Structural insight into the TRIAP1/PRELI-like domain family of mitochondrial phospholipid transfer complexes

Abstract

The composition of the mitochondrial membrane is important for its architecture and proper function. Mitochondria depend on a tightly regulated supply of phospholipid via intra-mitochondrial synthesis and by direct import from the endoplasmic reticulum. The Ups1/PRELI-like family together with its mitochondrial chaperones (TRIAP1/Mdm35) represent a unique heterodimeric lipid transfer system that is evolutionary conserved from yeast to man. Work presented here provides new atomic resolution insight into the function of a human member of this system. Crystal structures of free TRIAP1 and the TRIAP1-SLMO1 complex reveal how the PRELI domain is chaperoned during import into the intermembrane mitochondrial space. The structural resemblance of PRELI-like domain of SLMO1 with that of mammalian phoshatidylinositol transfer proteins (PITPs) suggest that they share similar lipid transfer mechanisms, in which access to a buried phospholipid-binding cavity is regulated by conformationally adaptable loops.

Figure 1

Crystal structure of TRIAP1

1. Cartoon representation in green for the crystal structure of TRIAP1 showing the location of the disulphide bonds (yellow) and the twin CX₉C motifs.

2. ¹H-¹⁵N HSQC NMR spectrum of TRIAP1ΔC (blue) overlaid on a single ¹H-¹⁵N HSQC NMR spectrum of full-length TRIAP1 from a ¹⁵N-transverse relaxation measurement series (red). The relaxation delay for the time point in the ¹⁵N-transverse relaxation experiment was set such that all ¹⁵N-signals for the folded coiled coil have decayed and therefore would not be observed in the spectrum. Remaining signals observed represent amides with slow transverse relaxation and therefore are highly dynamic and disordered. Assignment of the ¹H-¹⁵N HSQC spectra reveals that this flexible region is localised to the C-terminus of full-length TRIAP1.

3. Cartoon representation for the superposition of TRIAP1 with the solution structure of Mia40 revealing topological similarity of the twin CX₉C-coiled coil domain.

4. Conserved hydrophobic stripe on the surface of TRIAP1 comprising conserved aromatic residues. The conserved V4 residue in the N-terminus of helix I is also shown. Backbone of TRIAP1 is shown as a cartoon and stacked aromatic side chains labelled in stick representation. Shading of side chains according to alignment shown in (E).

5. Protein sequence alignment for TRIAP1, Mdm35 and selected homologues. Positions of experimentally determined and predicted α-helices are indicated above the alignment. Disulphide bond connectivities are also indicated. Red shading indicates invariant residues across the homologues, and yellow shading indicates locations where there are conserved residues in three homologues.

Figure 2

Crystal structure of the apo TRIAP1-SLMO1 complex

1. Cartoon representation for the crystal structure of the TRIAP1-SLMO1 complex. TRIAP1 is shown in green and SLMO1 in orange with annotated secondary structure elements.

2. Highlighted TRIAP1-SLMO1 interface with a superimposition of free TRIAP1 (grey) and bound TRIAP1 (green). The hydrophobic side chains of TRIAP1 are in green sticks, and the complementary interaction region on SLMO1 is shown as red cartoon. The rest of SLMO1 is shown as an orange cartoon.

3. Hydrophobic interaction at the TRIAP1-SLMO1 interface. Left: cartoon representation of the TRIAP1-SLMO1 complex with key interfacial hydrophobic side chains shown as sticks and labelled with residue numbers. TRIAP1 is coloured green, and the complementary interaction region on SLMO1 is shown as red cartoon with the remaining sequence of SLMO1 shown as an orange cartoon. Right: hydrophobic contacts to the N-terminal V4 from TRIAP1.

4. SDS–PAGE analysis of His-tag pull-down assays with His-SLMO1 and TRIAP1. For each sample, the column flow through (FT) and elution (EL) fraction are shown. SLMO1 mutants are shown in the left panel, and the lack of recovery of mutant complexes V36A and L49A suggests that these alterations disrupt the formation of the complex. TRIAP1 mutants are shown on the right, and while mutant complex can be purified for the single mutants, the complex is lost when F41A in TRIAP1 is accompanied by V38A in SLMO1.

Figure 3

The phospholipid head group-binding cavity within SLMO1

1. Protein sequence alignment for the PRELI domain protein family. Positions of secondary structural elements and loops for SLMO1 are numbered above the alignment. Numbering for the S. cerevisia Ups1 sequence is indicated below the alignment. The locations of the charge and loop mutations are highlighted with magenta and blue triangles, respectively. Interface mutations are highlighted with green triangles. Red shading indicates invariant residues across the homologues, and yellow shading indicates locations where there are conserved residues in at least four homologues.

2. Left panel: cut-through of the solvent-exposed surface for SLMO1 revealing the partially hydrophilic cavity. SLMO1 surface is coloured orange with positive and negative charge residues coloured blue and red, respectively. Right panel: cartoon representation showing four conserved charged side chains that are proximal to the cavity.

