We enrolled 4,349 individuals in 220 randomly selected villages covering all the ecological regions of the country (Figure 1). Blood samples and sociodemographic data were available for all 4,349 participants. All participants were ≥16 years old, and 2,227 (51.2%) females and 2,122 (48.4%) males participated. The participants were located in the Forest (2,540 participants; 58.4% of the study population), Grassland (918; 21.1%), Savannah (448; 10.3%) and Lakeland (443; 10.2%) regions. The Forest area was subdivided into North-Eastern Forest (825; 19%), Interior Forest (1,314; 30.2%) and Mountain Forest (401; 9.2%).

The cut-off value for IgG positivity was determined by using a negative control population of volunteers sampled in Marseille, France in 2008. Nothing was known of ZEBOV circulation in the area studied. It was therefore impossible to define a control population with which to determine the OD distribution in seronegative subjects: inclusion of seropositive subjects among the controls would have undermined the validity of this distribution and the determination of a valid cutoff. We therefore chose a more rigorous approach, based on the choice of control subjects who were almost certain to be seronegative, yielding a valid “background” OD distribution; we also chose a curve largely covering this distribution and made a conservative choice of cutoff (error risk below 1/1000 for the first “positive” value). The cutoff was therefore based on a highly conservative approach. Finally, the OD distribution of the Gabonese population sample showed a strong excess of values in the range [0.05, 0.20] (relative to the reference distribution), but, thanks to the use of a conservative approach, these values were not considered as positive.

The distribution in the negative control population was centered near 0 (mean 0.006, median 0.009), with a standard deviation of 0.071 (data not shown). This distribution can be surrounded in the positive values by a negative exponential distribution (y = a*exp(-35*(x-0.006))). The exponential distribution gave a better fit than normal and gamma distributions. With this formal distribution, the observed distribution of all ODs was under the curve and the probability of an individual having an OD above 0.2 was less than 1‰. A sample was considered positive when its adjusted OD was above the cut-off (0.2 at 1∶1600 dilution) and when the OD in the viral antigen-coated well was twice as high as the OD in the uninfected antigen-coated well. All samples were tested in duplicate.

The seroprevalence of ZEBOV-specific IgG in the study population was 15.3% overall (Table 1), and varied significantly according to the ecological area (Figure 1, Table 1). The seroprevalence rate in the Forest region (19.4%) was significantly higher than that found in the other regions (p<0.001). Similarly, the seroprevalence rate in the Lakeland region (2.7%) was significantly lower than that found in the other areas (p<0.001). No significant difference was observed (p≥0.3) between Savannah (10.5%) and Grassland (12.4%) nor between the three types of Forest area (p≥0.4) (Table 1).

As shown in Table 2, no significant difference (p≥0.9) in seroprevalence was observed across villages where no ZEBOV outbreaks had been reported (19.5%), villages hit by the 1996–1997 outbreaks (20.2%), and villages hit by the 2001–02 outbreak (18.3%).

Seroprevalence rates varied widely across neighboring villages in each ecological region (Figure 2), ranging from 0% to 13.2% in Lakeland, 0% to 16.1% in Savannah, 3.8% to 30.8% in Grassland, and 5% to 33.3% in Forest.

Because the seroprevalence rates varied across the ecological areas, we examined the possible influence of sociodemographic characteristics (Table 3). No correlation was found between the seroprevalence rate and gender, age, hunting activity or contact with specific forest animals in a given ecological area (Table 3). The ‘hunting’ subgroup consisted of men who hunted frequently or occasionally, and thus excluded females. The ‘contact with specific forest animals’ subgroup included hunters, individuals who kept wild animals as pets, those who butchered dead animals, and those who cooked them.

The seroprevalence did not significantly vary with age (Table 3). However, only individuals older than 21 years were included in this analysis, owing to the small number of younger participants. In order to evaluate the influence of age among individuals younger than 21 years, we conducted a specific field study of children living in six villages located in the north-east forest area. We enrolled 395 children between 2 and 15 years old. The seroprevalence rate was significantly lower in the 1–10 year age group (8.7%; p = 0.005) than in all the other age groups (Table 4). The seroprevalence rates were 18.5% in the 11–20 year age group, 20.2% in the 21–30 year age group, 23.7% in the 31–40 year age group, 20.1% in the 41–50 year group and 18.5% in the ≥51 year group. The seroprevalence rates increased linearly with age below 15 years (Figure 3).

