Seq2Neo: a comprehensive pipeline for cancer neoantigen immunogenicity prediction

Abstract

AbstractNeoantigens derived from somatic DNA alterations are ideal cancer-specific targets. In recent years, the combination therapy of PD-1/PD-L1 blockers and neoantigen vaccines shows clinical efficacy in original PD-1/PD-L1 blocker non-responders. However, not all somatic DNA mutations can result in immunogenicity in cancer cells, and efficient tools for predicting the immunogenicity of neoepitope are still urgently needed. Here we present the Seq2Neo pipeline, which provides a one-stop solution for neoepitope features prediction from raw sequencing data, and neoantigens derived from different types of genome DNA alterations, including point mutations, insertion deletions, and gene fusions are supported. Importantly a convolutional neural networks (CNN) based model has been trained to predict the immunogenicity of neoepitope. And this model shows improved performance compared with currently available tools in immunogenicity prediction in independent datasets. We anticipate that the Seq2Neo pipeline will become a useful tool in prediction of neoantigen immunogenicity and cancer immunotherapy. Seq2Neo is an open-source software under an academic free license (AFL) v3.0 and it is freely available athttps://github.com/XSLiuLab/Seq2Neo.