A quantitative comparison of cytosolic delivery via different protein uptake systems

Abstract

Over many years, a variety of delivery systems have been investigated that have the capacity to shuttle macromolecular cargoes, especially proteins, into the cytosol. Due to the lack of an objective way to quantify cytosolic delivery, relative delivery efficiencies of the various transport systems have remained unclear. Here, we demonstrate the use of the biotin ligase assay for a quantitative comparison of protein transport to the cytosol via cell-penetrating peptides, supercharged proteins and bacterial toxins in four different cell lines. The data illustrate large differences in both the total cellular internalization, which denotes any intracellular location including endosomes, and in the cytosolic uptake of the transport systems, with little correlation between the two. Also, we found significant differences between the cell lines. In general, protein transport systems based on cell-penetrating peptides show a modest total uptake, and mostly do not deliver cargo to the cytosol. Systems based on bacterial toxins show a modest receptor-mediated internalization but an efficient delivery to the cytosol. Supercharged proteins, on the contrary, are not receptor-specific and lead to massive total internalization into endosomes, but only low amounts end up in the cytosol.

Figure 1

The biotin ligase assay and protein uptake system components. (a) Schematic representation of the biotin ligase assay. (b) A non-selected DARPin with an avi tag was expressed in the cytosol of SKBR3 cells stably overexpressing prokaryotic biotin ligase. The lysate was either pre-incubated with streptavidin (+) or not (−) before being probed using anti-DARPin serum by western blotting. The biotinylated protein is symbolized by a grey circle, biotin by an orange circle, and tetrameric streptavidin by red circles. The blot image has been cropped for conciseness. The full-size blot is presented in Supplementary Fig. 5. The four cell lines, which were modified to stably overexpress biotin ligase, are listed. (c) Schematic structural models of the components of the transporter-cargo fusion proteins that were assessed for cytosolic delivery in this study. Not drawn to scale. From left to right, crystal structures used were PDB ID: 1IKQ for Pseudomonas exotoxin A, PDB ID: 1MDT for diphtheria toxin, PDB ID: 1ACC for anthrax protective antigen, PDB ID: 1J7N for lethal factor, PDB ID: 1EMA for green fluorescent protein and PDB ID: 2XEE for the designed ankyrin repeat proteins. The structure of the model cargo NI₁C is a model generated by removing two of the three internal repeats from the structure of the full consensus DARPin with three internal repeats (PDB ID: 2XEE). DARPin, designed ankyrin repeat protein. EpCAM, epithelial cell adhesion molecule. Diphtheria toxin (1-389) contains the mutation G79D inactivating the catalytic activity.

Figure 2

Schematic overview of the purification strategies for the fusion proteins used in uptake experiments. The numbers in the green boxes refer to the numbering system from Fig. 4. § The final purity of #5 was estimated to be ~70%, due to a co-purified degradation fragment (see Fig. 3). * 11 and 12 are binary toxins with two individually produced components. DT, diphtheria toxin; ETA, Pseudomonas exotoxin A; IMAC, immobilized metal-ion affinity chromatography; scGFP, supercharged GFP; SEC, size-exclusion chromatography; TEV protease, Tobacco Etch Virus protease.

Figure 3

Coomassie blue-stained gels showing the purity of the investigated cargo proteins. The numbering system is according to Fig. 4. Please note that 11 and 12 reflect binary toxins and consist of two proteins. Except for protein #3 (penetratin-NI₁C), all proteins were considered to have a purity > 90%. To compensate for the lower purity of #3 (~70%), this protein was tested at higher concentrations as well (5 μM). The juxtaposition of lanes from the same gel that were originally non-adjacent is indicated through black vertical lines. Ac2 and Ec1, designed ankyrin repeat proteins recognizing EpCAM; DT, diphtheria toxin; ETA, Pseudomonas exotoxin A; LF, lethal factor; MBP, maltose-binding protein; NI₁C, consensus designed ankyrin repeat protein; PA, protective antigen; sAntrx, soluble anthrax receptor domain; scGFP, supercharged GFP.

Figure 4

Numbering and block structures showing the modules of the cargo proteins that were assessed in this study. Note that # 11 and # 12 represent delivery systems based on binary toxins and thus encompass two separate components. DT, diphtheria toxin; ETA, Pseudomonas exotoxin A; LF, anthrax lethal factor; PA, anthrax protective antigen; pen, penetratin; santrx, soluble anthrax receptor domain; scGFP, supercharged green fluorescent protein.

Figure 5

Example western blot of a 4-hour uptake experiment of various protein uptake systems in Flp-In 293 cells. The numbering system is according to Fig. 4. The blot images have been cropped for conciseness. The full-size blots are presented in Supplementary Fig. 5.

Figure 6

Uptake of various systems in biotin ligase-overexpressing cells. The numbering system is according to Fig. 4. Concentrations are indicated for the respective conditions. LF-cargo fusions were used at 0.2 μM; PA fusions at 20 nM. Quantification of total cellular (a,c,e,g,i) and cytosolic uptake (b,d,f,h,j) of 4-hour (Flp-In 293) and 20-hour (all) uptake experiments in the indicated cell lines. Data points reflect absolute concentrations that were present in either the “total cell” or “cytosol” at the time of lysis, calculated using knowledge on the cell number, cell volume and a reference protein, as described in detail in the Methods section. All data points are derived from fully independent experiments. If no data points are shown, no protein could be detected. The horizontal line represents the average. * due to band overlap with an endogenously biotinylated species in the cell line, the cargo LF-NI₁C was replaced with LF-NI₂C-dest.5, which has a MW that is 3.4 kDa higher but possesses similar delivery characteristics.