Development of a Multiplex HIV/TB Diagnostic Assay Based on the Microarray Technology

Abstract

Currently there are diagnostic tests available for human immunodeficiency virus (HIV) and tuberculosis (TB); however, they are still diagnosed separately, which can delay treatment in cases of co-infection. Here we report on a multiplex microarray technology for the detection of HIV and TB antibodies using p24 as well as TB CFP10, ESAT6 and pstS1 antigens on epoxy-silane slides. To test this technology for antigen-antibody interactions, immobilized antigens were exposed to human sera spiked with physiological concentrations of primary antibodies, followed by secondary antibodies conjugated to a fluorescent reporter. HIV and TB antibodies were captured with no cross-reactivity observed. The sensitivity of the slides was compared to that of high-binding plates. We found that the slides were more sensitive, with the detection limit being 0.000954 µg/mL compared to 4.637 µg/mL for the plates. Furthermore, stability studies revealed that the immobilized antigens could be stored dry for at least 90 days and remained stable across all pH and temperatures assessed, with pH 7.4 and 25 °C being optimal. The data collectively suggested that the HIV/TB multiplex detection technology we developed has the potential for use to diagnose HIV and TB co-infection, and thus can be developed further for the purpose.

Keywords: HIV-1 p24; M.tb CFP10; M.tb ESAT6; M.tb pstS1; antibody; antigen; diagnosis; multiplex microarray.

Figure A1

Evaluation of sensitivity of epoxy-coated glass slides assay in PBS. Primary antibodies were serially diluted in PBS while the antigen and secondary antibody concentrations were kept constant. Fluorescence intensity values for pstS1 (A), CFP10 (B), ESAT6 (C) and p24 (D) are presented as line graphs, and the limit of detection is indicated by the red arrow. Data represent mean ± standard deviation (n = 4). (E) A representative image of the fluorescence emitted on the microarray slide.

Figure A2

Determination of antigen-antibody reaction sensitivity for the microtiter plates. The concentrations of immobilized antigen and secondary antibodies were kept constant while that of the primary antibodies varied. (A) shows the fluorescence intensity obtained when HIV and TB antibodies were diluted in human serum, while (B) shows the intensity obtained when these antibodies were diluted in PBS. Error bars represent mean ± standard deviation (n = 4).

Figure A3

Alternative set-up of Microarray plates’ antigen–antibody reaction specificity in human serum. The immobilized antigens were incubated with the anti-p24 antibody (A), anti-ESAT6 antibody (B), anti-CFP10 antibody (C) or anti-pstS1 antibody (D) only, before the addition of the Alexa fluor 488-labelled secondary antibody. Data represent mean ± standard deviation (n = 3).

Scheme 1

A schematic diagram showing the representation of the research strategy used to develop the HIV and TB multiplex microarray technology. The strategy started with stability studies of the immobilized antigens followed by sensitivity and specificity studies.

Figure 1

The immobilization of HIV-1 p24, M.tb CFP10, ESAT6 and pstS1 antigens on an epoxy-coated glass slide by covalent interactions. (A) The antigens were immobilized at different concentrations, PBS-only spots were used as negative control, and imaging was performed using bright-field microscopy. The antigen spots after washing and imaging are indicated by the red and blue circles, while yellow circles show the negative control. (B) The immobilized antigens were reacted with anti-p24, anti-CFP10, anti-ESAT6 and anti-pstS1 primary antibodies, and subsequently secondary antibodies conjugated to Alexa fluor 488 were added and the slide imaged with a cytation3 multimode reader with Gen5 2.08 software. (C) Mean fluorescence intensity of the spots was measured with ImageJ and plotted. The concentration at which the antigens were assessed is also shown. Error bars are means ± standard deviation (n = 3).

Figure 2

Effect of different pH on the immobilization of antigens on epoxy-coated glass slides. The antigens were printed and washed with PBS at different pH values. The bar graphs show fluorescence intensity obtained with M.tb pstS1 (A), CFP10 (B), ESAT6 (C) and HIV-1 p24 (D). Data represent mean ± standard deviation and error bars are standard deviation (n = 3). Asterisks signify statistical significance (p < 0.05) between the fluorescence intensity of the highest reading and the lowest. (E) shows representative images obtained at different pH (pH 5.0, 6.0, 7.4, 8.0 and 9.0).

Figure 3

Evaluation of the optimal storage temperature for the immobilized antigens. The immobilized antigens were stored at different temperatures (−20 °C, 4 °C, 15 °C, 25 °C and 37 °C) for 24 h. The bar graphs of the fluorescence intensity obtained from M.tb pstS1 (A), CFP10 (B), ESAT6 (C) and HIV-1 p24 (D) are shown. Data represent mean ± standard deviation (n = 3) and asterisks indicate significant differences between the groups being compared. The slide images from which the bar graphs were plotted are shown in (E).

Figure 4

Evaluation of the stability in dry and wet storage conditions of the HIV and TB antigens immobilized on the epoxy-coated glass slide. The antigens were stored in PBS and dry at room temperature for 24 h. (A) The mean fluorescence of each spot was measured and plotted. Data represent mean ± standard deviation (n = 3) and asterisks show significant difference between groups. (B) and (C) representative PBS and dry storage images, respectively, used to plot the graph in (A).

Figure 5

Evaluation of the shelf-life of the immobilized HIV and TB antigens on the epoxy-coated glass slides. The antigens were stored dry at room temperature from day 1 to day 90, followed by addition of primary and secondary antibodies, with fluorescence readings after every 15 days. The bar graphs show fluorescence intensity when M.tb pstS1 (A), CFP10 (B), ESAT6 (C) or HIV-1 p24 (D) were stored dry for 90 days. Data represent mean ± standard deviation (n = 2) and asterisks signify significant difference between the groups compared.

Figure 6

Evaluation of the sensitivity of the assay using epoxy-coated glass slides. Primary antibodies were diluted in human serum to mimic in vivo conditions where there are many other proteins present. The antigen and secondary antibody concentrations were kept constant. Fluorescence intensity values for pstS1 (A), CFP10 (B), ESAT6 (C) and p24 (D) are presented as line graphs for the different antibody concentrations, and the limit of detection is indicated by the red arrow. Data represent mean ± standard deviation (n = 4). (E) A representative image of the slide used to plot the graphs.

Figure 7

Microarray plates’ antigen-antibody reaction specificity in human serum. Immobilized antigens were incubated with cocktails of primary antibodies, missing one antibody at a time. Antigens and secondary antibody concentrations were kept constant, while primary antibodies were serially diluted. (A) A line graph representing the fluorescence intensity obtained when immobilized antigens were incubated in a cocktail of primary antibodies missing the anti-pstS1 antibody; (B–D) graphs for anti-CFP10 or anti-ESAT6 or anti-p24, respectively. Data represent mean ± standard deviation (n = 4).