. Sedykh, A. Tripathi, H. Zhu, A. Afantitis, V.D. Mouchlis, G. Melagraki, I. Rusyn, and A. Tropsha, Identification of putative estrogen receptor-mediated endocrine disrupting chemicals using QSAR- and structure-based virtual screening approaches, Toxicol. Appl. Pharmacol. 272 (2013), pp. 67–76.
   PubMed Web of Science ®Google Scholar
• METI, Ministry of Economy, Trade and Industry, Japan. Appendix 1 & 2. Data list of RBA values of human ER receptor binding assay, RA and PC 50 values of human ER reporter gene assay, 6th Meeting of the Task Force on Endocrine, Tokyo, Japan, 2002.
   Google Scholar
• A. Panaye, J.P. Doucet, J. Devillers, N. Marchand-Geneste, and J.M. Porcher, Decision trees versus support vector machine for classification of androgen receptor ligands, SAR QSAR Environ. Res. 19 (2008), pp. 129–151.
   PubMed Web of Science ®Google Scholar
• Y. Li, Y. Wang, J. Ding, Y. Wang, Y. Chang, and S. Zhang, In silico prediction of androgenic and nonandrogenic compounds using random forest, QSAR Comb. Sci. 28 (2009), pp. 396–405.
   Google Scholar
• M. Todorov, E. Mombelli, S. Aït-Aïssa, and O. Mekenyan, Androgen receptor binding affinity: A QSAR evaluation, SAR QSAR Environ. Res. 22 (2011), pp. 265–291.
   PubMed Web of Science ®Google Scholar
• A.M. Vinggaard, J. Niemelä, E.B. Wedebye, and G.E. Jensen, Screening of 397 chemicals and development of a quantitative structure–activity relationship model for androgen receptor antagonism, Chem. Res. Toxicol. 21 (2008), pp. 813–823.
   PubMed Web of Science ®Google Scholar
• J. Li and P. Gramatica, Classification and virtual screening of androgen receptor antagonists, J. Chem. Inf. Model. 50 (2010), pp. 861–874.
   PubMed Web of Science ®Google Scholar
• G.E. Jensen, J.R. Niemela, E.B. Wedebye, and N.G. Nikolov, QSAR models for reproductive toxicity and endocrine disruption in regulatory use - a preliminary investigation, SAR QSAR Environ. Res. 19 (2008), pp. 631–641.
   PubMed Web of Science ®Google Scholar
• H. Li, X. Ren, E. Leblanc, K. Frewin, P.S. Rennie, and A. Cherkasov, Identification of novel androgen receptor antagonists using structure- and ligand-based methods, J. Chem. Inf. Model. 53 (2013), pp. 123–130.
   PubMed Web of Science ®Google Scholar
• H. Hong, H. Fang, Q. Xie, R. Perkins, D.M. Sheehan, and W. Tong, Comparative molecular field analysis (CoMFA) model using a large diverse set of natural, synthetic and environmental chemicals for binding to the androgen receptor, SAR QSAR Environ. Res. 14 (2003), pp. 373–388.
   PubMed Web of Science ®Google Scholar
• H. Fang, W. Tong, W.S. Branham, C.L. Moland, S.L. Dial, H. Hong, Q. Xie, R. Perkins, W. Owens, and D.M. Sheehan, Study of 202 natural, synthetic, and environmental chemicals for binding to the androgen receptor, Chem. Res. Toxicol. 16 (2003), pp. 1338–1358.
   PubMed Web of Science ®Google Scholar
• G.E. Jensen, N.G. Nikolov, E.B. Wedebye, T. Ringsted, and J.R. Niemelä, QSAR models for anti-androgenic effect – a preliminary study, SAR QSAR Environ. Res. 22 (2011), pp. 35–49.
   PubMed Web of Science ®Google Scholar
• V. Vovk, A. Gammerman, and G. Shafer, Algorithmic Learning in a Random World, Springer, New York, NY, 2005.
   Google Scholar
• G.G.J.M. Kuiper, B. Carlsson, K. Grandien, E. Enmark, J. Häggblad, S. Nilsson, and J.-Å. Gustafsson, Comparison of the ligand binding specificity and transcript tissue distribution of estrogen receptors α and β, Endocrinology 138 (1997), pp. 863–870.
   PubMed Web of Science ®Google Scholar
• M.O. Taha, M. Tarairah, H. Zalloum, and G. Abu-Sheikha, Pharmacophore and QSAR modeling of estrogen receptor β ligands and subsequent validation and in silico search for new hits, J. Mol. Graph. Model. 28 (2010), pp. 383–400.
   PubMed Web of Science ®Google Scholar
• A. Rybacka, C. Rudén, I.V. Tetko, and P.L. Andersson, Identifying potential endocrine disruptors among industrial chemicals and their metabolites – development and evaluation of in silico tools, Chemosphere 139 (2015), pp. 372–378.
   PubMed Web of Science ®Google Scholar
• EBI standardizer. Available at https://pypi.python.org/pypi/standardiser, https://wwwdev.ebi.ac.uk/chembl/extra/francis/standardiser/.
   Google Scholar
• MolVS 2015. Available at https://pypi.python.org/pypi/MolVS.
   Google Scholar
• J.L. Faulon, M. Collins, and R.D. Carr, The signature molecular descriptor. 4. Canonizing molecules using extended valence sequence, J. Chem. Inf. Comput. Sci. 44 (2004), pp. 427–436.
   PubMedGoogle Scholar
• R. Todeschini and V. Consonni, Handbook of Molecular Descriptors, WILEY-VCH, Weinheim, 2000.
   Google Scholar
• RDKit, Open-Source Cheminformatics. Available at http://www.rdkit.org.
   Google Scholar
• L. Breiman, Random forests, Mach. Learn. 45 (2001), pp. 5–32.
   Web of Science ®Google Scholar
• F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and É. Duchesnay, Scikit-learn: Machine learning in Python, JMLR 12 (2011), pp. 2825–2830.
   Web of Science ®Google Scholar
• M. Eklund, U. Norinder, S. Boyer, and L. Carlsson, Application of conformal prediction in QSAR, AIAI 382 (2012), pp. 166–175.
   Google Scholar
• M. Eklund, U. Norinder, S. Boyer, and L. Carlsson, The application of conformal prediction to the drug discovery process, Ann Math Artif Intell. (2013)doi:10.1007/s10472-013-9378-2.
   Web of Science ®Google Scholar
• U. Norinder, L. Carlsson, S. Boyer, and M. Eklund, Introducing conformal prediction in predictive modeling. A transparent and flexible alternative to applicability domain determination, J. Chem. Inf. Model. 54 (2014), pp. 1596–1603.
   PubMed Web of Science ®Google Scholar
• U. Norinder, L. Carlsson, S. Boyer, and M. Eklund, Introducing conformal prediction in predictive modeling for regulatory purposes, A transparent and flexible alternative to applicability domain determination, Reg Tox Pharm 71 (2015), pp. 279–284.
   Google Scholar
• L. Carlsson M. Eklund, and U. Norinder, Aggregated conformal prediction, in Artificial Intelligence Applications and Innovations, IFIP Advances in Information and Communication Technology, L. Iliadis, I. Maglogiannis, H. Papadopoulos, S. Sioutas and C. Makris C, eds., Springer, Berlin Heidelberg, vol. 437, 2014, pp. 231–240.
   Google Scholar
• SIMCA 13.0 software package, Umetrics, Umeå, Sweden.
   Google Scholar