Fast photochemical oxidation of protein footprints faster than protein unfolding

Abstract

Fast photochemical oxidation of proteins (FPOP) is a chemical footprinting method whereby exposed amino-acid residues are covalently labeled by oxidation with hydroxyl radicals produced by the photolysis of hydrogen peroxide. Modified residues can be detected by standard trypsin proteolysis followed by LC/MS/MS, providing information about solvent accessibility at the peptide and even the amino-acid level. Like other chemical footprinting techniques, FPOP must ensure only the native conformation is labeled. Although oxidation via hydroxyl radical induces unfolding in proteins on a time scale of milliseconds or longer, FPOP is designed to limit (*)OH exposure to 1 micros or less by employing a pulsed laser for initiation to produce the radicals and a radical-scavenger to limit their lifetimes. We applied FPOP to three oxidation-sensitive proteins and found that the distribution of modification (oxidation) states is Poisson when a scavenger is present, consistent with a single conformation protein modification model. This model breaks down when a scavenger is not used and/or hydrogen peroxide is not removed following photolysis. The outcome verifies that FPOP occurs on a time scale faster than conformational changes in these proteins.

Figure 1

Schematic of FPOP whereby a protein in a solution flowing in fused silica reacts with OH radicals. Shown is the reaction region with typical flow rate, laser pulse frequency, and laser spot size.

Figure 2

Graph (a) is of the ESI-QTOF mass spectrum of the 15th charge state of FPOP-treated β-lactoglobulin and its composite model. Graph (b) is of the background-subtracted model and its first five oxygen-addition state components (hashed fill). The 0^th state (gray) is made up of a 53% contribution from the exclusion volume fraction (not shown) and a 47% contribution from the irradiated portion of the sample that did not react with OH radicals.

Figure 3

ESI-QTOF mass spectra of the 15th charge state of six β-lactoglobulin samples subjected to varying FPOP conditions. Spectrum (a) is of the control, absent only laser irradiation; (b) is of a normal FPOP treatment with an EVF 60%; (c) is of a normal treatment with an EVF 30%; (d–f) are of samples with an EVF of 15%; (d) is of a normal treatment (all controls); (e) is of a treatment absent 20 mM Gln; and (f) is of a treatment without use of scavenger (Gln), removal of peroxide (by catalase), and control of post FPOP oxidation (addition of Met).

Figure 4

ESI-QTOF mass spectra (a–c) are of the 15^th charge state apo-calmodulin; spectra (e–g) are of the 10^th charge state of lysozyme. Spectra (a) and (d) are of the controls, absent only laser irradiation; (b) and (e) are of samples after normal FPOP treatment (i.e., with scavenger and removal of peroxide post FPOP); (c) and (f) are of samples after FPOP treatment absent the scavenger (20 mM Gln).

Figure 5

The irradiation volume oxygen-addition state ion counts are modeled for the spectrum of each bovine β-lactoglobulin sample. The modeling was constrained such that the calculated EVF matched the independently measured EVF. Per condition, shown with standard error bars along a solid line, are the averages of the normalized ion counts of four replicates (a–c) and two replicates (d–e). The diamonds along a dotted line show the non-linear regression best-fit Poisson distribution to the average oxygen-addition state distribution. The number of states per sample distribution fit to a Poisson was chosen to account for at least 95% of protein signal. Plot (a) is for sample submitted to FPOP but without the glutamine radical scavenger. When all zero oxygen-addition protein is assigned to the EVF, its value is 9%, short of the measured 15%. Plot (b) is for sample submitted to FPOP but without removal of peroxide post-FPOP, with a 15% EVF. Plot (c) is for sample FPOP-treated with a 15% EVF. Plot (d) is for sample FPOP-treated with a 30% EVF. Plot (e) is for sample FPOP-treated with a 60% EVF.

Figure 6

The irradiation volume oxygen-addition state ion counts are modeled for the spectrum of each β-lactoglobulin sample. A non-linear regression best fit Poisson distribution was simultaneously determined; the EVF was varied to optimize the fit. Per condition, shown with standard error bars along a solid line, are the averages of the normalized ion counts of 4 replicates (b and c); case (a) is singlicate. The number of states per sample distribution plotted account for at least 95% of protein signal. The diamonds along a dotted line show the Poisson distribution. Plot (a) is for sample FPOP-treated without glutamine radical scavenger, post-FPOP catalase, or post-FPOP methionine. The best fit exclusion volume was calculated at 6.6%. Plot (b) is for sample FPOP-treated without glutamine, with a calculated EVF of 7.0 ± 0.4%. Plot (c) is for sample FPOP-treated with a calculated EVF of 17 ± 2%. In all cases the measured EVF was 15%.