Residual dipolar couplings and molecular dynamic calculations as a source for refinement of protein spatial structures

The precision of techniques and factors affecting the interpretation of residual dipolar couplings (RDCs) in analysis of spatial structures of partially aligned proteins are discussed. Experimental RDC values were obtained for pairs of 1H-15N nuclei of the protein barstar partially aligned in a liquid crystalline matrix of bicelles composed of dimiristoylphosphatidylcholine and dihexanoylphosphatidylcholine. The observed couplings agree well with the spatial structures of barstar determined earlier by X-ray and NMR methods. However, the differences between the experimental and calculated RDCs that were calculated on the basis of the known spatial structures of barstar, exceed the experimental errors three-to fourfold. These discrepancies can be explained by differences in the protein structures in solution and in crystal, a limited precision of the X-ray analysis, and the intramolecular mobility of the protein molecule. A comparison of the results of modeling of the molecular dynamics of barstar in solution, crystal structures, and the experimental RDCs showed that the methods of molecular dynamics provide for a reasonable description of the character and amplitudes of internal motions and they should be considered for the correct determination of protein spatial structures from NMR spectroscopic data.