Beyond the scope of free-wilson analysis: Building interpretable QSAR models with machine learning algorithms

Journal of Chemical Information and Modeling

Volumn 53, Issue 6, 2013, Pages 1324-1336

  Chen, Hongming ^a   Carlsson, Lars ^b   Eriksson, Mats ^a   Varkonyi, Peter ^a   Norinder, Ulf ^d,e   Nilsson, Ingemar ^c  

^a Discovery Research   (Sweden)

^b Global Safety Assessment   (Sweden)

^c ASTRAZENECA R AND D   (Sweden)

^d ASTRAZENECA R AND D   (Sweden)

^e H LUNDBECK A S   (Denmark)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL CHEMISTRY; FORECASTING; LEARNING ALGORITHMS; MOLECULAR GRAPHICS;

DRUG DISCOVERY; GROUP CONTRIBUTIONS; GROUP SIGNATURES; MODELING TOOL; NOVEL METHODOLOGY; PREDICTION ACCURACY; SVM ALGORITHM; TRADITIONAL MODELS;

MACHINE LEARNING;

DRUG;

ALGORITHM; ARTICLE; ARTIFICIAL INTELLIGENCE; CHEMISTRY; DRUG DEVELOPMENT; PHARMACOLOGY; QUANTITATIVE STRUCTURE ACTIVITY RELATION;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; DRUG DISCOVERY; PHARMACEUTICAL PREPARATIONS; PHARMACOLOGY; QUANTITATIVE STRUCTURE-ACTIVITY RELATIONSHIP;

EID: 84879570665     PISSN: 15499596     EISSN: 1549960X     Source Type: Journal    
DOI: 10.1021/ci4001376     Document Type: Article

References (45)

