Potential association factors for developing effective peptide-based cancer vaccines

Abstract

Peptide-based cancer vaccines have been shown to boost immune systems to kill tumor cells in cancer patients. However, designing an effective T cell epitope peptide-based cancer vaccine still remains a challenge and is a major hurdle for the application of cancer vaccines. In this study, we constructed for the first time a library of peptide-based cancer vaccines and their clinical attributes, named CancerVaccine (https://peptidecancervaccine.weebly.com/). To investigate the association factors that influence the effectiveness of cancer vaccines, these peptide-based cancer vaccines were classified into high (HCR) and low (LCR) clinical responses based on their clinical efficacy. Our study highlights that modified peptides derived from artificially modified proteins are suitable as cancer vaccines, especially for melanoma. It may be possible to advance cancer vaccines by screening for HLA class II affinity peptides may be an effective therapeutic strategy. In addition, the treatment regimen has the potential to influence the clinical response of a cancer vaccine, and Montanide ISA-51 might be an effective adjuvant. Finally, we constructed a high sensitivity and specificity machine learning model to assist in designing peptide-based cancer vaccines capable of providing high clinical responses. Together, our findings illustrate that a high clinical response following peptide-based cancer vaccination is correlated with the right type of peptide, the appropriate adjuvant, and a matched HLA allele, as well as an appropriate treatment regimen. This study would allow for enhanced development of cancer vaccines.

Keywords: cancer vaccine; clinical response; machine learning; peptide; potential factors.

Figure 1

Data filtering summary landscape of the library, CancerVaccine (https://peptidecancervaccine.weebly.com/). (A) Data filtering process. (B) The landscape of cancer types. (C) The landscape of peptide types. (D) The landscape of adjuvants. (E) The landscape of HLA alleles. (F) The landscape of treatment regimen (injection interval). (G) The landscape of treatment regimen (injection times).

Figure 2

Cancer vaccine criteria and feature comparison. The specific criteria of a clinical treatment response. A total of 78 peptides resulting which involved 673 patients were excluded. 273 high clinical response results (3,233 patients involved) and 354 low clinical response results (2,807 patients involved) were finally included in this study.

Figure 3

Peptide types in high and low clinical response results. (A) Comparison of peptide types between high clinical response (HCR) results and low clinical response (LCR) results. The distribution of peptide types in HCR and LCR results. (B) The distribution of peptide types in HCR and LCR results. (C) The distribution of peptide types in HCR and LCR results in melanoma and colorectal cancer, respectively. P-values were calculated using two-sided Wilcoxon rank-sum tests. NS., not significant.

Figure 4

HLA alleles in high and low clinical response results. (A) Comparison of HLA alleles between HCR and LCR results. (B) The distribution of HLA alleles in HCR and LCR results. (C) The distribution of HLA alleles in HCR and LCR results in melanoma and lung cancer, respectively. P-values were calculated using two-sided Wilcoxon rank-sum tests. NS, not significant.

Figure 5

Adjuvants in high and low clinical response results. (A) Comparison of adjuvants between HCR and LCR results. (B) The distribution of adjuvants in HCR and LCR results. (C) The distribution of adjuvants in HCR and LCR results in four main cancer types (breast cancer, melanoma, lung cancer, and colorectal cancer). P-values were calculated using two-sided Wilcoxon rank-sum tests.

Figure 6

Treatment regimens play an important role in cancer immunotherapy. (A) The distribution of treatment regimens (injection interval) in HCR and LCR results. (B) The distribution of treatment regimens (injection times) in HCR and LCR results. (C) Comparison of treatment regimens (injection interval and injection times) between HCR and LCR results. P-values were calculated using two-sided Wilcoxon rank-sum tests.

Figure 7

Features selection and model. (A) The variable importance for the selected features, such as injection interval, injection times, adjuvant types, and HLA alleles. (B) Receiver Operating Characteristic (ROC) curve for the total test set (black) and independent breast cancer (green), melanoma (light blue), lung cancer (blue), and colorectal cancer datasets (red).