Assisting and Accelerating NMR Assignment with Restrained Structure Prediction

Abstract

NMR experiments can detect in situ structures and dynamic interactions, but the NMR assignment process requires expertise and is time-consuming, thereby limiting its applicability. Deep learning algorithms have been employed to aid in experimental data analysis. In this work, we developed a RASP model which can enhance structure prediction with restraints. Based on the Evoformer and structure module architecture of AlphaFold, this model can predict structure based on sequence and a flexible number of input restraints. Moreover, it can evaluate the consistency between the predicted structure and the imposed restraints. Based on this model, we constructed an iterative NMR NOESY peak assignment pipeline named FAAST, to accelerate assignment process of NOESY restraints and obtaining high quality structure ensemble. The RASP model and FAAST pipeline not only allow for the leveraging of experimental restraints to improve model prediction, but can also facilitate and expedite experimental data analysis with their integrated capabilities.