- Poster presentation
- Open Access
Kernel learning for ligand-based virtual screening: discovery of a new PPARγ agonist
© Matthias et al; licensee BioMed Central Ltd. 2010
- Published: 04 May 2010
- Multiple Kernel Learning
- Kernel Learning
- Gaussian Process Regression
- Graph Kernel
We demonstrate the theoretical and practical application of modern kernel-based machine learning methods to ligand-based virtual screening by successful prospective screening for novel agonists of the peroxisome proliferator-activated receptor γ (PPARγ) . PPARγ is a nuclear receptor involved in lipid and glucose metabolism, and related to type-2 diabetes and dyslipidemia. Applied methods included a graph kernel designed for molecular similarity analysis , kernel principle component analysis , multiple kernel learning , and, Gaussian process regression .
In the machine learning approach to ligand-based virtual screening, one uses the similarity principle  to identify potentially active compounds based on their similarity to known reference ligands. Kernel-based machine learning  uses the "kernel trick", a systematic approach to the derivation of non-linear versions of linear algorithms like separating hyperplanes and regression. Prerequisites for kernel learning are similarity measures with the mathematical property of positive semidefiniteness (kernels).
The iterative similarity optimal assignment graph kernel (ISOAK)  is defined directly on the annotated structure graph, and was designed specifically for the comparison of small molecules. In our virtual screening study, its use improved results, e.g., in principle component analysis-based visualization and Gaussian process regression. Following a thorough retrospective validation using a data set of 176 published PPARγ agonists , we screened a vendor library for novel agonists. Subsequent testing of 15 compounds in a cell-based transactivation assay  yielded four active compounds.
The most interesting hit, a natural product derivative with cyclobutane scaffold, is a full selective PPARγ agonist (EC50 = 10 ± 0.2 μM, inactive on PPARα and PPARβ/δ at 10 μM). We demonstrate how the interplay of several modern kernel-based machine learning approaches can successfully improve ligand-based virtual screening results.
- Henke B: Progress in Medicinal Chemistry. 2004, 42: 1-53. full_text.View ArticleGoogle Scholar
- Rupp M, Proschak E, Schneider G: J Chem Inf Model. 2007, 47 (6): 2280-2286. 10.1021/ci700274r.View ArticleGoogle Scholar
- Schölkopf B, Smola A, Müller K-R: Neural Comput. 1998, 10 (5): 1299-1319. 10.1162/089976698300017467.View ArticleGoogle Scholar
- Sonnenburg S, Rätsch G, Schäfer C, Schölkopf B: J Mach Learn Res. 2006, 7 (7): 1531-1565.Google Scholar
- Rasmussen C, Williams C: 2006, MIT Press, CambridgeGoogle Scholar
- Johnson M, Maggiora M: 1990, Wiley, New YorkGoogle Scholar
- Schölkopf B, Smola A: 2002, MIT Press, CambridgeGoogle Scholar
- Rücker C, Scarsi M, Meringer M: Bioorg Med Chem. 2006, 14 (15): 5178-5195. 10.1016/j.bmc.2006.04.005.View ArticleGoogle Scholar
- Rau O, Wurglics M, Paulke A, Zitzkowski J, Meindl N, Bock A, Dingermann T, Abdel-Tawab M, Schubert-Zsilavecz M: Planta Med. 2006, 72 (10): 881-887. 10.1055/s-2006-946680.View ArticleGoogle Scholar
This article is published under license to BioMed Central Ltd.