DNA organization by the apicoplast-targeted bacterial histone-like protein of Plasmodium falciparum

Abstract

Apicomplexans, including the pathogens Plasmodium and Toxoplasma, carry a nonphotosynthetic plastid of secondary endosymbiotic origin called the apicoplast. The P. falciparum apicoplast contains a 35 kb, circular DNA genome with limited coding capacity that lacks genes encoding proteins for DNA organization and replication. We report identification of a nuclear-encoded bacterial histone-like protein (PfHU) involved in DNA compaction in the apicoplast. PfHU is associated with apicoplast DNA and is expressed throughout the parasite's intra-erythocytic cycle. The protein binds DNA in a sequence nonspecific manner with a minimum binding site length of approximately 27 bp and a K(d) of approximately 63 nM and displays a preference for supercoiled DNA. PfHU is capable of condensing Escherichia coli nucleoids in vivo indicating its role in DNA compaction. The unique 42 aa C-terminal extension of PfHU influences its DNA condensation properties. In contrast to bacterial HUs that bend DNA, PfHU promotes concatenation of linear DNA and inhibits DNA circularization. Atomic Force Microscopic study of PfHU-DNA complexes shows protein concentration-dependent DNA stiffening, intermolecular bundling and formation of DNA bridges followed by assembly of condensed DNA networks. Our results provide the first functional characterization of an apicomplexan HU protein and provide additional evidence for red algal ancestry of the apicoplast.

Figure 1.

Sequence alignment and structure model of PfHU. (A) ClustalW alignment of PfHU with bacterial (Bacillus stearothermophilus, B. subtilis, Thermotoga maritima), red algal chloroplast (Cyanidioschyzon merolae) and apicomplexan (Toxoplasma gondii) HU proteins. Conserved residues described in the text are marked with asterisk. (B) Structure of the PfHU dimer modeled on the crystal structure of B. stearothermophilus HU. The position of the leucine residue (L63) that replaces the conserved proline of other HU proteins is indicated. The 42 aa C-terminal domain could not be modeled on any known protein structure and is not depicted in the figure.

Figure 2.

Expression of recombinant PfHU and its detection in P. falciparum. (A) Purified recombinant proteins PfHU_ΔC (lane 1), PfHU_p (lane 2) and PfHU_up (lane 3). M denotes marker lane. (B) Multimeric forms of purified PfHU_p seen in Coomassie-stained SDS–PA gels (i) and detected by anti-6XHis antibody in Western blots (ii). (C) Chemical-crosslinking of 5 µg (lane 2) and 7 µg (lane 3) PfHU_p indicates dimerization of the protein in solution. Glut., glutaraldehyde. Dimer and tetramer forms are indicated by arrows. (D) Detection of processed HU protein in P. falciparum lysates immunoprecipitated with rabbit anti-PfHU_p antibody followed by detection using mouse anti-PfHU_p antibody in a Western blot. Lane 1 represents immunoprecipitation with rabbit preimmune serum. (E) Expression of PfHU in P. falciparum intra-erythrocytic stages. The upper and lower panels are Western blots using anti-PfHU_p antibody and α, β-tubulin antibodies (Sigma), respectively. R, rings; ET, early trophozoites; LT, late trophozoites; S, schizonts. Pre-I, lysate probed with preimmune serum. Arrows indicate unprocessed and processed forms of PfHU.

Figure 3.

Localization of PfHU. (A) Immunolocalization of PfHU using confocal microscopy. Panels show nuclear DNA staining with DAPI (1), PfHU fluorescence (2), MitoTracker Red signal (3) and their overlap (4) in a late trophozoite. The corresponding phase–contrast scan is shown in (5). (B) Co-localization of PfHU and apicoplast-targeted GFP. Nuclear DNA stained with DAPI (1), PfHU signal (2), GFP signal (3) and their overlay (4) are shown. (C) Anti-PfHU_p antibody specifically precipitates apicoplast DNA (plDNA) in a ChIP assay. Lanes 2–4 show PCR products obtained using primers for nuclear DNA (HU sequence) while lanes 5–7 show PCR products obtained using plDNA-specific primers for RIII. ID, input DNA; PI, preimmune serum; I, immune serum.

