AMR-GNN:一个多代表图神经网络框架,使基因组抗菌素耐药性预测能够实现
Hoai-An Nguyen1, Anton Y Peleg1,2,3, Jessica A Wisniewski1
1Department of Infectious Diseases, The Alfred Hospital and School of Translational Medicine, Monash University, Melbourne, Australia.
Nature communications
|March 6, 2026
概括
从全基因组测序 (WGS) 数据预测抗菌素耐药性 (AMR) 是一个挑战. 我们的AMR-GNN框架使用图形深度学习来准确预测AMR表型,改进现有的机器学习方法.
科学领域:
- 基因组学就是基因组学.
- 生物信息学是一种生物信息学.
- 机器学习 机器学习
背景情况:
- 全基因组测序 (WGS) 为了解抗菌素耐药性 (AMR) 提供了丰富的数据.
- 高维度和缺乏标准化的基因组表征阻碍了从WGS数据中准确预测AMR表型.
- 现有的机器学习 (ML) 方法在利用复杂的基因组信息来预测AMR方面面临挑战.
研究的目的:
- 开发和验证AMR-GNN,一种新的图形深度学习框架,用于使用WGS数据进行AMR表型预测.
- 将多个基因组表示集成到图形神经网络 (GNN) 架构中,以提高预测准确性.
- 解决基于ML的AMR预测的局限性,包括提高性能,减轻克隆效应和识别预测生物标志物.
主要方法:
- 开发了AMR-GNN,这是一个使用图形神经网络 (GNN) 的图形深度学习框架.
- 整合了多个基因组表示,以捕捉与AMR相关的多种遗传特征.
- 将框架应用于Pseudomonas aeruginosa,并在一个庞大的Gram-阴性和Gram-阳性病原体数据集上进行验证.
主要成果:
- 与传统的ML方法相比,AMR-GNN在AMR表型预测方面表现更好.
- 该框架成功地减轻了克隆关系对预测准确性的影响.
- 实现了对AMR具有信息性的基因组生物标志物的鉴定,为预测提供了可解释性.
- 证实了各种病原体类型和药物组合的广泛适用性.
结论:
- AMR-GNN提供了一种强大,数据驱动的方法,用于从WGS数据中准确预测AMR表型.
- 该框架能够整合多个基因组特征并提供可解释性,这代表了该领域的重大进步.
- AMR-GNN显示出在临床微生物学和传染病研究中广泛应用的希望.
相关概念视频
Development of Antibiotic Resistance
1.7K
Antibiotic resistance is a major public health concern that arises when bacteria evolve mechanisms to withstand the effects of antibiotic treatments. This resistance can be intrinsic, acquired through genetic mutations, or transferred between bacteria via horizontal gene transfer. The development of antibiotic resistance poses significant challenges in treating bacterial infections and necessitates ongoing research to develop new therapeutic strategies.Intrinsic resistance occurs when bacterial...
1.7K
Antimicrobial Proteins
14.9K
Antimicrobial proteins are important components of the immune system. They aid the body in combating pathogens by either killing them directly or hindering their replication processes. Four main types of antimicrobial substances are interferons, the complement system, iron-binding proteins, and antimicrobial proteins.
Interferons
Interferons (IFNs) are proteins produced by lymphocytes, macrophages, and fibroblasts infected with viruses. While IFNs cannot prevent viruses from entering and...
Interferons
Interferons (IFNs) are proteins produced by lymphocytes, macrophages, and fibroblasts infected with viruses. While IFNs cannot prevent viruses from entering and...
14.9K


