Pex19p, a farnesylated protein essential for peroxisome biogenesis

Abstract

We report the identification and molecular characterization of Pex19p, an oleic acid-inducible, farnesylated protein of 39.7 kDa that is essential for peroxisome biogenesis in Saccharomyces cerevisiae. Cells lacking Pex19p are characterized by the absence of morphologically detectable peroxisomes and mislocalization of peroxisomal matrix proteins to the cytosol. The human HK33 gene product was identified as the putative human ortholog of Pex19p. Evidence is provided that farnesylation of Pex19p takes place at the cysteine of the C-terminal CKQQ amino acid sequence. Farnesylation of Pex19p was shown to be essential for the proper function of the protein in peroxisome biogenesis. Pex19p was shown to interact with Pex3p in vivo, and this interaction required farnesylation of Pex19p.

FIG. 1

(A) Location of the PEX19 gene within the 4.8-kb genomic SpeI-BamHI fragment of chromosome IV. The arrows denote the orientations of PEX19 and adjacent genes. (B) Complementation analysis of the PEX19 genomic region. Subclones of the 4.8-kb SpeI-BamHI genomic fragment are shown along with their ability to restore growth of the pex19 mutant on oleic acid. −, complementing activity was not shown; +, full complementing activity was shown. The location of the PEX19 open reading frame within each subclone is indicated by the black bars. The smallest complementing region identified was the 1.793-kb ClaI-KpnI fragment, which was subjected to nucleotide sequence analysis. (C) Targeted gene disruption strategy for replacement of PEX19 with LEU2.

FIG. 2

(A) Nucleotide sequence of the PEX19 gene and deduced amino acid sequence of Pex19p. The potential oleic acid response element of the PEX19 promoter is underlined, and the putative TATA box is above the broken line. The CAAX box for farnesylation is double underlined. Asterisks indicate the stop codon. These sequence data are available from EMBL-GenBank-DDBJ under accession no. Z74113. (B) Hydropathy analysis of Pex19p. A hydropathy profile of the predicted amino acid sequence of Pex19p was calculated (44) with a window size of 17 amino acids. The analysis showed that the PEX19 gene product is extremely hydrophilic, with no apparent hydrophobic domains with the potential to span a membrane. X, axis, amino acids; y axis, hydrophobicity values.

FIG. 3

Alignment of deduced amino acid sequences of the products of S. cerevisiae PEX19 (ScPex19p), Caenorhabditis elegans open reading frame F54F2.8 (CeF54F2.8), Chinese hamster PxF (CgPxF) (41), and the human HK33 gene (HsHK33) (8). Amino acids identical or similar in S. cerevisiae Pex19p and at least one of the three other proteins are indicated by a black background. Similarity rules were as follows: G = A = S, A = V, V = I = L = M, I = L = M = F = Y = W, K = R = H, D = E = Q = N, and S = T = Q = N. Dashes indicate gaps.

FIG. 4

Mutant pex19Δ cells lack morphologically detectable peroxisomes. Shown are electron micrographs of oleic acid-induced cells of null-mutant pex19Δ lacking Pex19p (A) and pex19Δ cells complemented with the isolated PEX19 gene on a single-copy plasmid (pRS-PEX19) (B). In the case of the complemented mutant, growth on oleic acid resulted in marked peroxisome proliferation. Peroxisomes were not detectable in sections of cells of the pex19Δ mutant. L, lipid droplet; M, mitochondrion; N, nucleus; P, peroxisome. Bar, 1 μm.

FIG. 5

Mutant pex19Δ cells are defective in peroxisomal matrix protein import. (A) Immunofluorescence microscopy localization of PTS2-containing thiolase (Fox3p) and PTS1-containing Pcs60p in wild-type, pex19Δ mutant, and complemented pex19Δ mutant cells expressing pRS-PEX19. Bar, 5 μm. (B) Localization of peroxisomal matrix proteins in pex19Δ cells. A homogenate of oleic acid-induced pex19Δ cells was separated on a 20 to 54% (wt/wt) sucrose gradient by equilibrium density centrifugation. Peroxisomal marker enzymes catalase and 3-oxoacyl-CoA thiolase as well as the mitochondrial marker fumarase in gradient fractions were monitored by activity measurements. Mitochondria peaked in fraction 9 at a density of 1,185 g/cm³. Peroxisomal matrix enzymes were nearly exclusively found in the loading zone of the gradient, consistent with their mislocalization to the cytosol.

