一个无描述器的机器学习框架,以改善对细菌病原体的抗原发现
Marco Podda1, Castrense Savojardo2, Pier Luigi Martelli2
1Department of Computer Science, University of Pisa, Largo Bruno Pontecorvo, 3, Pisa, Italy.
PloS one
|June 5, 2025
概括
本研究介绍了用于细菌疫苗标识的蛋白序列嵌入 (PSEs). 新的基于PSE的方法优于传统的基于描述符的方法,减少了高达83%的临床前测试需求.
科学领域:
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
- 疫苗开发 疫苗开发
背景情况:
- 鉴定用于疫苗开发的细菌保护性抗原 (PA) 是具有挑战性的,因为大规模的体内试验是不切实际的.
- 反向疫苗学 (RV) 通过计算来选蛋白质组,但传统的机器学习 (ML) 方法依赖潜在的偏见和复杂的基于描述符的蛋白质表示.
- 来自深度学习模型的蛋白质序列嵌入 (PSE) 提供了一个基于数据的,简化的替代方法,用于ML中的特征提取.
研究的目的:
- 在反向疫苗学 (RV) 中引入和评估蛋白质序列嵌入 (PSE) 作为机器学习 (ML) 的无描述符特征表示.
- 将基于PSE的ML管道的性能与用于识别细菌保护抗原 (PA) 的传统描述器基础管道进行比较.
- 评估基于PSE的管道在排名新型蛋白质组中对临床前疫苗候选人选择的有用性.
主要方法:
- 使用了由FAIR ESM-2蛋白语言模型生成的蛋白序列嵌入 (PSE) 作为ML分类器的输入.
- 开发并比较基于PSE和基于描述器的ML管道,用于在10种细菌物种中对PA进行分类.
- 使用接收器操作特征曲线下的区域 (AUROC) 和基准数据集 (iBPA) 评估管道性能.
主要成果:
- 基于PSE的管道在10种细菌物种中的9种中表现优于基于描述器的管道,平均AUROC为0.875vs0.855.
- 与现有文献方法相比,PSE方法在iBPA基准 (0.86 AUROC) 上表现优异.
- 使用PSE管道对未见的蛋白质组进行排序,使PA识别所需的临床前测试数量平均减少了83%.
结论:
- 在反向疫苗学框架内,PSE为ML驱动的细菌保护抗原识别提供了强大的和有效的无描述符方法.
- 基于PSE的管道显著提高了选择候选疫苗的准确性和效率,简化了临床前测试过程.
- 这种方法提供了一个强大的工具,通过优先考虑最有前途的保护性抗原来加速疫苗开发.
相关概念视频
Defense Against Bacterial Pathogens
1.5K
The human immune system is a complex network of cells, tissues, and organs that work together to defend the body against bacterial infections. It consists of various immune cells, each playing a specific role in the defense mechanism.
Phagocytes
Phagocytes are the frontline soldiers of the immune system. They include neutrophils and macrophages. Neutrophils are the most abundant type of white blood cell and are quickly mobilized to the site of infection. Macrophages are larger cells that patrol...
Phagocytes
Phagocytes are the frontline soldiers of the immune system. They include neutrophils and macrophages. Neutrophils are the most abundant type of white blood cell and are quickly mobilized to the site of infection. Macrophages are larger cells that patrol...
1.5K
Modern Molecular Taxonomy
159
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...
159
Methods of Classification and Identification
241
Bacterial identification relies on a diverse array of techniques to classify and understand microorganisms, each tailored to uncover specific characteristics. Traditional morphological approaches, while still valuable, are limited for closely related or structurally simple organisms. Modern methods integrate biochemical, serological, genetic, and advanced molecular tools to achieve greater accuracy.Morphological and Biochemical TechniquesMorphological characteristics, such as cell shape and...
241


