Tuberculosis (TB) is an infectious disease of major global importance. An estimated ten million people were diagnosed with TB disease in 2017 and 1.6 million died [1]. Current efforts to curb the TB epidemic are insufficient to achieve the 2035 targets set by the World Health Organization, of a 95% reduction in TB deaths and a 90% reduction in the TB incidence rate, compared with levels in 2015 [1]. There is widespread consensus, supported by epidemiological modeling, that a highly efficacious TB vaccine is necessary to achieve these TB control objectives [2, 3].

Thirteen novel TB vaccine candidates were being assessed at various stages in phase 1–3 clinical trials in 2017. However, whilst criteria have been proposed to guide advancement of vaccine candidates to efficacy testing, these are neither unanimously agreed upon nor used [4]. There is also limited stakeholder effort to harmonize or standardize clinical trial design and, as a result, different vaccine candidates are typically assessed in unrelated trials with unique design features that preclude direct comparison of results. This is also the case for assessment of immunological outcomes of TB vaccine trials. Most clinical trials measure vaccine-induced CD4 and/or CD8 cells expressing the Th1 cytokines IFNγ, TNF and IL-2, on the basis that these cells are necessary, although not sufficient, for protective immunity against Mycobacterium tuberculosis (M.tb) in animal models and humans (reviewed in [5, 6]). However, the types of assays, methodologies and protocols employed by different investigators to measure Th1-cytokine expressing T cells vary considerably [7]. Direct comparison of the magnitude, character and durability of antigen-specific immune responses induced by different TB vaccine candidates is therefore highly problematic. We propose that this is an important gap in knowledge required to guide advancement of vaccine candidates through the clinical development pipeline.

To facilitate rational, data-driven decisions about vaccine candidate advancement, we compared Bacillus Calmette-Guérin (BCG) [8] and six novel TB vaccine candidates, including MVA85A [9, 10], AERAS-402 [11], H1:IC31 [12], M72/AS01_E [13, 14], ID93+GLA-SE [15] and H56:IC31 [16], by their induced antigen-specific CD4 and CD8 T cell responses from data generated in human clinical trials previously completed at the South African TB Vaccine Initiative. The immune responses were measured using the same immunological assay [17, 18], enabling direct comparisons between vaccines. We aimed to define group(s) of vaccines that induced distinct immune responses. Within a group, the vaccines would induce similar immune responses, thus motivating further testing for only one vaccine per group by applying an objective, data-based criterion for vaccine prioritisation.

We identified appropriate statistical approaches and performed an analysis of antigen-specific T cell responses to each antigen in the different vaccine candidates. Comparing the magnitude and cytokine co-expression profiles of vaccine-induced memory CD4 and CD8 T cell responses that persisted to the final study visit in each trial, we revealed considerable homogeneity in vaccine-induced Th1 memory response profiles, particularly in individuals with underlying M.tb infection. Our study provides a framework for interpreting immunological characteristics that may be useful for prioritization of vaccine candidates for advancement through the development pipeline.

Immune responses from a total of 225 (117 M.tb-uninfected and 108 M.tb-infected, as determined either by tuberculin skin test or IFN-gamma release assay in the original trial) HIV-uninfected individuals vaccinated with one of six novel TB vaccine candidates, and 27 re-vaccinated with BCG, were analyzed (Tables 1 and 2). Study participants were either HIV-negative adolescents or adults from the Worcester region of the Western Cape Province of South Africa. Immune responses were measured by a whole blood intra-cellular cytokine staining assay (WB-ICS) with multiparameter flow cytometry [17, 18]. For each vaccine, frequencies of CD4 and CD8 T cells that produced IFNγ, TNF, IL-2 and/or IL-17 in response to antigens in that vaccine were measured. Immune response data from all trials for which such WB-ICS results from adolescents or adults were available were included in our analyses.

TB vaccine development has substantially progressed in recent years, with great advances in our understanding of vaccine platforms, antigen and adjuvant selection and correlates of risk of TB disease [4]. Animal models have been standardized to enable head-to-head comparison and selection of candidate TB vaccines for advancement to phase I clinical trials [4]. Thirteen TB vaccine candidates were assessed in clinical trials in 2017 [4], but only one or two can be advanced to large-scale efficacy trials due to limited global resources.

