Combining immunoprofiling with machine learning to assess the effects of adjuvant formulation on human vaccine-induced immunity

Abstract

Adjuvants produce complex, but often subtle, effects on vaccine-induced immune responses that, nonetheless, play a critical role in vaccine efficacy. In-depth profiling of vaccine-induced cytokine, cellular, and antibody responses ("immunoprofiling") combined with machine-learning holds the promise of identifying adjuvant-specific immune response characteristics that can guide rational adjuvant selection. Here, we profiled human immune responses induced by vaccines adjuvanted with two similar, clinically relevant adjuvants, AS01B and AS02A, and identified key distinguishing characteristics, or immune signatures, they imprint on vaccine-induced immunity. Samples for this side-by-side comparison were from malaria-naïve individuals who had received a recombinant malaria subunit vaccine (AMA-1) that targets the pre-erythrocytic stage of the parasite. Both adjuvant formulations contain the same immunostimulatory components, QS21 and MPL, thus this study reveals the subtle impact that adjuvant formulation has on immunogenicity. Adjuvant-mediated immune signatures were established through a two-step approach: First, we generated a broad immunoprofile (serological, functional and cellular characterization of vaccine-induced responses). Second, we integrated the immunoprofiling data and identify what combination of immune features was most clearly able to distinguish vaccine-induced responses by adjuvant using machine learning. The computational analysis revealed statistically significant differences in cellular and antibody responses between cohorts and identified a combination of immune features that was able to distinguish subjects by adjuvant with 71% accuracy. Moreover, the indepth characterization demonstrated an unexpected induction of CD8 + T cells by the recombinant subunit vaccine, which is rare and highly relevant for future vaccine design.

Design of a Multiepitope-Based Peptide Vaccine against the E Protein of Human COVID-19: An Immunoinformatics Approach

“…Designing a novel vaccine is very crucial to defend against the rapid endless global burden of diseases [56][57][58][59]. In the last few decades, biotechnology has advanced rapidly, alongside with the understanding of immunology which assisted the rise of new approaches towards rational vaccine design [60]. Peptide-based vaccines are designed to elicit immunity particular pathogens by selectively stimulating antigenspecific B-and T-cells [25].…”

The COVID-19 Vaccine Race: Challenges and Opportunities in Vaccine Formulation

“…MD simulation has been applied in epitopecarrier fusion construction in HIV vaccine and malaria vaccine (19,20). The machine learning tool was used to predict the antigen-specific immune signatures in vaccines based on immune profiling data (21,22). Ong et al (2020) predicted possible vaccine targets of COVID-19 using a machine learning tool, including the non-structural protein (nsp3), a novel target that has not been tested for vaccines (23).…”

“…MD simulation has been applied in epitope-carrier fusion construction in HIV vaccine and malaria vaccine ( 19 , 20 ). The machine learning tool was used to predict the antigen-specific immune signatures in vaccines based on immune profiling data ( 21 , 22 ). Ong et al .…”

Design of multi epitope-based peptide vaccine against E protein of human COVID-19: An immunoinformatics approach

“…Designing of a novel vaccine is very crucial to defending the rapid endless of global burden of disease [56][57][58][59]. In the last few decades, biotechnology has advanced rapidly; alongside with the understanding of immunology which assisted the rise of new approaches towards rational vaccines design [60]. Peptide-based vaccines are designed to elicit immunity particular pathogens by selectively stimulating antigen specific for B and T cells [61].Applying the advanced bioinformatics tools and databases, various peptide-based vaccines could be designed where the peptides act as ligands [62][63][64].…”