Advances in quantitative hepcidin measurements by time-of-flight mass spectrometry

Abstract

Assays for the detection of the iron regulatory hormone hepcidin in plasma or urine have not yet been widely available, whereas quantitative comparisons between hepcidin levels in these different matrices were thus far even impossible due to technical restrictions. To circumvent these limitations, we here describe several advances in time-of flight mass spectrometry (TOF MS), the most important of which concerned spiking of a synthetic hepcidin analogue as internal standard into serum and urine samples. This serves both as a control for experimental variation, such as recovery and matrix-dependent ionization and ion suppression, and at the same time allows value assignment to the measured hepcidin peak intensities. The assay improvements were clinically evaluated using samples from various patients groups and its relevance was further underscored by the significant correlation of serum hepcidin levels with serum iron indices in healthy individuals. Most importantly, this approach allowed kinetic studies as illustrated by the paired analyses of serum and urine samples, showing that more than 97% of the freely filtered serum hepcidin can be reabsorbed in the kidney. Thus, the here reported advances in TOF MS-based hepcidin measurements represent critical steps in the accurate quantification of hepcidin in various body fluids and pave the way for clinical studies on the kinetic behavior of hepcidin in both healthy and diseased states.

Figure 1. SELDI-TOF MS profiles obtained in the different experiments.

SELDI-TOF MS profiles of (A) hepidin-24 spiked urine sample showing next to the expected hepcidin forms also methionine oxidized (Ox) forms of Hepc24 and Hepc25; (B and C) different patient sera and urines, respectively, spiked with Hepc24 (5 nM into urines and 10 nM into sera). Note, the influence of the serum and urine matrices on the peak height of the Hepc24 spiked to patient samples; (D and E), blank serum and urine samples spiked with both Hepc24 and Hepc25 (7.5 nM of both hepcidin forms into urine and 10 nM into serum). Note that the method appears to be more sensitive for Hepc25 than for Hepc24, with an average peak intensity ratio Hepc24/Hepc25 of 0.693. This is probably due to the absence of a negatively charged aspartic acid residue in Hepc24, which negatively affects its binding on the IMAC-Cu²⁺ protein chip surface. The hepcidin isoforms Hepc20, Hepc22 (only in urine), Hepc24 (synthetic analogue) and Hepc25 are indicated by arrows.

Figure 2. Effect of the use of an internal standard on the hepcidin-25 concentrations in urine and serum of selected clinical populations.

Hepc25 concentrations were calculated in nM based on the known concentration of spiked hepc24 in serum (A) and urine (B) samples. For serum, hepc24 intensities were corrected for the background intensity of unspiked samples (hepc24-bl). Note that for both urine and serum specimens the LLOD depends on the individual sample matrix and therefore varies between samples. The LLOD was determined in the 25 human serum and urine samples by using the background intensities at m/z 2400, 2515, 2846 for serum and at m/z 2299, 2510, 2910, for urine samples, respectively. The detection limit was defined as the mean+2 SD of these measurements and found be 2.0 peak intensity for serum and 1.76 peak intensity for urine. The lower level of detection (LLOD) in nM of each individual sample was determined by incorporating the sample specific hepc24 peak intensity value and these mean LLOD values in peak int for hepc25 peak at 2789 m/z in the formulas 1 and 2 for urine and serum (see Material and Methods section). Ctrl, control; LPS, volunteers injected with polysaccharide (6 h after injection); IDA, iron deficiency anemia; TM, thalassemia major in various stages of disease; HH, C282Y homozygous hereditary hemochromatosis patients of various stages of disease; ◊, hepcidin concentration; Ж, sample specific LLOD, the hepcidin concentration of the sample is then

Figure 3. Correlation between serum hepcidin and ferritin.

Serum hepcidin levels in 23 healthy volunteers (Table 2), as determined by our updated MS method, were correlated with their ferritin levels. Values were log transformed prior to correlation analysis. Pearson correlation: 0.6804 (p = 0.0004).