近日，中国军事科学院教授李锦及其课题组揭示了深度学习预测H5N1禽流感病毒与人类流感病毒的潜在重组。2025年9月17日，国际知名学术期刊《国家科学评论》发表了这一成果。

研究团队的目标是建立一个名为HAIRANGE的注意力深度学习模型，用于预测H5N1和人类IAVs可能适应人类的重组。在HAIRANGE中，一种名为Codon2Vec的生物相关且未经预先训练的嵌入物在与其他嵌入物（如ESM2、DNABERT2等）的基准测试中表现出竞争性，表明IAV RNA聚合酶相关基因的基因组背景与病毒宿主或血清型高度相关。HAIRANGE准确预测了每个聚合酶相关基因的适应性和适应性聚合酶相关基因的重组，并通过体外报告实验验证了聚合酶活性。令人担忧的是，HAIRANGE预测了H5N1型禽流感病毒与人H3N2型禽流感病毒之间的适应性重组，并通过聚合酶活性试验进行了验证。总之，HAIRANGE可以基于嵌入的基因组背景预测IAV的适应性重组。目前H5N1禽流感病毒可能与人类禽流感病毒重新组合，有可能造成大流行。

据介绍，H5N1甲型禽流感病毒主题（IAVs）的频繁感染病例构成了人类/禽类再组合IAVs的大流行风险。

附：英文原文

Title: Deep learning predicts potential reassortments of avian H5N1 with human influenza viruses

Author: Wei, Jun-Qing, Zhang, Sen, Dan Li, Ya-, Jiang, Shu-Yang, Yan, Si-Rui, Liu, Ying, Chen, Yue-Hong, Feng, Ye, Ding, Xiao, Li, Yu-Chang, Kang, Xiao-Ping, Liu, Wei, Wu, Aiping, Jiang, Tao, Tong, Yigang, Li, Jing

Issue&Volume: 2025-09-17

Abstract: Frequent infection cases with avian H5N1 influenza A viruses (IAVs) are posing pandemic risks of human/avian-reassorted IAVs. We aimed to build an attentional deep learning model named HAIRANGE, for predicting potentially human-adapted reassortment of H5N1 and human IAVs. A biologically relevant and non-pretrained embedding named Codon2Vec in HAIRANGE performed competitively in benchmarking against other embedders, such as ESM2, DNABERT2 and others, indicating a high association of genomic context with virus’s hosts or serotypes, for IAV RNA polymerase-related genes. HAIRANGE predicted accurately the adaptation of each polymerase-related gene and the adaptive polymerase-related gene reassortment with polymerase activity validated by in vitro reporting assay. Worrisomely, an adaptive reassortment between avian H5N1 and human H3N2 IAVs was predicted by HAIRANGE and validated by polymerase activity assay. Summarily, HAIRANGE can predict adaptive IAV reassortment based on embedded genomic context. Current avian H5N1 IAV is posing a pandemic potential via possible reassortment with human IAVs.

DOI: 10.1093/nsr/nwaf396

Source: https://academic.oup.com/nsr/advance-article/doi/10.1093/nsr/nwaf396/8256855searchresult=1