To provide a data-driven basis for selection of vaccine candidates for further testing in efficacy trials, we performed a comparison of antigen-specific T cell responses induced by six novel TB vaccine candidates that have been assessed in phase 1b or 2a trials at SATVI. Three major points emerged from our study: (1) Antigen-specific T cell responses induced by the candidate TB vaccines were strongly CD4 T cell biased and predominantly expressed Th1-cytokines, (2) Th1 cytokine co-expression profiles of vaccine-induced memory CD4 T cells, a feature of T cell differentiation and functional quality, demonstrated considerable homogeneity between the vaccine candidates, (3) Analysis of T cell response magnitudes showed that amongst the novel vaccine candidates, M72/AS01_E induced the highest memory cytokine-expressing CD4 T cell responses.

Our finding that vaccine-induced responses were strongly CD4 T cell-biased with little IL-17 production, and that Th1-cytokine expression profiles were similar across vaccine candidates, highlights a lack of diversity in immunological responses typically analysed in TB vaccine immunogenicity assessments. This result is perhaps not surprising given that most current TB vaccine candidates were designed to specifically target induction of IFNγ-expressing CD4 T cells, predicated on the well-established evidence that Th1 cells are necessary, although not sufficient, for protective immunity against M.tb, based on animal models and human studies(reviewed in [5, 6, 24]). We acknowledge that analysis of Th1-cytokine and IL-17 expressing CD4 and CD8 T cell responses may miss important T cell functions. Further, assays that can detect alternative T cell functions or outcomes to the ones we measured, such as proliferative potential or cytotoxic function, may have revealed diversity in immunological responses that were missed by our analyses.

We did not include analysis of immunogenicity data from trials performed in age groups other than adults or adolescents, or from trials performed in current or prior TB patients. We also excluded data for other vaccine candidates assessed in clinical trials at SATVI, such as MTBVAC, VPM1002 and H4:IC31, because data from vaccinated adults or adolescents at the end of study time point were not available. The whole live mycobacterial vaccines, MTBVAC and VPM1002, are known to induce responses by a broader range of immune cells [25, 26] than those we observed and might add to the diversity of the immune responses induced by vaccine candidates. Further, we did not include analyses of antigen-specific antibody responses, which may also be important in immunity against M.tb [27, 28], largely because antibody responses were not measured in each trial assessed here. It should be noted that high-level antigen-specific IgG responses were induced by a number of these TB vaccine candidates [14, 15] and we suggest that such responses should be measured in vaccine trials and included in future head-to-head comparisons.

Our study revealed negligible evidence of an effect of underlying M.tb infection on the vaccine-induced memory response magnitude of CD4 or CD8 T cells for any vaccine, but strong evidence for an effect of M.tb infection on the vaccine-induced memory response cytokine co-expression profile. For CD4 T cells, M.tb infection was associated with a reduction in TNF+IL-2+ and possibly IL-2+ CD4 T cells, which corresponded to an increase in IFNγ+ CD4 T cells for M72/AS01_E and possibly IFNγ+TNF+IL-2+ for all novel vaccine candidates. The net effect was that the response profiles induced by MVA85A and the protein sub-unit vaccines in M.tb-infected individuals were similar. This drove the response closer to that induced by M.tb infection, as detected by megapool stimulation. These data suggest that underlying M.tb infection can play a strong role in the character of the vaccine-induced T cell response, as noted in published vaccine trials [12, 14, 21].

Since the vaccine-induced memory Th1 cytokine co-expression profiles were similar, only the response magnitude separated vaccine candidates. M72/AS01_E induced the largest antigen-specific CD4 T cell responses, with similar responses between other novel vaccine candidates. Therefore, based on CD4 T cell response magnitude, our study suggests that M72/AS01_E demonstrated the best vaccine take, providing support for further clinical testing. Non-immunological differences between vaccines, such as manufacturing cost, potential production capacity and ease of logistical arrangements, are also critical factors in decisions of candidate selection for further testing.

