Molecule Kernels: A Descriptor- and Alignment-Free Quantitative Structure–Activity Relationship Approach Export

@article{MohrJO08, abstract = {Abstract: Quantitative structure activity relationship (QSAR) analysis is traditionally based on extracting a set of molecular descriptors and using them to build a predictive model. In this work, we propose a QSAR approach based directly on the similarity between the 3D structures of a set of molecules measured by a so-called molecule kernel, which is independent of the spatial prealignment of the compounds. Predictors can be build using the molecule kernel in conjunction with the potential support vector machine (P-SVM), a recently proposed machine learning method for dyadic data. The resulting models make direct use of the structural similarities between the compounds in the test set and a subset of the training set and do not require an explicit descriptor construction. We evaluated the predictive performance of the proposed method on one classification and four regression QSAR datasets and compared its results to the results reported in the literature for several state-of-the-art descriptor-based and 3D QSAR approaches. In this comparison, the proposed molecule kernel method performed better than the other QSAR methods.}, address = {School for Electrical Engineering and Computer Science, Berlin Institute of Technology, Berlin, Germany, and Department of Psychiatry and Psychotherapy, CCM, Charite
- University Medicine, Berlin, Germany}, author = {Mohr, Johannes A. and Jain, Brijnesh J. and Obermayer, Klaus}, citeulike-article-id = {3197937}, citeulike-linkout-0 = {http://dx.doi.org/10.1021/ci800144y}, citeulike-linkout-1 = {http://pubs.acs.org/doi/abs/10.1021/ci800144y}, day = {4}, doi = {10.1021/ci800144y}, journal = {J. Chem. Inf. Model.}, keywords = {alignment, alignment-free, bipod, descriptor, kernels, molecule, qsar}, month = {September}, posted-at = {2008-09-08 14:19:36}, priority = {2}, title = {Molecule Kernels: A Descriptor- and Alignment-Free Quantitative Structure\&\#x2013;Activity Relationship Approach}, url = {http://dx.doi.org/10.1021/ci800144y}, year = {2008} }

TY - JOUR ID - MohrJO08 L3 - citeulike-article-id:3197937 N2 - Abstract: Quantitative structure activity relationship (QSAR) analysis is traditionally based on extracting a set of molecular descriptors and using them to build a predictive model. In this work, we propose a QSAR approach based directly on the similarity between the 3D structures of a set of molecules measured by a so-called molecule kernel, which is independent of the spatial prealignment of the compounds. Predictors can be build using the molecule kernel in conjunction with the potential support vector machine (P-SVM), a recently proposed machine learning method for dyadic data. The resulting models make direct use of the structural similarities between the compounds in the test set and a subset of the training set and do not require an explicit descriptor construction. We evaluated the predictive performance of the proposed method on one classification and four regression QSAR datasets and compared its results to the results reported in the literature for several state-of-the-art descriptor-based and 3D QSAR approaches. In this comparison, the proposed molecule kernel method performed better than the other QSAR methods. JF - J. Chem. Inf. Model. AD - School for Electrical Engineering and Computer Science, Berlin Institute of Technology, Berlin, Germany, and Department of Psychiatry and Psychotherapy, CCM, Charite
- University Medicine, Berlin, Germany TI - Molecule Kernels: A Descriptor- and Alignment-Free Quantitative Structure–Activity Relationship Approach KW - alignment KW - alignment-free KW - bipod KW - descriptor KW - kernels KW - molecule KW - qsar AU - Mohr, Johannes AU - Jain, Brijnesh AU - Obermayer, Klaus PY - 2008/09/04/ UR - http://dx.doi.org/10.1021/ci800144y ER -