The protein-phosphatome of the human malaria parasite Plasmodium falciparum

Abstract

Background: Malaria, caused by the parasitic protist Plasmodium falciparum, represents a major public health problem in the developing world. The P. falciparum genome has been sequenced, which provides new opportunities for the identification of novel drug targets. We report an exhaustive analysis of the P. falciparum genomic database (PlasmoDB) aimed at identifying and classifying all protein phosphatases (PP) in this organism.

Results: Using a variety of bioinformatics tools, we identified 27 malarial putative PP sequences within the four major established PP families, plus 7 sequences that we predict to dephosphorylate "non-protein" substrates. We constructed phylogenetic trees to position these sequences relative to PPs from other organisms representing all major eukaryotic phyla except Cercozoans (for which no full genome sequence is available). Predominant observations were: (i) P. falciparum possessed the smallest phosphatome of any of the organisms investigated in this study; (ii) no malarial PP clustered with the tyrosine-specific subfamily of the PTP group (iii) a cluster of 7 closely related members of the PPM/PP2C family is present, and (iv) some P. falciparum protein phosphatases are present in clades lacking any human homologue.

Conclusion: The considerable phylogenetic distance between Apicomplexa and other Eukaryotes is reflected by profound divergences between the phosphatome of malaria parasites and those of representative organisms from all major eukaryotic phyla, which might be exploited in the context of efforts for the discovery of novel targets for antimalarial chemotherapy.

Figure 1

Phylogenetic tree demonstrating the putative relationships between the major types of eukaryotic organisms. Where possible one genome has been selected from each major branch of the tree for comparative studies of the protein phosphatase sequences present. See text for details. Adapted from [40], with permission from the Publisher (AAAS).

Figure 2

Summary of the genome-wide surveys of the model organisms selected for the comparative studies of protein phosphatase catalytic domains. Results represent HMMER hmmsearch analyses of the conceptual translation set of each genome using the profiles for the four main catalytic domain types. Note the major expansion of PPP (especially PPM type) domains in green plants (A. thaliana) and the expansion of PTP type domains in metazoans (H. sapiens).

Figure 3

A. Neighbour-Net tree of all Metallophosphatase type (PPP) domains detected in the model genomes. The coloured wedges indicate the distinct clusters defined by the Markov clustering algorithm, which are labelled according to the consensus of annotations available in Swiss-Prot/Trembl/. P. falciparum sequences appearing in the tree are labelled by capital letters: A-I Plasmodium falciparum PPP type phosphatase domains (see Fig. 3B for identification) J, PF14_0036; K, PF13_0222; L, PF4390w; M, PF14_0064; N, PF14_0614; O, PF14_0660; P, PFL0300c. Sequences J-M are not expected to encode protein phosphatases. The organisms from which the sequences originate are colour-coded as follows: Red and boxed, P. falciparum (Alveolates); green, A. thaliana (Plants); Blue, H. Sapiens (Opisthokonts); Turquoise, G. lamblia (Excavates); purple, T, brucei (Discicristates); black, T. pseudonana (Heterokonts); and magenta, D. discoideum (Amoebozoa). B. Enlargement of the region of the Metallophosphatase type domain Neighbour-Net tree of PPP phosphatase domains. Most domain types are labelled according to the human homologue, where present. P. falciparum sequences appearing in the tree are labelled by capital letters: A, PF14_0630; B, PF14_0142; C, PF14_0224; D, PFC0595c; E, PF10_0177; F, PF08_0129; G, PFI1245c; H, PFI1360c; I, MAL13P1.274. A high-resolution version of this Figure is available as a PNG file (see Additional file 7). We recommend viewing this file using a graphics programme enabling magnification, such as Microsoft Office Picture Manager.}

Figure 4

Neighbour-Net tree of all PPM (PP2c) type domains detected in the model genomes. The Markov clustering algorithm defined a single group encompassing the large majority of the sequences; therefore, in contrast to the other figures, no wedges are indicated. P. falciparum sequences appearing in the tree are labelled by capital letters: A, MAL13P1.44; B, PFL2365w; C, PF14_0523; D, PFD0505c; E, PFE1010w; F, PF11_0362; G, PF11_0396; H, MAL8P1.109; I, MAL8P1.108; J, PF10_0093. A high-resolution version of this Figure is available as a PNG file (see Additional file 8). We recommend viewing this file using a graphics programme enabling magnification, such as Microsoft Office Picture Manager.

Figure 5

Neighbour-Net tree of all PTP type domains detected in the model genomes. The coloured wedges indicate the distinct clusters defined by the Markov clustering algorithm, which are labelled according to the consensus of annotations available in Swiss-Prot/Trembl. P. falciparum sequences appearing in the tree are labelled by capital letters: A, PF14_0525 & PF14_0524; B, PFC0380w; C, PF11_0139; D, PF11_0281. Red dots indicate characterised mammalian MAPK phosphatases. A high-resolution version of this Figure is available as a PNG file (see Additional file 9). We recommend viewing this file using a graphics programme enabling magnification, such as Microsoft Office Picture Manager.

Figure 6

Neighbour-Net tree of all NIF type domains detected in the model genomes. The coloured wedges indicate the distinct clusters defined by the Markov clustering algorithm. P. falciparum sequences appearing in the tree are labelled by capital letters: A, PFE0795c; B, PF07_0110; C, PF10_0124; D, MAL13P1.275. A high-resolution version of this Figure is available as a PNG file (see Additional file 10). We recommend viewing this file using a graphics programme enabling magnification, such as Microsoft Office Picture Manager.

Figure 7

Neighbour-Net tree of all Rhodanese type domains detected in the model genomes. The sequences annotated as "MAPK phosphatase-associated domains" refer to the same polypeptides as the MAPK phosphatases in the PTP tree (Fig. 5), because these proteins contain both a DSP domain and a (non-catalytic) Rhodanese-like domain. The coloured wedges indicate the distinct clusters defined by the Markov clustering algorithm. P. falciparum sequences appearing in the tree are shown within red squares. Sequences annotated as cdc25s, containing the CX₅R catalytic motif, are indicated with an asterisk. See Additional file 6 for an alignment of these sequences with all P. falciparum sequences containing a Rhodanese domain. A high-resolution version of this Figure is available as a PNG file (see Additional file 11). We recommend viewing this file using a graphics programme enabling magnification, such as Microsoft Office Picture Manager.