Molecule kernels: A descriptor- and alignment-free quantitative structure-activity relationship approach

Journal of Chemical Information and Modeling

Volumn 48, Issue 9, 2008, Pages 1868-1881

  Mohr, Johannes A ^a,b,c   Jain, Brijnesh J ^a   Obermayer, Klaus ^a  

^a TECHNISCHE UNIVERSITÄT BERLIN   (Germany)

^b CHARITÉ UNIVERSITÄTSMEDIZIN BERLIN   (Germany)

^c FR 2 1   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

CLASSIFICATION (OF INFORMATION); COMPUTATIONAL CHEMISTRY; MOLECULES; PREDICTIVE ANALYTICS; STRUCTURES (BUILT OBJECTS); SUPPORT VECTOR MACHINES;

MACHINE LEARNING METHODS; MOLECULAR DESCRIPTORS; PREDICTIVE MODELING; PREDICTIVE PERFORMANCE; QUANTITATIVE STRUCTURE ACTIVITY RELATIONSHIP; QUANTITATIVE STRUCTURE-ACTIVITY RELATIONSHIPS; STATE OF THE ART; STRUCTURAL SIMILARITY;

LEARNING SYSTEMS;

ALGORITHM; ARTICLE; CHEMICAL MODEL; CHEMICAL STRUCTURE; COMPUTER SIMULATION; DRUG DESIGN; FACTUAL DATABASE; QUANTITATIVE STRUCTURE ACTIVITY RELATION;

ALGORITHMS; COMPUTER SIMULATION; DATABASES, FACTUAL; DRUG DESIGN; MODELS, CHEMICAL; MODELS, MOLECULAR; MOLECULAR STRUCTURE; QUANTITATIVE STRUCTURE-ACTIVITY RELATIONSHIP;

EID: 54249156505     PISSN: 15499596     EISSN: 1549960X     Source Type: Journal    
DOI: 10.1021/ci800144y     Document Type: Article

References (24)

1. Wold, S.; Sjostrom, M.; Eriksson, L. PLS-regression: A basic tool of chemometrics. Chemom. Intell. Lab. Syst. 2001, 58, 109-130.
2. Vapnik, V. N. Statistical Learning Theory; Wiley: New York, 1998.
3. Schoelkopf, B.; Smola, A. J. Learning with Kernels; MIT Press: Cambridge, MA, 2002.
4. Bakhir, G. H.; Hofmann, T.; Schoelkopf, B.; Smola, A. J.; Taskar, B.; Vishwanathan, S. V. N. Predicting Structured Data; MIT Press: Cambridge, MA, 2007.
5. Gaertner, T.; Flach, P. A.; Wrobel, S. On graph kernels: Hardness results and efficient alternatives. In Proceedings of the 16th Annual Conference on Computational Learning Theory and the 7th Kernel Workshop, Washington, DC, August 2003; Schoelkopf, B., Warmuth, M. K., Eds.; Springer: Berlin, Heidelberg, New York, 2003; pp 129-143.
6. Kashima, H.; Tsuda, K.; Inokuchi, A. Marginalized kernels between labeled graphs. In Proceedings of the International Conference Machine Learning, Washington, DC; Morgan Kaufmann: San Francisco, CA., 2003; pp 321-328.
7. Ralaivola, L.; Swamidass, S.; Saigo, H.; Baldi, P. Graph Kernels for Chemical Informatics. Neural Networks 2005, 18, 1093-1110.
8. Hochreiter, S.; Obermayer, K. Support vector machines for dyadic data. Neural Comput. 2006, 18, 1472-1510.
9. Kearsley, S. K.; Smith, G. M. An Alternative Method for the Alignment of Molecular Structures: Maximizing Electrostatic and Steric Overlap. Tetrahedron Comp. Methodol. 1990, 3, 615-633.
10. These terms are used here informally to give an intuition, their rigorous definition will be given in the Methods section.
11. Heritage, T. W.; Lowis, D. R. Molecular hologram QSAR In Rational Drug Design: Novel Methodology and Practical Applications; Parrill, A. L., Reddy, M. R., Eds.; ACS Symposium Series 719, American Chemical Society: Washington, D.C., 1999.
12. Cramer, R.; Patterson, D.; Bunce, J. Comparative molecular field analysis (CoMFA). 1. Effect of shape on binding of steroids to carrier proteins. J. Am. Chem. Soc. 1988, 110, 5959-5967.
13. Klebe, G.; Abraham, U.; Mietzner, T. Molecular similarity indexes in a comparative analysis (CoMSIA) of drug molecules to correlate and predict their biological-activity. J. Med. Chem. 1994, 37, 4130-4146.
14. Pastor, M.; Cruciani, G.; McLay, I.; Pickett, S.; Clementi, S. Grid-independent descriptors (GRIND): A novel class of alignmentindependent three-dimensional molecular descriptors. J. Med. Chem. 2000, 43, 3233-3243.
15. Fontaine, F.; Pastor, M.; Zamora, I.; Sanz, F. Anchor-GRIND: Filling the Gap between Standard 3D QSAR and the GRid-INdependent Descriptors. J. Med. Chem. 2005, 48, 2687-2694.
16. Depriest, S. A.; Mayer, D.; Naylor, C. B.; Marshall, G. R. 3DQSAR of angiotensin-converting enzyme and thermolysin inhibitors. A comparison of CoMFA models based on deduced and experimentally determined active-site geometries. J. Am. Chem. Soc. 1993, 115, 5372-5384.
17. Ferguson, A. M.; Heritage, T.; Jonathon, P.; Pack, S. E.; Phillips, L.; et al. A new theoretically based molecular descriptor for use in QSAR/QSPR analysis. J. Comput.-Aided Mol. Des. 1997, 11, 143-152.
18. The requirement of non-colinearity makes sure that a pair of matching bipods can later be used to define a unique spatial alignment (otherwise the alignment would allow arbitrary rotations around the colinear bipod axes).
19. Knebel, T.; Hochreiter, S.; Obermayer, K. An SMO algorithm for the potential support vector machine. Neural Comput. 2008, 20, 271-287.
20. AU the used datasets are publicly available at http://www. cheminformatics.org/datasets/ (accessed July 7, 2008).
21. Sutherland, J. J.; O'Brien, L. A.; Weaver, D. F. A Comparison of Methods for Modeling Quantitative Structure-Activity Relationships. J. Med. Chem. 2004, 47, 5541-5554.
22. http://ni.cs.tu-berlin.de/software/psvm/index.html (accessed July 7, 2008).
23. 21 use the term 2.5D descriptors to distinguish descriptors which involve straightforward calculations like molecular volume from descriptors based on force-field calculations.
24. Challis, J. A Procedure for Determining Rigid Body Transformation Parameters. J. Biomech. 1995, 28, 733-737.