To confirm the specificity of anti-ZEBOV IgG, 150 randomly selected sera of the 667 positive samples were analyzed by western blotting in denaturing conditions with purified ZEBOV antigens, but technical problems meant that clear-cut results could not be obtained for 12 of them. All 138 sera tested by western blot (about 21% of all the positive samples) reacted with at least one ZEBOV protein. These selected sera represented a broad range of ODs and a broad geographic area of Gabon. Depending on the individual, IgG reactivity was directed against NP, VP40, VP35 VP24 and/or sGP (Figure 4). In total, 76% of the 138 sera reacted to VP40, 56% to NP, 36% to VP35 and 24% to sGP, while only one sample reacted to VP24. The IgG reactivity of serum from two survivors was also mainly directed to NP and VP40 (Figure 4).

To detect ZEBOV-specific T cell memory responses in these IgG+ individuals, intracellular levels of TNF-α and IFN-γ were determined in CD4+ and CD8+ T cell populations from seven randomly selected IgG+ individuals. Positive gating for lymphocytes based on forward and side scatter was followed by CD3+CD4+ and CD3+CD8+ gating, and specific populations were further defined by using antibodies specific for CD8 and CD4, respectively. Cytokine-positive cells were expressed as a percentage of the corresponding lymphocyte subset.

With samples from IgG+ individuals and from three survivors of ZEBOV infection, the percentage of circulating CD4+ T cells producing IFN-γ did not increase after PBMC stimulation (data not shown). In contrast, with samples from the seven IgG+ individuals, the percentage of circulating CD8+ T cells producing IFN-γ was higher on day 2 or 3 of PBMC stimulation by iZEBOV than after mock stimulation (Figure 5). This increase was noted on day 2 in individuals #IgG+1, IgG+3 and IgG+4, and on day 3 in individuals #IgG+2, IgG+5, IgG+6 and IgG+7. The strongest responses were observed in individuals #IgG+1, IgG+2 and IgG+3, with a 3-fold increase. Similar levels of IFN-γ-producing CD8+ T cells were observed in PBMC obtained from three survivors of ZEBOV infection, after iZEBOV stimulation. By contrast, no increase was observed with samples from the four IgG-negative controls (Figure 5).

PBMC from one individual were stimulated with iZEBOV on day 0 and again on day 6. The percentage of circulating IFN-γ-producing CD8+ T rose one day after each stimulation, i.e. on day 2 and day 7 (Figure 6). No increase in the percentage of TNF-α-producing CD8+ or CD4+ T cells was observed with PBMC from IgG+ individuals, although both CD8+ and CD4+ T cells from all three survivors produced low levels of TNF-α on day 3 after iZEBOV stimulation (data not shown).

The survey was conducted in Gabon, Central Africa. Nearly 80% of Gabon is covered by rain forest, which is subdivided into three different types, from North-East to South-West of the country [57]: the northern-eastern forest located near Cameroon and the Republic of Congo, the interior forest (characterized mainly by the presence of Okoume trees), and the mountain forest. Gabon also has a grassland region located between the coastline and mountain forest, as well as a dry savannah located mainly in the south-east, south-west and center, and a wide “Lakeland” and long coastline to the west (Figure 1). Gabon has a surface area of 267,667 km² and is divided into nine administrative regions comprising a total of 2,048 villages, most of which are located along roads (Figure 1). Few villages have more than 300 inhabitants.

The current serosurvey was conducted by a multidisciplinary team, including a doctor from the Gabonese Ministry of Health, a nurse, an epidemiologist, a virologist, a veterinarian and laboratory technicians. It focused on rural villages with fewer than 300 inhabitants located in the nine administrative regions of Gabon. It took place during nine one-month field missions, between 2005 and 2008. The survey covered 220 randomly selected villages (Figure 1), representing 10.7% of all villages in Gabon. The traditional chiefs of each village were first informed of the survey, followed, with the chief's approval, by all interested villagers. All inhabitants aged ≥16 years were eligible for the study. The study was described orally, and volunteers gave their signed informed consent to be enrolled in the study and for their blood samples to be used for future research studies. Each participant answered an anonymous oral questionnaire that included questions on demographics, lifestyle, work, social activities, diet and past medical illness. Villages were randomly selected in each of the nine provinces. We then randomly selected around 10% of the villages in each province, regardless of their size (50 to 300 persons). We systematically excluded children, elderly persons (more than ∼65 years), persons who were not permanent residents in the villages, and those who had been permanent residents for less than a year. Some inhabitants were not present at the time of our visit, because of their daily activities. In view of all these factors, the number of persons who refused was quite low (around 15% of the eligible population), representing 12 to 97 persons per village. This is unlikely to have had a significant impact on the results. A free medical examination and basic medicines were proposed to all participants and non participants. The samples were obtained after the interview. A total of 4,349 persons were enrolled.

