Machine learning-based single cell and integrative analysis reveals that baseline mDC predisposition predicts protective Hepatitis B vaccine response

Vaccination to prevent infectious disease is one of the most successful public health interventions ever developed. And yet, variability in individual vaccine effectiveness suggests a better mechanistic understanding of vaccine-induced immune responses could improve vaccine design and efficacy. We have previously shown that protective antibody levels could be elicited in a subset of recipients with only a single dose of the hepatitis B virus (HBV) vaccine. Why some, but not all, recipients responded in this way was not clear. Using single cell RNA sequencing of sorted innate immune cell subsets, we identified two distinct myeloid dendritic cell subsets (NDRG1-expressing mDC2 and CDKN1C-expressing mDC4), the ratio of which at baseline (pre-vaccination) predicted immune response to a single dose of HBV vaccine. Our results suggest that the participants in our vaccine study were in one of two different dendritic cell dispositional states at baseline - an NDRG2-mDC2 state in which the vaccine elicited an antibody response after a single immunization or a CDKN1C-mDC4 state in which the vaccine required two or three doses for induction of antibody responses. Genes expressed in these mDC subsets were used as an approach for feature selection prior to the construction of a predictive model using supervised canonical correlation machine learning. The resulting model showed an improved ability to predict serum antibody titers in response to vaccination. Taken together, these results suggest that the propensity of circulating dendritic cells toward either activation or suppression, their "dispositional endotype", could dictate response to vaccination. The fact that these mDCs could be modulated via TLR stimulation could guide progress towards design of effective single dose vaccination strategies.