基于机器学习的抗菌素耐药性的预测和在Mycobacterium tuberculosis中识别与AMR相关的SNP
Yi Xu1,2, Ying Mao3,2, Xiaoting Hua1,4
1Department of Infectious Diseases, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, 310016, China.
BMC genomic data
|July 11, 2025
概括
机器学习使用全基因组测序数据准确预测了Mycobacterium tuberculosis (MTB) 的抗菌耐药性. 渐变增强分类器模型确定了对利芬素和异化物耐药性的关键遗传突变,提高了诊断透明度.
科学领域:
- 基因组学和生物信息学
- 计算生物学 计算生物学
- 传染病研究 传染病研究
背景情况:
- 由Mycobacterium tuberculosis (MTB) 引起的结核病 (TB) 仍然是一个全球健康威胁,由抗菌素耐药性 (AMR) 加剧.
- 全基因组测序 (WGS) 数据为了解MTB中AMR的遗传基础提供了一个强大的资源.
- 机器学习 (ML) 方法可以分析复杂的基因组数据,以识别与药物耐药性相关的模式.
研究的目的:
- 开发和评估一个ML框架,用WGS数据预测MTB中的AMR表型.
- 确定与对第一线抗结核药物耐药性相关的特定单核酸多态 (SNP).
- 为了提高ML模型在AMR研究中的可解释性,以提高潜在的临床应用.
主要方法:
- 利用了18个MTB基因型和抗菌素敏感性测试表型的二进制矩阵.
- 开发了一个ML框架,包含12个算法,在各种SNP数据集 (全部,交叉,随机) 上进行训练和测试.
- 采用了SHapley添加式扩展 (SHAP) 来解释最佳ML模型的决策过程,并将其应用于来自印度和以色列的独立数据集.
主要成果:
- 渐变增强分类器 (GBC) 模型在一线药物中实现了最高的预测准确性 (例如,利芬素97.28%,异化96.06%).
- 在SHAP分析中,特定的SNP (例如,Rifampicin的rpoB_p.Ser450,Isoniazid的katG_p.Ser315) 是对药物耐药性的高度预测.
- 该GBC模型展示了强大的概括能力,准确地预测了独立的外部MTB数据集中的耐药性表型.
结论:
- 综合ML方法为预测MTB抗微生物耐药性提供了一个透明和可解释的框架.
- 确定了与AMR相关的关键SNP,为药物耐药性的基因组机制提供了洞察力.
- 开发的ML方法有可能在结核病诊断和治疗策略中获得临床应用.
相关概念视频
Modern Molecular Taxonomy
154
Advancements in molecular biology have revolutionized the identification and characterization of bacteria, with multiple methods leveraging DNA sequencing for enhanced precision. As sequencing technologies improve and costs decline, these approaches are increasingly used in clinical, environmental, and evolutionary studies.Multilocus Sequence Typing (MLST) examines several housekeeping genes, essential chromosomal genes encoding cellular functions, to distinguish strains. Approximately...
154
Applications of Molecular Taxonomy
115
Molecular taxonomy has revolutionized the understanding and classification of bacteria, providing precise insights into their diversity, evolutionary relationships, and ecological roles. By utilizing molecular techniques such as DNA sequencing and fingerprinting, researchers have made significant strides in various fields related to bacterial studies.Resolving Taxonomic AmbiguitiesMolecular taxonomy has been instrumental in distinguishing closely related bacterial species initially thought to...
115


