A constructive approach for discovering new drug leads: Using a kernel methodology for the inverse-QSAR problem

Journal of Cheminformatics

Volumn 1, Issue 1, 2009, Pages

  Wong, William Wl ^a   Burkowski, Forbes J ^a  

^a UNIVERSITY OF WATERLOO   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 74049144437     PISSN: None     EISSN: 17582946     Source Type: Journal    
DOI: 10.1186/1758-2946-1-4     Document Type: Article

References (48)

1. Potential functions for virtual screening and ligand binding calculations: Some theoretical considerations. KA Sharp, Virtual Screening in Drug Discovery New York: Taylor & Francis, Alvarez J, Shoichet B, 2005 229 248
2. R Todeschini V Consonni, Handbook of molecular descriptors Weinheim: Wiley-VCH 2000
3. Reverse engineering chemical structures from molecular descriptors: how many solutions? JL Faulon W Brown S Martin, J Comput-Aided Mol Des 2005 19 637 650 10.1007/s10822-005-9007-1 16267694
4. A general method for exploiting QSAR models in lead optimization. RA Lewis, J Med Chem 2005 48 1638 1648 10.1021/jm049228d 15743205
5. A novel workflow for the inverse QSPR problem using multi-objective optimization. N Brown B McKay J Gasteiger, J Comput-Aided Mol Des 2006 20 333 341 10.1007/s10822-006-9063-1 17031542
6. Sharing chemical information without sharing chemical structure. BB Masek L Shen KM Smith RS Pearlman, J Chem Inf Model 2008 48 256 261 10.1021/ci600383v 18254609
7. Using a genetic algorithm to suggest combinatorial libraries. RP Sheridan SK Kearsley, J Chem Inf Comput Sci 1995 35 310 320
8. Evolutionary design of molecules with desired properties using the genetic algorithm. V Venkatasubramanian K Chan JM Caruthers, J Chem Inf Comput Sci 1995 35 188 195
9. Simulated annealing construction of molecular graphs with required properties. V Kvasnicka J Pospichal, J Chem Inf Comput Sci 1996 36 516 526
10. Design of molecules from quantitative structure-activity relationship models.2. Derivation and proof of information-transfer relating equations. LH Hall LB Kier JW Frazer, J Chem Inf Comput Sci 1993 33 148 152
11. Design of molecules from quantitative structure-activity relationship models.3. Role of higher-order path counts: path 3. LH Hall RS Dailey LB Kier, J Chem Inf Comput Sci 1993 33 598 603
12. Design of molecules from quantitative structure-activity relationship models.1. Information-transfer between path and vertex degree counts. LB Kier LH Hall JW Frazer, J Chem Inf Comput Sci 1993 33 143 147
13. Inverse problem in QSAR, QSPR studies for the case of topological indexes characterizing molecular shape (Kier indexes). MI Skvortsova II Baskin OL Slovokho tova VA Palyulin NS Zefirov, J Chem Inf Comput Sci 1993 33 630 634
14. The signature molecular descriptor - 3. Inverse quantitative structure-activity relationship of ICAM-1 inhibitory peptides. CJ Churchwell MD Rintoul S Martin DP Visco A Kotu RS Larson LO Sillerud DC Brown JL Faulon, J Mol Graphics Modell 2004 22 263 273 10.1016/j.jmgm.2003.10.002 (Pubitemid 38183096)
15. The signature molecular descriptor. 1. Using extended valence sequences in QSAR and QSPR studies. JL Faulon DP Visco RS Pophale, J Chem Inf Comput Sci 2003 43 707 720 12767129
16. The signature molecular descriptor. 2. Enumerating molecules from their extended valence sequences. JL Faulon CJ Churchwell DP Visco, J Chem Inf Comput Sci 2003 43 721 734 12767130
17. The signature molecular descriptor. 4. Canonizing molecules using extended valence sequences. JL Faulon MJ Collins RD Carr, J Chem Inf Comput Sci 2004 44 427 436 15032522
18. One- to four-dimensional kernels for virtual screening and the prediction of physical, chemical, and biological properties. CA Azencott A Ksikes SJ Swamidass JH Chen L Ralaivola P Baldi, J Chem Inf Model 2007 47 965 974 10.1021/ci600397p 17338509
19. Kernels for small molecules and the prediction of mutagenicity, toxicity and anti-cancer activity. SJ Swamidass J Chen J Bruand P Phung L Ralaivola P Baldi, Bioinformatics 2005 21 supplement 1 359 i368 10.1093/bioinformatics/bti1055 (Pubitemid 41794509)
20. Optimal assignment kernels for attributed molecular graphs. H M Fröhlich JK Wegner F Sieker A Zell, Bonn, Germany 225 232
21. Graph kernels for molecular structure-activity relationship analysis with support vector machines. P Mahe N Ueda T Akutsu JL Perret JP Vert, J Chem Inf Model 2005 45 939 951 10.1021/ci050039t 16045288
22. Graph kernels for chemical informatics. L Ralaivola SJ Swamidass H Saigo P Baldi, Neural Net 2005 18 1093 1110 10.1016/j.neunet.2005.07.009 (Pubitemid 41476343)
23. The pharmacophore kernel for virtual screening with support vector machines. P Mahe L Ralaivola V Stoven JP Vert, J Chem Inf Model 2006 46 2003 2014 10.1021/ci060138m 16995731