FIG. 6

The HK33 gene product is the putative human ortholog of Pex19p. (A) Growth of pex19Δ transformants expressing S. cerevisiae PEX19-human HK33 chimeras on oleic acid medium. Expression of the YH1 construct complements the growth defect of pex19Δ cells, suggesting that the fusion protein is functionally active. The yeast and human protein amino acid (aa) regions fused are as follows: YH1 (yeast aa 1 to 231, human aa 187 to 299), YH2 (yeast aa 1 to 86, human aa 87 to 299), YH3 (yeast aa 1 to 154, human aa 133 to 299), HY1 (human aa 1 to 186, yeast aa 232 to 350), and Y1 (yeast aa 1 to 231). The solid boxes indicate the S. cerevisiae Pex19p portion; the open boxes indicate the human HK33 gene product portion. (B) Electron micrograph of oleic acid-induced pex19Δ cells expressing fusion construct YH1. Complementation of the mutant strain is indicated by the presence of peroxisomes. p, peroxisome; n, nucleus, v, vacuole. Bar, 1 μm.

FIG. 7

(A) Immunological detection of Pex19p. Equal amounts of oleic acid-induced wild-type and pex19Δ homogenates (50 μg of protein) were subjected to immunoblot analysis with rabbit antiserum against Pex19p. Pex19p was detected as a doublet of 44 and 46 kDa. (B) Immunoblot analysis of cell fractions obtained by centrifugation of cell homogenates from oleic acid-induced wild-type cells at 25,000 × g. Equal proportions of the supernatant and pellet fractions were loaded on the gel. Molecular mass standards (in kilodaltons) are indicated on the left. (C) Subcellular localization of myc-tagged Pex19p by immunogold labeling. Sections of pex19Δ cells expressing myc-PEX19 from the multicopy plasmid YEp-mycPEX19 were probed with polyclonal antiserum against Pex19p and goat anti-rabbit antibodies coupled to 10-nm-diameter gold particles. p, peroxisome. Bar, 0.2 μm.

FIG. 8

Time course of Pex19p induction during growth on oleic acid. (A) Wild-type cells were precultured in 0.3% SD and subsequently shifted to YNO. At the indicated time points, whole-cell extracts were prepared for immunological detection of oleic acid-inducible peroxisomal thiolase (Fox3p) (24), constitutively expressed Kar2p (62), and Pex19p. The amount loaded per lane corresponds to 0.3 mg of cells. (B) Northern blot analysis of total RNA from wild-type (wt) and pex19Δ mutant cells grown on either glucose (i.e., SD) or oleate (i.e., YNO) as indicated. A radiolabeled internal fragment of the PEX19 open reading frame was used as a probe. Fifty micrograms of total RNA was loaded per lane.

FIG. 9

In vivo and in vitro farnesylation of Pex19p. (A) C-terminal amino acid sequence of wild-type Pex19p and mutated Pex19p-C347S. The letters in boldface type indicate amino acid substitutions within the CAAX box. (B) Immunoblot analysis of Pex19p in whole-cell lysates from oleic acid-induced pex19Δ mutant cells expressing wild-type or mutated Pex19p from pRSPEX19 or pRSPEX19-C347S, respectively. Note the disappearance of the faster-migrating form of Pex19p upon expression of the mutated Pex19p, suggesting that it represents the farnesylated Pex19p. (C) Fluorogram and immunoblot results of in vitro farnesylation assays. Yeast homogenates expressing wild-type or mutated Pex19p from YEpPEX19 or YEpPEX19-C347S, respectively, were subjected to an in vitro assay with [³H]farnesyldiphosphate in the absence (−) or presence (+) of farnesyltransferase as indicated. Comparison with the immunoblot shows that the faster-migrating Pex19p form had incorporated the farnesyl moiety. The absence of farnesylated Pex19p upon expression of the mutated Pex19p indicated that the CAAX box of Pex19p is essential for its farnesylation. Positions of molecular mass standards are indicated for both panels B and C.