In addition, we conducted a specific field mission to enroll laboratory-confirmed survivors of the three Gabonese ZEBOV outbreaks. After three months of investigations throughout the outbreak areas of Ogooué Ivindo region between June and August 2007, 20 survivors of the 2001 Mekambo, 1996 Booué and 1996 Mayibout outbreaks were identified and enrolled.

Finally, another specific field mission was carried out to enroll children aged 15 years or less. In total, 395 children aged between 2 and 15 years were randomly selected in six villages located in the northern-eastern forest region (Figure 1). In addition to a free medical examination and basic medicines, all children in each village had blood smears for malaria diagnosis and blood typing in the field. The results were given the following day and antimalarial drugs were provided if appropriate.

The two study protocols were reviewed and approved together by the Gabonese Ministry of Health (authorization n°00093/MSP/SG/SGAQM). Written consent was obtained from the Health Director of each region, the traditional chiefs of each village, and all participants. The parents' written consent was obtained for participating children.

A total of 4,349 blood samples were collected, usually in the villages' local healthcare centers. Our team was located in the main town of each administrative region, and field laboratory facilities were set up interior the General Hospital. Blood samples were collected in the villages on a daily basis, into two 7-ml Vacutainer tubes containing EDTA (VWR International, France). The tubes were then transported to the field lab, and plasma was obtained by centrifugation each evening. Plasma samples were kept at −20°C until the end of the field mission, then transported to Centre International de Recherches Médicales de Franceville (CIRMF), Gabon, and stored at −80°C until use.

Peripheral blood mononuclear cells (PBMC) were collected from 200 randomly selected individuals from among the 4,349 participants, and from the 20 survivors (see above). PBMC were separated from whole blood by density gradient centrifugation on lymphocyte separation medium (Eurobio) at 2,300 rpm for 20 min at room temperature. PBMC were then washed with phosphate buffered saline (PBS)-2% fetal calf serum (FCS), and were cryopreserved in FCS containing 10% DMSO in dry nitrogen until being transported to CIRMF. PBMC were finally stored at CIRMF in liquid nitrogen until immunological analysis.

An IgG ELISA method was used as previously described [27], with antigens kindly provided by the Special Pathogens Branch, Centers for Disease Control (Atlanta, USA). Briefly, Maxisorp plates (Nunc, Denmark) were coated with ZEBOV antigens diluted 1∶1000 in PBS, overnight at +4°C. Control plates were coated with uninfected Vero cell culture antigens in the same conditions. Sera were diluted 1∶1600 in 5% non fat milk in PBS-Tween 20 (0.1%) and incubated in the wells overnight at +4°C. Binding was visualized by using a peroxidase-labeled antibody to human IgG (Sigma, France) and the TMB detector system (Dynex Technologies, France). Optical density was measured at 450 nm with an ELISA plate reader. For each sample, we calculated the corrected optical density (OD) as the optical density of the antigen-coated well minus the OD of the corresponding control well.

A panel of 104 sera from individuals who had never visited Africa was obtained from Marseille, France, and used as negative controls for cut-off calculation.

ZEBOV antigens were kindly provided by Dr. V.E. Volchkov (Laboratoire P4 Jean Mérieux, Lyon, France). They were separated on 10% NuPAGE Bis-Tris acrylamide gel (Invitrogen, UK) and transferred to nitrocellulose membranes for 1 hour at 30 V. The membranes were blocked overnight at 4°C in PBS, 5% nonfat milk, and 0.1% Tween 20. The test sera were diluted 1∶100 in PBS, 2.5% milk, 0.1% Tween, and incubated with the membrane for 2 hours at room temperature. The membrane was then incubated with HRP-conjugated goat anti-human IgG (H+L) (P.A.R.I.S., France) diluted 1∶5000 in PBS 2.5% milk, 0.1% Tween 20. Bound antibodies were visualized with a chemiluminescent substrate, following the manufacturer's protocol (Pierce, France). Three washes in PBS 0.1% Tween 20 were performed after blocking and each incubation step.