1. Paul, S. M.; Mytelka, D. S.; Dunwiddie, C. T.; Persinger, C. C.; Munos, B. H.; Lindborg, S. R.; Schacht, A. L. How to improve R&D productivity: the pharmaceutical industry's grand challenge Nat. Rev. Drug Discovery 2010, 9, 203-14
2. Plowright, A. T.; Johnstone, C.; Kihlberg, J.; Pettersson, J.; Robb, G.; Thompson, R. A. Hypothesis driven drug design: improving quality and effectiveness of the design-make-test-analyse cycle Drug Discovery Today 2012, 17, 56-62
3. Andersson, S.; Armstrong, A.; Björe, A.; Bowker, S.; Chapman, S.; Davies, R.; Donald, C.; Egner, B.; Elebring, T.; Holmqvist, S.; Inghardt, T.; Johannesson, P.; Johansson, M.; Johnstone, C.; Kemmitt, P.; Kihlberg, J.; Korsgren, P.; Lemurell, M.; Moore, J.; Pettersson, J. A.; Pointon, H.; Pontén, F.; Schofield, P.; Selmi, N.; Whittamore, P. Making medicinal chemistry more effective - application of Lean Sigma to improve processes, speed and quality Drug Discovery Today 2009, 14, 598-604
4. Hutter, M. C. In silico prediction of drug properties Curr. Med. Chem. 2009, 16, 189-202
5. Cramer, R. D.; Patterson, D. E.; Bunce, J. D. Comparative molecular field analysis (CoMFA). 1. Effect of shape on binding of steroids to carrier proteins J. Am. Chem. Soc. 1988, 110, 5959-67
6. Li, H.; Yap, C. W.; Xue, Y.; Li, Z. R.; Ung, C. Y.; Han, L. Y.; Chen, Y. Z. Statistical learning approach for predicting specific pharmacodynamic, pharmacokinetic, or toxicological properties of pharmaceutical agents Drug Dev. Res. 2005, 66, 245-259
7. Chadwick, A.; Hajek, M. Learning to improve the decision-making process in research Drug Discovery Today 2004, 9, 251-257
8. Duch, W.; Swaminathan, K.; Meller, J. Artificial intelligence approaches for rational drug design and discovery Curr. Pharm. Des. 2007, 13, 1497-1508
9. Yap, C.; Xue, Y.; Li, H.; Li, Z.; Ung, C.; Han, L.; Zheng, C.; Cao, Z.; Chen, Y. Prediction of compounds with specific pharmacodynamic, pharmacokinetic or toxicological property by statistical learning methods Mini-Rev. Med.Chem. 2006, 6, 449-459
10. Yap, C. W.; Li, H.; Ji, Z. L.; Chen, Y. Z. Regression methods for developing QSAR and QSPR models to predict compounds of specific pharmacodynamic, pharmacokinetic and toxicological properties Mini- Reviews in Med. Chem. 2007, 7, 1097-107
11. Mager, D. E. Quantitative structure-pharmacokinetic/pharmacodynamic relationships Adv. Drug Delivery Rev. 2006, 58, 1326-56
12. Free, S. M.; Wilson, J. W. A mathematical contribution to structure-activity studies J. Med. Chem. 1964, 7, 395-9
13. Craig, P. N. Proceedings: comparison of Hansch and free-Wilson methods for structure-activity correlation Cancer Chemother. Rep., Part 2 1974, 4, 39
14. Kubinyi, H.; Kehrhahn, O. H. Quantitative structure-activity relationships. 3.1. A comparison of different Free-Wilson models J. Med. Chem. 1976, 19, 1040-9
15. Hansch, C.; Muir, R. M.; Fujita, T.; Maloney, P. P.; Geiger, F.; Streich, M. The correlation of biological activity of plant growth regulators and chloromycetin derivatives with Hammett constants and partition coefficients J. Am. Chem. Soc. 1963, 719, 2817-24
16. Hansch, C.; Maloney, P. P.; Fujita, T.; Muir, R. M. Correlation of biological activity of phenoxyacetic acids with Hammett substituent constants and partition coefficients Nature 1962, 194, 178-180
17. Nilsson, I.; Polla, M. O. Composite multi-parameter ranking of real and virtual compounds for design of MC4R agonists: renaissance of the Free-Wilson methodology J. Comput.-Aided Mol. Des. 2012, 26, 1143-57
18. Goldberg, F. W.; Leach, A. G.; Scott, J. S.; Snelson, W. L.; Groombridge, S. D.; Donald, C. S.; Bennett, S. N. L.; Bodin, C.; Gutierrez, P. M.; Gyte, A. C. Free-Wilson and structural approaches to co-optimizing human and rodent isoform potency for 11β-hydroxysteroid dehydrogenase type 1 (11β-HSD1) inhibitors J. Med. Chem. 2012, 55, 10652-61
19. Jorissen, R. N.; Reddy, G. S. K. K.; Ali, A.; Altman, M. D.; Chellappan, S.; Anjum, S. G.; Tidor, B.; Schiffer, C. A.; Rana, T. M.; Gilson, M. K. Additivity in the analysis and design of HIV protease inhibitors J. Med. Chem. 2009, 52, 737-54
20. Sciabola, S.; Stanton, R. V; Johnson, T. L.; Xi, H. Application of Free-Wilson selectivity analysis for combinatorial library design Methods Mol. Biol. 2011, 685, 91-109
