Glycosylation of Trypanosoma cruzi TcI antigen reveals recognition by chagasic sera

Abstract

Chagas disease is considered the most important parasitic disease in Latin America. The protozoan agent, Trypanosoma cruzi, comprises six genetic lineages, TcI-TcVI. Genotyping to link lineage(s) to severity of cardiomyopathy and gastrointestinal pathology is impeded by the sequestration and replication of T. cruzi in host tissues. We describe serology specific for TcI, the predominant lineage north of the Amazon, based on expression of recombinant trypomastigote small surface antigen (gTSSA-I) in the eukaryote Leishmania tarentolae, to allow realistic glycosylation and structure of the antigen. Sera from TcI-endemic regions recognised gTSSA-I (74/146; 50.7%), with no cross reaction with common components of gTSSA-II/V/VI recombinant antigen. Antigenicity was abolished by chemical (periodate) oxidation of gTSSA-I glycosylation but retained after heat-denaturation of conformation. Conversely, non-specific recognition of gTSSA-I by non-endemic malaria sera was abolished by heat-denaturation. TcI-specific serology facilitates investigation between lineage and diverse clinical presentations. Glycosylation cannot be ignored in the search for immunogenic antigens.

Figure 1

T. cruzi TSSA recombinant proteins produced in L. tarentolae expression system. (a) gTSSA-I protein sequence (based on GenBank GU059925) and (b) gTSSA-II/V/VI protein sequence (based on GenBank GU075675): histidine tag (blue), SUMO sequence (green), linker sequences (black) and TSSA sequences (red). Dots: Residues predicted to be O-glycosylated. Starred: Ser residue present in native TSSA-II/V/VI but absent in native TSSA-I. Underlined: lineage-specific polymorphic residues. (c) Predicted likelihood scores for O-glycosylation of TSSA-I sequence range between 0 (least)—1 (highest); scores below 0.5 not listed. (d) Coomassie blue stained gel of purified gTSSA-I.

Figure 2

Antigenicity of gTSSA-I is due to TSSA-I sequence. (a) Absorbance values with Colombian (Medellín) sera recognising gTSSA-I (blue bars) and gTSSA-II/V/VI (orange bars). (b) Overall absorbance values for Colombian (Medellín) sera against gTSSA-I (blue) and gTSSA-II/V/VI (orange); gTSSA-I is recognised, whereas gTSSA-II/V/VI is not (P < 0.0001). (c) ELISA plate illustrating the recognition of gTSSA-I but not of gTSSA-II/V/VI; all samples were seropositive with lysate, and coating buffer controls were negative. Sample numbers correspond with (a). Positive control: serum from a Bolivian patient previously shown to be reactive with synthetic peptide TSSApep-II/V/VI and also seropositive with gTSSA-I, indicating co-infection (see text).

Figure 3

gTSSA-I antigenicity is dependent on glycosylation, whereas recognition by non-endemic malaria sera is dependent on structure. (a) Absorbance values of Colombian Medellín sera recognising unmodified gTSSA-I (blue bars), heat denatured gTSSA-I (orange bars) and oxidised gTSSA-I (green bars); oxidation decreases absorbance values substantially more than heat denaturing for all samples except 2. (b) Absorbance values of Gambian malaria (G) sera recognising unmodified gTSSA-I (blue bars), heat denatured gTSSA-I (orange bars) and oxidised gTSSA-I (green bars); heat denaturing decreases absorbance values substantially, whereas oxidation does not. For each of the data sets represented in (a) and (b) individual samples are presented on the main graph and composite absorbance values in the inset box-and-whisker plots. (c) ELISA plate illustrating the effects of modifications: coating with of unmodified gTSSA-I (fourth row); heat denatured gTSSA-I (second row), with slight signal reduction for Colombian sera but ablation for Gambian malaria sera; oxidised gTSSA-I (third row), with considerable reduction for Colombian sera, yet no reduction with Gambian malaria sera; coating buffer only (no antigen) control (first row). Sample numbers correspond with (a) and (b).