The virus used in this study belonged to Zaire ebolavirus lineage B and was isolated from the plasma of a patient who died during the 2003 outbreak in RC [17]. The virus was isolated on confluent monolayers of Vero E6 cells in 25-cm² plastic tissue culture flasks. The cells were maintained in Dulbecco's modified Eagle's medium (DMEM, Life Technologies, France) supplemented with 2% heat-inactivated FCS, penicillin 10 U/ml and streptomycin 10 µg/ml (Invitrogen) at +37°C with 5% CO₂. The virus stock was prepared from the supernatant of infected Vero E6 cells after two passages (Vero E6+2).

The ZEBOV stock was titered using a modified conventional plaque assay [58]. Serial 10-fold dilutions of 250 µL of supernatant were incubated in DMEM-2% heat-inactivated FCS for 1 h at 37°C on Vero E6 cells grown to confluence in 6-well plastic tissue culture plates. Two milliliters of 1.6% carboxymethyl cellulose (BDH Laboratories, Poole, United Kingdom) in complete DMEM-2% FCS were then added to each well, and the plates were incubated at 37°C with 5% CO2 for 5 days. The cells were fixed with 4% formaldehyde (Sigma, Courtaboeuf, France) in PBS, washed, and permeabilized with 0.5% Triton X-100 (Sigma) in PBS. A mix of monoclonal antibodies specific for ZEBOV GP, NP, VP40 and VP35, kindly provided by Dr. S. Baize (Laboratoire P4 Jean Mérieux, Lyon, France), was then added overnight at +4°C. A peroxidase-conjugated goat anti-mouse antibody diluted 1∶1600 (Sigma) was then added for 1 h at 37°C, and foci of infected cells were revealed with diaminobenzidine (Sigma).

All infections were performed in BSL-4 conditions at CIRMF (glove box model). ZEBOV-infected supernatants were removed in BSL-4 conditions and heat-inactivated at 56°C for 40 min. Inactivated ZEBOV (iZEBOV) was stored at −80°C until use.

Cryopreserved PBMC were rapidly thawed in a 37°C water bath, washed twice and incubated overnight at 37°C in RPMI 1640 culture medium (Life technologies, UK) with 10% heat-inactivated FCS (full RPMI-10% FCS), 1% penicillin-streptomycin, 1% nonessential amino acids, and 1 M HEPES. PBMC were then washed in RPMI medium, adjusted to a density of 1×10⁶ cells/mL, and cultured in 24-well flat-bottom culture plates. Cells were immediately stimulated with inactivated ZEBV (iZEBOV) at a multiplicity of infection (MOI) of 1. Three samples containing enough PBMC were again stimulated with iZEBOV at MOI 1 on day 5 (Figure 4). Interleukin-2 (Becton Dickinson, France) was added to the cells on day 2 after stimulation with iZEBOV (PI) at a final concentration of 100 U/mL. Negative controls included cells stimulated with an equal volume of uninfected Vero E6 supernatant (mock), and positive controls included cells stimulated with phytohemagglutinin A (PHA, 3 µg/mL final).

PBMC from seven individuals were analyzed on days 2 and 3 after iZEBOV stimulation, and PBMC from three of these individuals were also analyzed on days 5 and 7. PBMC were incubated for 5 hours with 10 µg/mL Brefeldin A (Sigma) and 2 µM monensin (Sigma), then harvested and washed in culture medium. Approximately 0.5×10⁶ cells were labeled for 20 min at room temperature with monoclonal antibodies (Beckman-Coulter, Geneva, Switzerland): PC5-conjugated anti-human CD3, PC7-conjugated anti-CD4 and PC7-conjugated anti-CD8. Isotype controls consisted of cells labeled with FITC-conjugated mouse IgG1 and PE-conjugated IgG1 (Beckman-Coulter). Cells were then fixed and permeabilized with IntraPrep reagent (Beckman-Coulter) as recommended by the manufacturer. Permeabilized cells were labeled for 20 min at room temperature with FITC-conjugated anti-IFN-γ and PE-conjugated anti-TNF-α (Beckman-Coulter). Cells were then washed, resuspended in 2% FCS, and analyzed with an FC500 four-color flow cytometer (Beckman Coulter) and CXP software (Beckman Coulter).

All statistical analyses were performed using STATA software version 10 (STATA Corporation, College Station, Texas, USA). Overall and subgroup-specific ZEBOV seroprevalence rates were estimated and potential differences between subgroups were evaluated by using binomial survey-adjusted chi-square tests. Significance was assumed at p ≤0.01.