In Silico Model Estimates the Clinical Trial Outcome of Cancer Vaccines

Over 30 years after the first cancer vaccine clinical trial (CT), scientists still search the missing link between immunogenicity and clinical responses. A predictor able to estimate the outcome of cancer vaccine CTs would greatly benefit vaccine development. Published results of 94 CTs with 64 therapeutic vaccines were collected. We found that preselection of CT subjects based on a single matching HLA allele does not increase immune response rates (IRR) compared with non-preselected CTs (median 60% vs. 57%, p = 0.4490). A representative in silico model population (MP) comprising HLA-genotyped subjects was used to retrospectively calculate in silico IRRs of CTs based on the percentage of MP-subjects having epitope(s) predicted to bind ≥ 1–4 autologous HLA allele(s). We found that in vitro measured IRRs correlated with the frequency of predicted multiple autologous allele-binding epitopes (AUC 0.63–0.79). Subgroup analysis of multi-antigen targeting vaccine CTs revealed correlation between clinical response rates (CRRs) and predicted multi-epitope IRRs when HLA threshold was ≥ 3 (r = 0.7463, p = 0.0004) but not for single HLA allele-binding epitopes (r = 0.2865, p = 0.2491). Our results suggest that CRR depends on the induction of broad T-cell responses and both IRR and CRR can be predicted when epitopes binding to multiple autologous HLAs are considered.