Linear discriminant analysis reveals hidden patterns in NMR chemical shifts of intrinsically disordered proteins

NMR spectroscopy is key in the study of intrinsically disordered proteins (IDPs). Yet, even the first step in such an analysis--the assignment of observed resonances to particular nuclei--is often problematic due to low peak dispersion in the spectra of IDPs. We show that the assignment process can be aided by finding "hidden" chemical shift patterns specific to the amino acid residue types. We find such patterns in the training data from the Biological Magnetic Resonance Bank using linear discriminant analysis, and then use them to classify spin systems in an alfa-synuclein sample prepared by us. We describe two situations in which the procedure can greatly facilitate the analysis of NMR spectra. The first involves the mapping of spin systems chains onto the protein sequence, which is part of the assignment procedure--a prerequisite for any NMR-based protein analysis. In the second, the method supports assignment transfer between similar samples. We conducted experiments to demonstrate these cases, and both times the majority of spin systems could be unambiguously assigned to the correct residue types. Author summaryIntrinsically disordered proteins dynamically change their conformation, which allows them to fulfil many biologically significant functions, mostly related to process regulation. Their relation to many civilization diseases makes them essential objects to study. Nuclear magnetic resonance spectroscopy (NMR) is the method for such research, as it provides atomic-scale information on these proteins. However, the first step of the analysis - assignment of experimentally measured NMR chemical shifts to particular atoms of the protein - is more complex than in the case of structured proteins. The methods routinely used for these proteins are no more sufficient. We have developed a method of resolving ambiguities occurring during the assignment process. In a nutshell, we show that an advanced statistical method known as linear discriminant analysis makes it possible to determine chemical shift patterns specific to different types of amino acid residues. It allows assigning the chemical shifts more efficiently, opening the way to a plethora of structural and dynamical information on intrinsically disordered proteins.