Hydroxyl and Trifluoromethyl Radical Carbohydrate Footprinting for Probing Protein Binding Components of Oligosaccharides

Abstract

Carbohydrates are found in various forms in living organisms, both as free-standing glycans as well as glycoconjugates including glycoproteins, glycolipids, and glycosaminoglycans. These structures play crucial roles in many biological processes, often mediated or influenced by interactions of carbohydrates with other biomolecules. However, studying these interactions is particularly challenging due to the structural complexity of carbohydrates, their dynamic conformational behavior, and the low binding affinities often involved. To address these challenges, we are developing a novel method that leverages mass spectrometry-based radical carbohydrate footprinting (RCF). We monitored changes in the solvent accessibility of specific regions within oligosaccharides by measuring variations in the apparent rate of hydroxyl radical and trifluoromethyl radical-mediated oxidation. In our studies, a collection of trisaccharide isomers and N,N',N″-triacetylchitotriose (NAG₃) shows no significant change in modification in nonbinding protein solutions. However, in the presence of two proteins that bind NAG₃ specifically, NAG₃ oxidation is reduced. We find that the free reducing end is the primary site of hydroxyl radical oxidation under covalent labeling conditions, allowing it to distinguish interactions at the glycan reducing end. Trifluoromethyl radicals, conversely, label broadly across the trisaccharide by substitution into a C-H bond. Overall, this approach offers a powerful novel approach for identifying glycan-protein interactions and mapping the binding interface of glycans.

Figure 1.. Hydroxyl radical-carbohydrate chemistry under FOX conditions.

(A) HILIC-MS extracted ion chromatogram of reduced NAG₃ (red), (NAG₃ + O green), unmodified unreduced NAG₃ (black, no signal detected) and reduced and modified NAG₃ (blue, no signal detected). (B) MS/MS spectrum of the reduced NAG₃ after sodium borohydride reduction. (C) MS/MS spectrum of (NAG₃+O) after attempted sodium borohydride reduction. No reduced modified NAG₃ was observed, and no ions containing the reducing end was observed. (D) Proposed scheme for observed hydroxyl radical oxidation product.

Figure 2:. Hydroxyl radical carbohydrate footprinting:

An equimolar mixture of NAG₃ and four isomeric trisaccharides (Isomaltotriose, 1-kestose, raffinose, and melezitose) was oxidized with hydroxyl radicals generated by the laser irradiation of hydrogen peroxide in the presence of different proteins. Brackets with asterisk indicate a statistically significant difference between bracketed pairs by ANOVA with Tukey’s post-hoc analysis (p < 0.05). (A) The mixture of isomeric trisaccharides that do not bind to any protein show no significant difference in oxidation, irrespective of the protein used. (B) NAG₃ oxidation is significantly reduced in the presence of proteins it binds (lysozyme and lectin) compared to proteins it does not bind (ubiquitin and myoglobin). Error bars represent one standard deviation from a triplicate data.

Fig 3.. Optimization of H₂O₂ concentration for trifluoromethyl RCF.

(A) Percentage of modified NAG₃ at different concentrations of H₂O₂ in the presence of 40 mM sodium triflinate with a 900V FOX lamp voltage. (B) Percentage modification of NAG₃ and isomeric glycans at 40 mM hydrogen peroxide.

Figure 4:. Trifluoromethyl radical carbohydrate footprinting.

Mixture of NAG₃ and isomeric trisaccharides (Isomaltotriose, 1-kestose, raffinose, and melezitose) was oxidized with trifluoromethyl radicals in the presence of a protein. Brackets with asterisk indicate a statistically significant difference between bracketed pairs by ANOVA with Tukey’s post-hoc analysis (p < 0.05). (A) Isomeric trisaccharides that do not bind to any protein show no significant difference in modification irrespective of the protein present (p = 0.174). (B) NAG₃ modification is significantly reduced (p<0.05) in the presence of proteins it binds (lysozyme and lectin) as compared to proteins it does not bind (ubiquitin and myoglobin). Error bars represent one standard deviation from a triplicate data set.

Figure 5:. MS/MS spectra of reduced trifluoromethylated NAG₃.

(A) MS/MS spectrum of reduced NAG₃ in the presence of lysozyme. (B) MS/MS spectrum of reduced trifluoromethylated NAG₃ in the presence of lysozyme. (C) MS/MS spectrum of reduced NAG₃ in the presence of lectin. (D) MS/MS spectrum of reduced trifluoromethylated NAG₃ in the presence of lectin.

Figure 6.. HILIC-MS analysis of trifluoromethylated NAG₃.

(A) HILIC-MS extracted ion chromatogram of unmodified reduced NAG₃. (B) HILIC-MS extracted ion chromatogram of trifluoromethylated and reduced NAG₃.

Figure 7.. Hydrogen-deuterium exchange shows CF₃ replaces a C-H hydrogen.

(A) MS of unmodified NAG₃ after HDX of ~50%. (B) MS of trifluoromethylated NAG₃ taken from same spectrum. Spectrum is consistent with a trifluoromethylated NAG3 that retains all 11 exchangeable hydrogens with ~50% exchange. It is inconsistent with trifluoromethylated NAG3 with only 10 exchangeable hydrogens with ~50% exchange.