| 引用本文: | 杜航,唐景玲,周玲,杨远.Neo-Pred:全变异来源的肿瘤新生[]抗原检测流程[J].生物信息学,2026,24(1):95-100. |
| DU Hang,TANG Jingling,ZHOU Ling,YANG Yuan.Neo-Pred: A comprehensive workflow for detecting tumor neoantigens from all types of mutation sources[J].Chinese Journal of Bioinformatics,2026,24(1):95-100. |
|
| 摘要: |
| 基于体细胞突变产生的新生抗原因其肿瘤特异性高、免疫原性强且不表达于正常组织的特点,成为激活抗肿瘤T细胞应答的理想靶点。目前能全面检测来自不同变异来源的新生抗原的生物信息学工具仍然很匮乏。基于Snakemake流程管理工具,我们开发了Neo-Pred肿瘤新生抗原检测流程,它可以读取高通量测序数据,检测单核苷酸变异(Single nucleotide variant, SNV)、插入缺失(Insertion-deletion, InDel)、基因融合、可变剪接多种变异衍生的新生抗原。我们在肿瘤新生抗原筛选联盟提供的基准数据集上进行了测试,其新生抗原检出的性能为精确率-召回率曲线下面积(Area under the precision-recall curve, AUPRC) 0.71,领先于肿瘤新生抗原筛选联盟其他参与团队(全部参与机构均值为0.221,其中表现最好的团队均值为0.540),筛选性能提升31.5%~221.3%,展示出领先的新生抗原检测能力。通过Singularity容器化和模块化设计,Neo-Pred实现了良好的稳定性、可移植性与动态扩展性。 |
| 关键词: 新生抗原 单核苷酸突变 基因融合 可变剪接 流程 |
| DOI：10.12113/202504006 |
| 分类号:R73 |
| 文献标识码:A |
| 基金项目:国家自然科学基金(No.82260584);贵州省科技厅项目(No.黔科合支撑[2022]一般193、黔科合基础-ZK[2023]一般359、黔科合支撑[2023]一般373)；贵州医科大学附属医院2024年国家自然科学基金培育计划(地区基金)(No.gyfynsfc[2024]-21). |
|
| Neo-Pred: A comprehensive workflow for detecting tumor neoantigens from all types of mutation sources |
|
DU Hang1,2,TANG Jingling1,ZHOU Ling2,YANG Yuan1
|
|
( 1. Clinical Medical Research Center, The Affiliated Hospital of Guizhou Medical University,Guiyang 550004,China;2. Guizhou Sinorda Biotechnology Co.,Ltd, Guiyang 550004,China)
|
| Abstract: |
| Neoantigens derived from somatic mutations have emerged as ideal targets for activating anti-tumor T-cell responses due to their high tumor specificity, strong immunogenicity, and absence of expression in normal tissues. Current bioinformatics tools remain limited in comprehensively detecting neoantigens originating from diverse genomic variations. To address this challenge, we developed Neo-Pred, a tumor neoantigen detection pipeline based on the Snakemake workflow management system. This pipeline processes high-throughput sequencing data to identify neoantigens derived from multiple variant types, including single nucleotide variants (SNVs), insertions-deletions (InDels), gene fusions, and alternative splicing. When evaluated on the benchmark dataset from the Tumor Neoantigen Screening Consortium, Neo-Pred demonstrated superior performance with an Area Under the Precision-Recall Curve (AUPRC) of 0.71 (mean AUPRC: 0.221 for all teams; 0.540 for the top-performing team). This represents a performance improvement of 31.5% to 221.3%, highlighting its leading-edge detection capabilities. The implementation of Singularity containerization and modular architecture ensures remarkable stability, portability, and dynamic scalability. These technical advancements establish Neo-Pred as a cutting-edge solution for neoantigen detection, providing critical support for precision cancer immunotherapy research. |
| Key words: Neoantigen Single nucleotide variant Gene fusion Alternative splicing Workflow |