It is important to note that measures of antigen-specific T cell responses, such as the ones we analyzed, do not represent known correlates of protection against M.tb. Since immune correlates of protection against M.tb remain undefined [4, 6, 27], the induced CD4 and CD8 T cell response producing Th1 cytokines can only be considered a measure of vaccine take. The recent demonstration of protection afforded by BCG re-vaccination against sustained M.tb-infection [29] presents an opportunity for elucidating immune correlates of vaccine-induced protection against M.tb.

We focused our comparative analyses only on the memory T cell response that persisted to the final study visit of each clinical trial for practical reasons. This is partly because some vaccines were administered once and others twice or three times. We acknowledge that restricting our analyses to the memory response at the final study visit ignores the effector response early after vaccination and other phases of the post-vaccination response, which could have provided more heterogeneity and revealed important immune features for differentiating between the vaccine candidates. However, considering the very different study designs and the fact that the ultimate purpose of vaccination is to induce long-lasting immunological memory, we decided against analysis of earlier time points. Focusing on a single timepoint rather than a longitudinal response also strengthened the statistical analysis. It simplified interpretation and permitted standard multivariate analysis. It also increased statistical power, as it reduced the number of hypothesis tests to perform and assessed the post-vaccination timepoint with the lowest response variability. Moreover, the number of days between the final measurement and both the first vaccination and the last vaccination varied between vaccines, which confounded measurement timings with vaccine. Regardless, it is unlikely that this would have affected our interpretation that M72/AS01_E induced the highest T cell response magnitude among novel vaccine candidates, since follow-up time in the M72/AS01_E trial was well within the follow-up ranges for the other vaccines. Finally, the small sample sizes for some groups limited our ability to detect significant differences between vaccines.

Our study provides a framework for data-driven vaccine prioritisation. To facilitate these analyses in future, we highlight important factors that relate to standardisation, statistical power and immune response measurements.

The first factor to strive for is achieving as much standardization as possible across trials of vaccine candidates, particularly in terms of the immunological assay and time points at which immune responses are measured, but also of participant inclusion and exclusion criteria and the method for defining Mtb infection. Inclusion of a common stimulation antigen preparation, such as a “megapool” of M.tb peptides (as in [19]), would facilitate cross-trial comparisons, although responses to antigens that are not in individual vaccines could mask vaccine-specific response differences.

The second factor is sample size. Comparing vaccines entails numerous pair-wise comparisons and ensuring sufficiently large sample sizes would facilitate detecting and characterising differences. Whilst a formal calculation of the precise sample size required depends on both inherent response variability and planned hypothesis tests, our experience from this work suggests that groups with less than twenty participants handicap statistical analyses. We also recommend the following to achieve robustness in statistical comparisons. When comparing multiple outcomes or groups the false discovery rate should be stringently controlled and statistical approaches that are robust to outliers, yet still efficient (e.g. trimmed mean) should be used. In addition, both the significance of differences and confidence intervals should be reported. Another means of increasing power is to reduce the number of hypothesis tests to perform. This can be done by pre-defining and ranking hypotheses in order of importance [30]. One means of informing hypothesis prioritisation would be to use data from any vaccine dose groups in the same trials not used for inter-vaccine comparisons to identify likely differences between vaccines. Another would be to focus such analyses on any correlates of protection that may be identified in future [29, 31].

The third factor is measuring relevant immune responses and transforming them appropriately. We suggest widening the scope of immune responses measured to more broadly characterise the vaccine-induced responses (i.e. covering the widest specific immune response “real estate”). For analysis of antigen-specific T cells producing one of various cytokine combinations, we think that our response size and response profile measures accurately and intuitively capture two distinct and important features of the immune response. Transformations of other immune responses should also be meaningful and interpretable.

In conclusion, our study suggests that the T cell response feature which most differentiated between the TB vaccine candidates was response magnitude, whilst functional profiles suggested a lack of response diversity. Since M72/AS01_E induced the highest memory CD4 T cell response it demonstrated the best vaccine take. In the absence of immunological correlates of protection, the likelihood of finding a protective vaccine by empirical testing of candidates may be increased by the addition of candidates that induce distinct immune characteristics.