24. Predicting multiple binding modes in QSAR studies using a vector Space model molecular descriptor in reproducing kernel Hilbert space. FJ Burkowski WWL Wong, International Journal of Computational Biology and Drug Design 2009
25. Similarity searching using reduced graphs. VJ Gillet P Willett J Bradshaw, J Chem Inf Comput Sci 2003 43 338 345 12653495
26. Circular fingerprints: Flexible molecular descriptors with applications from physical chemistry to ADME. RC Glenn A Bender CH Arnby L Carlsson S Boyer J Smith, IDrugs 2006 9 199 204 16523386
27. A comparison of methods for modeling quantitative structure-activity relationships. JJ Sutherland LA O'Brien DF Weaver, J Med Chem 2004 47 5541 5554 10.1021/jm0497141 15481990
28. J Shawe-Taylor N Cristianini, Kernel methods for pattern analysis Cambridge, UK: Cambridge University Press 2004
29. The pre-image problem in kernel methods. JTY Kwok IWH Tsang, IEEE Trans Neural Net 2004 15 1517 1525 10.1109/TNN.2004.837781
30. Embedded kernel eigen-voice speaker adaptation and its implication to reference speaker weighting. B Mak R Hsiao S Ho JT Kwok, IEEE Trans Speech Audio Proc 2006 14 1267 1280 10.1109/TSA.2005.860836 (Pubitemid 46547622)
31. Minimum enclosing and maximum excluding machine for pattern description and discrimination. Y Liu YF Zheng, 18th International Conference on Pattern Recognition 129 132
32. Kernel PCA and de-noising in feature spaces. S Mika B Schölkopf JA Smola K-R Müller M Scholz G Rätsch, Proceedings of the 1998 conference on Advances in neural information processing system II 536 542
33. Fast approximation of support vector kernel expansions, and an interpretation of clustering as approximation in feature spaces. B Schölkopf P Knirsch AJ Smola CJC Burges, DAGM-Symposium 125 132
34. Learning to find graph pre-images. GH Bakir A Zien K Tsuda, Lecture Notes in Computer Science 2004 3175 253 261
35. Inferring a graph from path frequency. A Tatsuya D Fukagawa, Lecture Notes in Computer Science 2005 3537 371 382
36. Inferring a chemical structure from a feature vector based on frequency of labelled paths and small fragments. A Tatsuya D Fukagawa, APBC 2007 165 174
37. JW Robin, Introduction to Graph Theory Addison Wesley 1996
38. A general regression technique for learning transductions. C Cortes M Mohri J Weston, Proceedings of the 22nd international conference on Machine learning; Bonn, Germany 153 160
39. An Eulerian path approach to DNA fragment assembly. PA Pevzner H Tang MS Waterman, Proc Natl Acad Sci USA 2001 98 9748 9753 11504945 10.1073/pnas.171285098 (Pubitemid 32769375)
40. Diaryl indenes and benzofurans - novel classes of potent and selective cyclooxygenase-2 inhibitors. HC Huang TS Chamberlain K Seibert CM Koboldt PC Isakson, Bioorg Med Chem Lett 1995 5 2377 2380 10.1016/0960-894X(95)00414-O
41. Three-dimensional quantitative structure-activity relationships of cyclo-oxygenase-2 (COX-2) inhibitors: A comparative molecular field analysis. P Chavatte S Yous C Marot N Baurin D Lesieur, J Med Chem 2001 44 3223 3230 10.1021/jm0101343 11563921 (Pubitemid 32917102)
42. The chemistry development kit (CDK): an open-source Java library for chemo- and bioinformatics. C Steinbeck Y Han S Kuhn O Horlacher E Luttmann E Willighagen, J Chem Inf Comput Sci 2003 43 493 500 12653513
43. Recent developments of the chemistry development kit (CDK) - an open-source java library for chemo- and bioinformatics. C Steinbeck C Hoppe S Kuhn M Floris R Guha EL Willighagen, Curr Pharm Des 2006 12 2111 2120 10.2174/138161206777585274 16796559
44. Recent advances in inducible cyclooxygenase (COX-2) inhibition. X Leval J Delarge F Somers P Tullio Y Henrotin B Pirotte J Dogne, Curr Med Chem 2000 7 1041 1062 10911017
45. Selective cyclooxygenase inhibitors: Novel 1,2-diarylcyclopentenes are potent and orally active COX-2 inhibitors. DB Reitz JJ Li MB Norton EJ Reinhard JT Collins GD Anderson SA Gregory CM Koboldt WE Perkins, J Med Chem 1994 37 3878 3881 10.1021/jm00049a005 7966148
46. An introduction to kernel-based learning algorithms. K-R Müller S Mika G Räts ch K Tsuda B Schölkopf, IEEE Trans Neural Net 2001 12 181 201 10.1109/72.914517 (Pubitemid 32371478)
47. Measuring CAMD technique performance. 2. How "druglike" are drugs? Implications of Random test set selection exemplified using druglikeness classification models. AC Good MA Hermsmeier, J Chem Inf Model 2007 47 110 114 10.1021/ci6003493 17238255
48. Measuring CAMD technique performance: a virtual screening case study in the design of validation experiments. AC Good MA Hermsmeier SA Hindle, J Comput-Aided Mol Des 2005 18 529 536 10.1007/s10822-004-4067-1