Developing a scoring function for NMR structure-based assignments using machine learning

This is the latest version of this item.

Official URL: http://dx.doi.org/10.1007/978-90-481-9794-1_17

Determining the assignment of signals received from the ex- periments (peaks) to speci_c nuclei of the target molecule in Nuclear Magnetic Resonance (NMR1) spectroscopy is an important challenge. Nuclear Vector Replacement (NVR) ([2, 3]) is a framework for structure- based assignments which combines multiple types of NMR data such as chemical shifts, residual dipolar couplings, and NOEs. NVR-BIP [1] is a tool which utilizes a scoring function with a binary integer programming (BIP) model to perform the assignments. In this paper, support vector machines (SVM) and boosting are employed to combine the terms in NVR-BIP's scoring function by viewing the assignment as a classi_ca- tion problem. The assignment accuracies obtained using this approach show that boosting improves the assignment accuracy of NVR-BIP on our data set when RDCs are not available and outperforms SVMs. With RDCs, boosting and SVMs o_er mixed results.