FIG. 10

Farnesylation is essential for proper function of Pex19p in peroxisome biogenesis. (A) Growth behavior on oleic acid medium of wild-type cells, pex19Δ mutant cells, and mutant cells expressing wild-type Pex19p or Pex19p containing the indicated mutations of the CAAX box. The pex19Δ null mutant was not able to grow on oleic acid medium. The mutant cells regained the wild-type growth behavior upon transformation with the wild-type PEX19 gene. Cells expressing Pex19p containing mutations in the CAAX box are characterized by a slow-growth phenotype on oleic acid medium. The plasmids used for the expression were pRSPEX19, pRSPEX19-C347S, pRSPEX19-C347R, and pRSPEX19-C347*. (B) Relative amount of catalase in supernatant (gray bars) and pellet (white bars) fractions derived by 25,000 × g centrifugation of cell homogenates from pex19Δ mutant (lane 1) and nontransformed wild-type (lane 10) cells and from pex19Δ mutant cells expressing wild-type or mutant PEX19 from plasmids pRSPEX19-C347S (lane 2), pRSPEX19-C347R (lane 3), pRSPEX19-C347* (lane 4), pRS-PEX19 (lane 5), YEpPEX19-C347S (lane 6), YEpPEX19-C347R (lane 7), YEpPEX19-C347* (lane 8), and YEp-PEX19 (lane 9). (C) Immunofluorescence microscopy localization of PTS1-containing Pcs60p in pex19Δ cells expressing pRS316 (a), pRSPEX19-C347S (b), YEpPEX19-C347S (c), or YEpPEX19 (d). Bar, 10 μm. (D) Electron micrograph of oleic acid-induced pex19Δ cells expressing YEpPEX19-C347S. Complementation of the mutant strain is suggested by the presence of peroxisomes (p). m, mitochondria; n, nucleus; l, lipid droplets. Bar, 0.5 μm.

FIG. 11

Activity of peroxisomal and mitochondrial marker enzymes in fractions derived by continuous 20 to 54% (wt/wt) sucrose density gradient centrifugation of cell homogenates from pex19Δ mutant cells expressing either wild-type or nonfarnesylated Pex19p. Expression was from YEpPEX19 or YEpPEX19-C347S, respectively. Expression of wild-type Pex19p resulted in the comigration of the majority of the peroxisomal enzymes and peroxisomal membrane proteins at a density of 1.23 g/cm³, typical for wild-type peroxisomes. Upon expression of mutated Pex19p, only a minor portion of the peroxisomal markers was found at 1.23 g/cm³, suggesting that nonfarnesylated Pex19p cannot fully complement the pex19Δ mutation. The majority of the peroxisomal membrane protein was found in fractions of 1.18 g/cm³, cosegregating with mitochondrial fumarase activity. Peroxisomal and mitochondrial proteins were monitored by enzyme activity measurements. Equal volumes of each fraction were analyzed for the presence of peroxisomal membrane proteins Pex3p (39) and Pex11p (25, 50) by immunoblotting.

FIG. 12

Physical interaction of Pex19p with Pex3p. (A) PCY2 double transformants expressing the indicated combinations of fusion proteins were tested for β-galactosidase expression. The color intensities of these strains after the β-galactosidase filter assay are shown. (B) Coimmunoprecipitation of myc-Pex19p with Pex3p. Immunoprecipitations were performed with antibodies against the c-myc epitope and solubilized membranes prepared from pex19Δ cells and from pex19Δ cells expressing myc-Pex19p. The upper band that appears in both lanes corresponds to the heavy chain of IgG. Equal amounts of immunoprecipitates were separated by SDS-PAGE and subjected to immunoblot analysis with monoclonal antibodies against the myc epitope and polyclonal antibodies against Pex3p.