Comprehensive identification of protein substrates of the Dot/Icm type IV transporter of Legionella pneumophila

Abstract

A large number of proteins transferred by the Legionella pneumophila Dot/Icm system have been identified by various strategies. With no exceptions, these strategies are based on one or more characteristics associated with the tested proteins. Given the high level of diversity exhibited by the identified proteins, it is possible that some substrates have been missed in these screenings. In this study, we took a systematic method to survey the L. pneumophila genome by testing hypothetical orfs larger than 300 base pairs for Dot/Icm-dependent translocation. 798 of the 832 analyzed orfs were successfully fused to the carboxyl end of β-lactamase. The transfer of the fusions into mammalian cells was determined using the β-lactamase reporter substrate CCF4-AM. These efforts led to the identification of 164 proteins positive in translocation. Among these, 70 proteins are novel substrates of the Dot/Icm system. These results brought the total number of experimentally confirmed Dot/Icm substrates to 275. Sequence analysis of the C-termini of these identified proteins revealed that Lpg2844, which contains few features known to be important for Dot/Icm-dependent protein transfer can be translocated at a high efficiency. Thus, our efforts have identified a large number of novel substrates of the Dot/Icm system and have revealed the diverse features recognizable by this protein transporter.

Figure 1. Construction of a library expressing fusions of β-lactamase and L. pneumophila hypothetical proteins.

A. A schematic structure of the fusion proteins and the screening strategy. In most cases, the gene was fused with the β-lactamase by inserting into the vector as a BamHI/SalI fragment. After infection, samples were loaded with the CCF4-AM dye and were inspected under a fluorescence microscope. B. Evaluation of the library for expression of the fusion proteins. Plasmids directing expression of β-lactamase fusions were introduced into a wild type L. pneumophila strain. Total cell lysates of bacteria grown in the presence of IPTG were used to examine the steady state of the fusion proteins by immunoblot. In each image, the detection of a protein nonspecifically recognized by the antibody (arrow) was used as a loading control.

Figure 2. Dot/Icm-dependent translocation of substrates.

Effectors identified in this study were divided into four groups according to their transfer efficiencies, 5 genes from each group were shown as representatives. U937 cells seeded in 96-well plates were infected with wild type or dot/icm-deficient L. pneumophila strains expressing a gene fusion and images were acquired 2 hrs after CCF4-AM loading with a DP72 color camera (Olympus). Group I, genes with translocation efficiency >90%; Group II, genes with translocation efficiency between 50% and 80%; Group III, genes with translocation efficiency between 20% and 45% and Group IV, genes with translocation efficiency less than 15%.

Figure 3. Translocation efficiency does not correlate with levels of β-lactamase fusion expressed in L. pneumophila.

A. The translocation efficiency of 9 substrates in the β-lactamase assay. After CCF4-AM loading, macrophages infected with bacterial strains expression fusions between β-lactamase and individual genes were inspected under a fluorescence microscope, translocation efficiencies were obtained by enumerating cells emitting blue and green fluorescence signals, respectively. Experiments were performed in triplicates and at least 300 cells were counted each sample. Similar results were obtained in at least two independent experiments. B. The levels of the fusion proteins in L. pneumophila strains used for infections shown in A. Bacterial cells equivalent to one OD₆₀₀ unit were lysed in 200 µl of SDS loading buffer, 15 µl of boiled supernatant were resolved by SDS-PAGE. After transferring to nitrocellulose membranes, the fusion protein was detected with a β-lactamase specific antibody by immunoblot. The isocitrate dehydrogenase (ICDH) was probed as a loading control. Samples: 1. Lpg1776; 2, Lpg0021; 3, Lpg2425; 4, Lpg1147; 5, Lpg0181; 6, Lpg2555; 7, Lpg2874; 8, Lpg0405; 9, Lpg0195.

Figure 4. Diverse features presented in the C-terminal end of Dot/Icm substrates.

A. Alignment of the last 50 amino acids of three well-established effectors and the new substrate Lpg2844 to highlight the features important for translocation found in Dot/Icm substrates, including: i) The hydrophobic residue at the -3^rd position (▽, red) and ii) the E-block (the three blue residues in SidF). Note the different amino acids composition in Lpg2844. B–D. A region containing the last 100 amino acids of Lpg2844 is important and sufficient for promoting translocation. Bacterial strains expressing fusions of β-lactamase to full-length Lpg2844 (I), it's last 100 aa (II) or a fragment lacking the last 100 aa (III) were used to infect macrophages and infected cells were loaded with the CCF4-AM dye. Translocation efficiency (B) was obtained as described in Fig. 3, data shown are the average of three independent experiments done in triplicates; stable expression of the fusions by L. pneumophila, equal amount of protein samples resolved by SDS-PAGE was probed for the fusions with a β-lactamase specific antibody. The ca. 60-kDa non-specific band detected by the antibody was used as a loading control (arrow in panel C). Representative images of infected cells loaded with CCF4-AM (D). Similar results were obtained in at least two independent experiments.

Figure 5. The distribution of all verified Dot/Icm substrates according to their length.

Proteins experimentally shown as substrates of the Dot/Icm transporter were collected and sorted according to the length of the gene, which were then divided into four groups: I, genes larger than 3 kbp; II, genes ranging between 2 to 3 kbp; III, genes ranging between 1 to 2 kbp and IV, genes smaller than 1 kbp.