pVAC-Seq: A genome-guided in silico approach to identifying tumor neoantigens

Abstract

Cancer immunotherapy has gained significant momentum from recent clinical successes of checkpoint blockade inhibition. Massively parallel sequence analysis suggests a connection between mutational load and response to this class of therapy. Methods to identify which tumor-specific mutant peptides (neoantigens) can elicit anti-tumor T cell immunity are needed to improve predictions of checkpoint therapy response and to identify targets for vaccines and adoptive T cell therapies. Here, we present a flexible, streamlined computational workflow for identification of personalized Variant Antigens by Cancer Sequencing (pVAC-Seq) that integrates tumor mutation and expression data (DNA- and RNA-Seq). pVAC-Seq is available at https://github.com/griffithlab/pVAC-Seq .

Fig. 1

Overview of the pipeline pVAC-Seq: This figure illustrates the methodological framework behind the pVAC-Seq pipeline. Starting with preparation of inputs, it consists of three main steps - epitope prediction, integration of sequencing information, and filtered candidate selection

Fig. 2

Generation of peptide sequences and filtering predicted epitope candidates. a Amino acid FASTA sequence is built using 10 flanking amino acids on each side of the mutated amino acid. The preceding or succeeding 20 amino acids are taken if the mutation lies near the end or beginning of the transcript, respectively. b All predicted candidate peptides from epitope prediction software based on selected k-mer window size. c Only localized peptides (those containing the mutant amino acid) are considered to compare to WT counterpart. d The ‘best candidate’ (lowest MT binding score) per mutation is chosen across all specified k-mers and between all independent HLA allele types that were used as input

Fig. 3

Landscape of filtered neoantigen candidates. This figure illustrates the landscape of neoantigen vaccine candidates in patient MEL21 after being prioritized using the pVAC-Seq pipeline. The points represent the overall sequencing information: exome and RNA VAFs, gene expression in terms of log2 FPKM value, as well log2 fold change, calculated as the ratio of WT binding affinity over mutant binding affinity. Recommended exome and RNA VAF cutoffs are also indicated. Candidates that were incorporated in the vaccine are labeled based on the genes containing these somatic mutations. Red boxes depict naturally occurring (that is, pre-existing T cell response) and blue boxes denote vaccine-induced neoantigens that were recognized by T cells. Since BRAF was used as a guide for assessing clonality of other mutations, it is also shown in each of three metachronous tumors (from the same patient)