3. NBD-PA transfer by the TRIAP1-SLMO1 complex. Donor liposomes (12.5 μM; DOPC/DOPE/CL/Lac-PE/NBD-PA/Rhod-PE = 50/18/15/10/5/2%) and acceptor liposomes (50 μM; DOPC/DOPE/CL/Lac-PE/DOPA = 50/20/15/10/5%) were incubated for 5 min with indicated concentration of TRIAP1-SLMO1 and the NBD fluorescence was monitored. Values were normalised to the NBD fluorescence of liposomes lacking quenching Rhod-PE.

4. PA transfer for native and R54E Ups1-Mdm35 complexes. Upper panel: NBD-PA transfer by the Ups1-Mdm35 complex and Ups1R54E-Mdm35. Donor liposomes (12.5 μM; DOPC/DOPE/CL/Lac-PE/NBD-PA/Rhod-PE = 50/28/5/10/5/2%) and acceptor liposomes (50 μM; DOPC/DOPE/CL/Lac-PE/DOPA =50/30/5/10/5%) were incubated for 5 min with 10 nM of Ups1-Mdm35 or mutant, and the NBD fluorescence was monitored. Values were normalised to the NBD fluorescence of liposomes lacking quenching Rhod-PE. Lower panel: quantitative assessment of the transport activity. Values are represented as the number of NBD-PA transported per complex in a minute. Columns and error bars indicate the mean ± SD. n = 4. Student's t-test was used to calculate P-values. **P < 0.01.

5. Binding to PA-containing liposomes. Purified Ups1-Mdm35 complex or its mutant variant was incubated with liposomes composed of DOPC/POPE/DOPA (50/30/20%), and binding was assessed by flotation of liposomes in a sucrose gradient. Upper panel: fractions after sucrose gradient were analysed by SDS–PAGE and CBB staining. All liposomes were recovered in the upper two fractions. Lower panel: quantification of Ups1 and Mdm35. Signals in upper two fractions (bound) or lower two fractions (unbound) were quantified and are represented as a fraction in total signals of all four fractions.

Figure 4

PRELI domains are structurally similar to mammalian phosphatidylinositol transfer proteins

1. Cartoon representation for the superposition of the modelled Mdm35-Ups1 structure (blue and red, respectively) with apo mouse PITPα (pdb: 1KCM; green). The identified lipid exchange loop in PITPα and equivalent region in Ups1 (L4-a2-L5) are indicated.

2. Cartoon representation for the superposition of the modelled Mdm35-Ups1 structure (blue and red, respectively) with phosphatidylcholine-bound rat PITPα (pdb: 1T2Z; brown). Conformational changes in lipid exchange loop and the C-terminal helical lid (indicated by arrows) close the structure and cap the bound phospholipid.

3. Liposome binding. Purified Mdm35-Ups1 complex or its mutant variant was incubated with liposomes composed of DOPC/POPE/DOPA (50/30/20%), and binding was assessed by flotation of liposomes in a sucrose gradient. Upper panel: fractions after sucrose gradient were analysed by SDS–PAGE and CBB staining. All liposomes were recovered in the upper two fractions. Lower panel: quantification of Ups1 and Mdm35. Signals in upper two fractions (bound) or lower two fractions (unbound) were quantified and represented as a fraction of total signals of four fractions.

4. NBD-PA extraction. Purified Mdm35-Ups1 complexes (80 nM) were incubated with liposomes (4 μM) composed of DOPC/POPE/NBD-PA/Rhod-PE (50/43/5/2%) filled with 12.5% sucrose. After incubation at 25°C for 2 min, liposomes were sedimented by an ultracentrifugation step (200,000× g, 30 min) and NDB fluorescence in the supernatant fraction was quantified using standard probes of NBD-PA. Columns and error bars indicate the mean ± SD. n = 3.

Figure 5

In vivo analysis of Ups1-mutant yeast strains and suggested mechanism of assisted PA transfer by PRELI-like domains

1. Restoration of CL levels by plasmid-encoded Ups1 and its mutant variants. Δups1 cells carrying empty vector (YCplac111ADH, vector) or a plasmid encoding indicated Ups1 variants were grown to logarithmic phase in YP medium supplemented with 2% galactose. Cells were collected and subjected to lipid extraction and phospholipidome analysis. CL levels were represented as a proportion in total phospholipids. Wild-type cells carrying empty vector were analysed as a control. Columns and error bars indicate the mean ± SD. n = 3. Student's t-test was used to calculate P-values. **P < 0.01.

2. Proposed mechanism of phosphatidic acid (PA) transport by PRELI-like domains. Phospholipid transport between mitochondrial inner and outer membranes (MIMs & MOMs) catalysed by TRIAP1/Mdm35-PRELID complexes: (a) import of PRELID and degradation by mitochondrial proteases if no complex formed; (b) folding of PRELI-like domain on the TRIAP1/Mdm35 twin coiled-coiled CX₉C motif; (c) donor bilayer (MOM) binding and preloading by the complex; (d) PA loading and dissociation of TRIAP1/Mdm35; (e) recapture of loaded PRELID by TRIAP1/Mdm35, donor bilayer binding and delivery of PA; (f) degradation of PRELID at the MIM; and (g) biosynthesis of cardiolipin (CL) from PA.