21. Höfgen, N.; Stange, H.; Schindler, R.; Lankau, H.-J.; Grunwald, C.; Langen, B.; Egerland, U.; Tremmel, P.; Pangalos, M. N.; Marquis, K. L.; Hage, T.; Harrison, B. L.; Malamas, M. S.; Brandon, N. J.; Kronbach, T. Discovery of imidazo[1,5-a]pyrido[3,2-e]pyrazines as a new class of phosphodiesterase 10A inhibitiors J. Med. Chem. 2010, 53, 4399-411
22. Patel, Y.; Gillet, V. J.; Howe, T.; Pastor, J.; Oyarzabal, J.; Willett, P. Assessment of additive/nonadditive effects in structure-activity relationships: implications for iterative drug design J. Med. Chem. 2008, 51, 7552-62
23. Tomic, S.; Nilsson, L.; Wade, R. C. Nuclear receptor-DNA binding specificity: a COMBINE and Free-Wilson QSAR analysis J. Med. Chem. 2000, 43, 1780-92
24. Freeman-Cook, K. D.; Amor, P.; Bader, S.; Buzon, L. M.; Coffey, S. B.; Corbett, J. W.; Dirico, K. J.; Doran, S. D.; Elliott, R. L.; Esler, W.; Guzman-Perez, A.; Henegar, K. E.; Houser, J. A.; Jones, C. S.; Limberakis, C.; Loomis, K.; McPherson, K.; Murdande, S.; Nelson, K. L.; Phillion, D.; Pierce, B. S.; Song, W.; Sugarman, E.; Tapley, S.; Tu, M.; Zhao, Z. Maximizing lipophilic efficiency: the use of Free-Wilson analysis in the design of inhibitors of acetyl-CoA carboxylase J. Med. Chem. 2012, 55, 935-42
25. Daylight Manual. http://www.daylight.com/dayhtml/doc/theory/theory. finger.html (accessed Jan 2, 2013).
26. UNITY 2D fingerprint; Tripos Inc.: St. Louis, MO, USA.
27. Accelrys Whitepaper; The keys to understanding MDL keyset technology. http://accelrys.com/products/pdf/keys-to-keyset-technology.pdf (accessed Jan 2, 2013).
28. Rogers, D.; Hahn, M. Extended-connectivity fingerprints J. Chem. Inf. Model. 2010, 50, 742-54
29. Faulon, J.-L.; Visco, D. P.; Pophale, R. S. The signature molecular descriptor. 1. Using extended valence sequences in QSAR and QSPR studies J. Chem. Inf. Comput. Sci. 2003, 43, 707-20
30. Rosenbaum, L.; Hinselmann, G.; Jahn, A.; Zell, A. Interpreting linear support vector machine models with heat map molecule coloring J. Cheminf. 2011, 3, 11
31. Carlsson, L.; Helgee, E. A.; Boyer, S. Interpretation of nonlinear QSAR models applied to Ames mutagenicity data J. Chem. Inf. Model. 2009, 49, 2551-8
32. GOSTAR databases 2012; GVK Bioscieces Private Ltd.: Hyderabad, India.
33. Perl programming language. http://www.perl.org/ (accessed Jan 20, 2013).
34. Openbabel version 2.2.3. http://http://openbabel.org/wiki/Main-Page (accessed Jan 20, 2013).
35. Pipeline Pilot version 8.5; Accelrys Inc.: San Diego, CA, USA.
36. Paine, S. W.; Barton, P.; Bird, J.; Denton, R.; Menochet, K.; Smith, A.; Tomkinson, N. P.; Chohan, K. K. A rapid computational filter for predicting the rate of human renal clearance J. Mol. Graphics Modell. 2010, 29, 529-37
37. Bruneau, P. Search for predictive generic model of aqueous solubility using Bayesian neural nets. J. Chem. Inf. Comput. Sci. 41, 1605-16.
38. Katritzky, A. R.; Wang, Y.; Sild, S.; Tamm, T.; Karelson, M. QSPR studies on vapor pressure, aqueous solubility, and the prediction of water-air partition coefficients J. Chem. Inf. Model. 1998, 38, 720-725
39. Yao, X. J.; Panaye, A.; Doucet, J. P.; Zhang, R. S.; Chen, H. F.; Liu, M. C.; Hu, Z. D.; Fan, B. T. Comparative study of QSAR/QSPR correlations using support vector machines, radial basis function neural networks, and multiple linear regression. J. Chem. Inf. Comput. Sci. 44, 1257-66.
40. Darnag, R.; Mostapha Mazouz, E. L.; Schmitzer, A.; Villemin, D.; Jarid, A.; Cherqaoui, D. Support vector machines: development of QSAR models for predicting anti-HIV-1 activity of TIBO derivatives Eur. J. Med. Chem. 2010, 45, 1590-7
41. Vapnik, V. N. The Nature of Statistical Learning Theory; Springer: New York, 1995.
42. Vapnik, V. N. Statistical Learning Theory; John Wiley and Sons, Inc.: New York, 1998.
43. Chang, C.-C.; Lin, C.-J. LIBSVM: a library for support vector machines ACM Trans. Intell. Syst. Technol. 2011, 2, 1-27
44. JMP, version 10.0; SAS Institute Inc.: Cary, NC, USA.
45. StaÌŠlring, J. C.; Carlsson, L. A.; Almeida, P.; Boyer, S. AZOrange-high performance open source machine learning for QSAR modeling in a graphical programming environment J. Cheminf. 2011, 3, 28