Large scale testing of chemical shift prediction algorithms and improved machine learning-based approaches to shift prediction

@inproceedings{citeulike:936298, abstract = {The resonant frequencies, or chemical shifts, of nuclear magnetic resonance (NMR) active nuclei in proteins are determined by covalent and through-space interactions and, more generally, the electronic environment surrounding each nucleus. However, the precise nature of the correlation between protein three-dimensional (3D) structure and chemical shift remains largely unsolved. Thus, chemical shift prediction is a non-trivial task. This study tests the accuracy of three existing structure-based chemical shift prediction algorithms (SHIFTS, SHIFTX, PROSHIFT) against REFDB, a large database of experimentally determined, and manually re-referenced /sup 1/H, /sup 13/C, and /sup 15/N chemical shifts. We report that the accuracy of backbone chemical shift predictions for each program is lower than that originally reported. This suggests these programs over-fit the data used in their construction. We then compare two novel methods for chemical shift prediction based on support vector machines (SVM) and bagging respectively. Each method was trained on REFUB using predictions made by SHIFTS, SHIFTX, and PROSHIFT as features. In cross-validated experiments, bagging is shown to be superior to SVMs, while both methods are substantially better than SHIFTS, SHIFTX, and PROSHIFT. Our results suggest that meta-methods for chemical shift prediction yield increased accuracy for chemical shift prediction.}, author = {Arun, K. and Langmead, C. J. }, citeulike-article-id = {936298}, journal = {Computational Systems Bioinformatics Conference, 2004. CSB 2004. Proceedings. 2004 IEEE}, keywords = {chemical, meta, methods, prediction, shift}, pages = {712--713}, posted-at = {2006-11-08 14:23:24}, priority = {2}, title = {Large scale testing of chemical shift prediction algorithms and improved machine learning-based approaches to shift prediction}, url = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=1332556}, year = {2004} }

TY - CONF ID - citeulike:936298 L3 - citeulike-article-id:936298 TI - Large scale testing of chemical shift prediction algorithms and improved machine learning-based approaches to shift prediction JF - Computational Systems Bioinformatics Conference, 2004. CSB 2004. Proceedings. 2004 IEEE SP - 712 EP - 713 N2 - The resonant frequencies, or chemical shifts, of nuclear magnetic resonance (NMR) active nuclei in proteins are determined by covalent and through-space interactions and, more generally, the electronic environment surrounding each nucleus. However, the precise nature of the correlation between protein three-dimensional (3D) structure and chemical shift remains largely unsolved. Thus, chemical shift prediction is a non-trivial task. This study tests the accuracy of three existing structure-based chemical shift prediction algorithms (SHIFTS, SHIFTX, PROSHIFT) against REFDB, a large database of experimentally determined, and manually re-referenced /sup 1/H, /sup 13/C, and /sup 15/N chemical shifts. We report that the accuracy of backbone chemical shift predictions for each program is lower than that originally reported. This suggests these programs over-fit the data used in their construction. We then compare two novel methods for chemical shift prediction based on support vector machines (SVM) and bagging respectively. Each method was trained on REFUB using predictions made by SHIFTS, SHIFTX, and PROSHIFT as features. In cross-validated experiments, bagging is shown to be superior to SVMs, while both methods are substantially better than SHIFTS, SHIFTX, and PROSHIFT. Our results suggest that meta-methods for chemical shift prediction yield increased accuracy for chemical shift prediction. KW - chemical KW - meta KW - methods KW - prediction KW - shift AU - Arun, K AU - Langmead, CJ PY - 2004/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1332556 ER -