Integrated changes in thermal stability and proteome abundance during altered nutrient states in Escherichia coli and human cells

Abstract

Altered thermal solubility measurement techniques are emerging as powerful tools to assess ligand binding, post-translational modification, protein-protein interactions, and many other cellular processes that affect protein state under various cellular conditions. Thermal solubility or stability profiling techniques are enabled on a global proteomic scale by employing isobaric tagging reagents that facilitate multiplexing capacity required to measure changes in the proteome across thermal gradients. Key among these is thermal proteomic profiling (TPP), which requires 8-10 isobaric tags per gradient and generation of multiple proteomic datasets to measure different replicates and conditions. Furthermore, using TPP to measure protein thermal stability state across different conditions may also require measurements of differential protein abundance. Here, we use the proteome integral stability alteration (PISA) assay, a higher throughput version of TPP, to measure global changes in protein thermal stability normalized to their protein abundance. We explore the use of this approach to determine changes in protein state between logarithmic and stationary phase Escherichia coli as well as glucose-starved human Hek293T cells. We observed protein intensity-corrected PISA changes in 290 and 350 proteins due to stationary phase transition in E. coli and glucose starvation, respectively. These data reveal several examples of proteins that were not previously associated with nutrient states by abundance alone. These include E. coli proteins such as putative acyl-CoA dehydrogenase (aidB) and chaperedoxin (cnoX) as well as human RAB vesicle trafficking proteins and many others which may indicate their involvement in metabolic diseases such as cancer.

Keywords: E. coli stationary phase; glucose starvation; isobaric peptide tagging; ligand-protein interactions; proteome integral stability alteration assay.

FIGURE 1

Integrated PISA and proteome abundance measurements comparing logarithmic and stationary phase E. coli. (A) Growth curve of E. coli measured by OD₆₀₀. Circles represent samples used for logarithmic and stationary phases. (B) Experimental layout for preparing both global proteome and PISA analysis of E. coli protein lysates from the logarithmic and stationary phases of growth. PISA samples were subjected to a thermal gradient (43° to 59° C) (n = 4) and samples from each temperature were pooled, after which they were labeled using TMT reagents alongside proteome samples without thermal treatment (n = 4). All labeled samples were combined and analyzed by 2D-LC-FAIMS-MS2. (C) Comparison of mean log₂ ratios of protein abundance to mean log₂ PISA ratios (proteins significantly different in abundance are shown in yellow (Benjamini-Hochberg-adjusted p-value <0.05 and log₂ fold change <- 1 or > 1)). (D) GO term analysis of proteins with significantly up- and down-regulated protein abundance in stationary phase (Benjamini-Hochberg-adjusted p-value <0.05 and log₂ fold change < –1 or > 1). (E) Comparison of summed TMT intensities of arginine catabolism pathway proteins. (F) Comparison of summed TMT signal intensities of several ribosomal proteins.

FIGURE 2

Comparison of thermally shifted proteins to their protein abundances in logarithmic and stationary phase E. coli. (A) Comparison of mean log₂ normalized nPISA ratios to mean log₂ ratios of protein abundance. Proteins significantly different by nPISA, abundance, or both (Benjamini-Hochberg-adjusted p-value <0.05 and log₂ fold change <- 1 or > 1) appear as indicated. (B) Summed TMT intensities for several proteins with significant differences by nPISA. (C) Heatmap of normalized thermal stability (nPISA) and protein abundance (Protein) of proteins from A. (D) Summed TMT intensities for several proteins with in the heatmap from C.

FIGURE 3

Comparison of nPISA-specific protein differences in stationary phase to Mateus et al. (A) Heatmap showing thermal stability differences across 122 E. coli mutant strains for 12 matched nPISA changes. Shown also are significantly different proteins with respect to thermal stability in this study. (B–F) and the rank of mutants according to their effect on the protein’s stability in Mateus et al. (labeled proteins are mutant strains from Mateus et al. which showed a significant effect on the indicated proteins also observed to have thermal stability differences in this study).

FIGURE 4

Integrated PISA and global proteome abundance measurements in glucose-starved Hek293T cells. (A) Experimental layout for integrating PISA proteomic abundance measurements in Hek293T cells cultured with and without glucose for 24 h. Lysates for PISA were subjected to a thermal gradient (43° to 59°C) and pooled, after which they were labeled using TMT reagents as in Figure 1A. (B) Scatter plot comparing mean log₂ changes in PISA versus protein abundance. Yellow dots signify the significant changes in protein abundance intensity (Benjamini-Hochberg-adjusted p-value <0.05 and log₂ fold change < –0.5 or > 0.5). (C) GO term analysis of proteins that were significantly decreased in abundance in glucose starved cells (Benjamini-Hochberg-adjusted p-value <0.05 and log₂ fold change < 0.5). (D) Examples of summed TMT signal intensities for proteins significantly shifted in abundance having ubiquitin ligase activity, ribosomal biogenesis/translation, (six proteins) and antigen presentation functions in the dataset.

FIGURE 5

Thermally-shifted, but stably-abundant, proteins between starved and unstarved Hek293T cells. (A) Scatter plot comparing nPISA versus mean log₂ changes in protein abundance. Significant differences in nPISA, abundance, or both (Benjamini-Hochberg-adjusted p-value <0.05 and log₂ fold change < −0.5 or >0.5) are indicated as shown. (B) Heatmap of nPISA and protein abundance (Protein) of proteins with significant differences by PISA-level only. (C) Enriched GO terms among proteins significantly shifted by nPISA only (Benjamini-Hochberg-adjusted p-value <0.05 and log₂ fold change < −0.5 or >0.5). Also shown are comparisons of summed TMT signal intensities for several RAB signal transduction pathway proteins (D).

FIGURE 6

Validation of GAPDH and TKT thermal shifts following glucose starvation in Hek293T cells. (A) Comparison of summed TMT signal intensities for GAPDH protein from nPISA. (B) Western blotting analysis of GAPDH in glucose-starved and unstarved Hek293T lysates across a temperature gradient of 43 to 60.4°C. (C) Plot of Western blot band intensities from (B). (D) Summed intensities across all bands from C. (E) Comparison of summed TMT signal intensities for TKT from our PISA experiment. (F) Western blotting analysis of TKT in glucose-starved and unstarved Hek293T lysates across a temperature gradient of 37–52.1°C. (G) Plot of Western blot band intensities from (F). (H) Summed intensities across all bands from (G).