An assessment of computational methods for obtaining structural information of moderately flexible biomolecules from ion mobility spectrometry

Abstract

When utilized in conjunction with modeling, the collision cross section (Ω) from ion mobility spectrometry can be used to deduce the gas phase structures of analyte ions. Gas phase conformations are determined computationally, and their Ω calculated using an approximate method, the results of which are compared with experimental data. Though prior work has focused upon rigid small molecules or large biomolecules, correlation of computational and experimental Ω has not been thoroughly examined for analytes with intermediate conformational flexibility, which constitute a large fraction of the molecules studied in the field. Here, the computational paradigm for calculating Ω has been tested for the tripeptides WGY, YGW, and YWG (Y = tyrosine, W = tryptophan, G = glycine). Experimental data indicate that Ω(exp) (YWG) > Ω(exp) (WGY) ≈ Ω(exp) (YGW). The energy distributions of conformations obtained from tiers of simulated annealing molecular dynamics (SAMD) were analyzed using a wide array of density functionals. These quantum mechanical energy distributions do not agree with the MD data, which leads to structural differences between the SAMD and DFT conformations. The latter structures are obtained by reoptimization of the SAMD geometries, and are the only suite of structures that reproduce the experimental trend in analyte separability. In the absence of fitting Lennard Jones potentials that reproduce experimental results for the Trajectory Method, the Exact Hard Sphere Scattering method produced numerical values that are in best agreement with the experimental cross sections obtained in He drift gas.