Figure 4.

DNA-binding properties of PfHU_p. (A) EMSA depicting binding of PfHU_p to supercoiled and linear pBR322. Four hundred nanograms of supercoiled (lanes 2–6) or linear (lanes 7–11) plasmid was incubated with PfHU_p at different protein/DNA mass ratios. M, DNA marker. (B) EMSA with increasing concentrations of PfHU_p (lanes 2–7) and PfHU_ΔC (lanes 8–13) using supercoiled pBR322 DNA. Lane 1 is free DNA. (C) Binding of PfHU_p to supercoiled DNA in the presence of 50 mM (i) and 100 mM (ii) NaCl. (D) DNA supercoiling assay with increasing concentrations of PfHU_p (lanes 3–7) and PfHU_ΔC (lanes 8–12). Lane 1 is naked DNA (negatively supercoiled pBR322), lane 2 is pBR322 partially relaxed with topoisomerase I, lane 12 is linearized pBR322. Form-I, supercoiled DNA; form-II, relaxed DNA.

Figure 5.

PfHU_p-mediated condensation of E. coli nucleoids. (A) Fluorescence images of DAPI-stained, IPTG-induced E. coli cells that had been co-transformed with pQE30 + RIG plasmid (1 and 2) or pQE30-HU_p + RIG plasmid (3 and 4). (B) Western blot using anti-PfHU_p antibody to detect expression of PfHU_p in E. coli cells co-transformed with RIG and pQE30 (lane 1) or pQE30-HU_p (lane 2) followed by induction with IPTG. Arrow indicates the PfHU_p band.

Figure 6.

Binding site length and affinity of PfHU_p for DNA. (A) EMSA showing binding of PfHU_p with end-labeled 55 bp probe. (B) EMSA of PfHU_p with a 30 bp probe. (C) The K_d of the single complex obtained in (B) was determined from its binding isotherm by curve-fitting using nonlinear regression. The mean K_d value from three repeat experiments was estimated as 62.7 ± 6.5 nM.

Figure 7.

DNA concatenation by PfHU_p. (A) DNA ligation of a 136 bp labeled DNA fragment carried out in the presence of increasing concentrations of PfHU_p (lanes 3–6). Lane 1 is free DNA while lane 2 is DNA probe ligated in the absence of PfHU_p. Ligation reactions were treated with BAL31 nuclease to detect circularized DNA products (lanes 7–10). (B) Ligation of the 136 bp fragment in the presence of increasing concentrations of PfHU_ΔC (lanes 3–5 and 7–9). Lane 1 is free DNA while lanes 2 and 6 are DNA probe ligated in the presence of HBsu as positive control for DNA circularization. (C) Percentage transformation efficiency of ligation reactions of linear pBR322 carried out in the presence of PfHU_p. Transformation efficiency was calculated as percentage of that obtained with pBR322 ligated in the absence of PfHU_p. Mean and SE of repeat determinations is plotted.

Figure 8.

AFM images of PfHU_p-linear pBR322 DNA complexes with increasing dimer/bp ratio. (A) DNA in the absence of protein. (B) Dimer/bp ratio of 1 : 750. Stiffened DNA strands (i) as well as DNA bundles (ii) are shown. (C) Dimer/bp ratio of 1 : 500. Formation of complexes with a small number of foci and extruding DNA loops (i), a DNA bridge resulting in DNA looping (ii) and a nucleoprotein complex with a single focus (iii) are shown. (D) Dimer/bp ratio of 1 : 250. Large complexes (i and iii) are formed by the assembly of DNA bundles (ii) and bridges.