对分子动力学模拟的机器学习提供了对病毒囊组装模拟的洞察力
Anna Pavlova1, Zixing Fan2, Diane L Lynch1
1School of Physics, Georgia Institute of Technology, Atlanta, GA, 30332 USA.
bioRxiv : the preprint server for biology
|February 20, 2025
概括
机器学习模型可以准确地区分乙型肝炎病毒 (HBV) 囊组合状态. 这有助于开发新的抗病毒药物,通过了解囊组装调节器 (CAM) 和它们对病毒结构的影响.
科学领域:
- 病毒学和结构生物学
- 计算化学和机器学习
背景情况:
- 开发新型抗病毒药物通常涉及使用囊组装调节器 (CAM) 准病毒囊组装.
- 乙型肝炎病毒 (HBV) CAM可以加速或误导核囊组合,影响病毒结构.
- 之前的分子动力学 (MD) 模拟表明,体蛋白中间体在apo和CAM结合状态之间存在构造差异.
研究的目的:
- 开发和评估机器学习 (ML) 分类模型,以区分阿波-四胺中间体和那些加速或误导CAM的中间体.
- 确定关键的结构特征和蛋白质区域对于区分这些组装状态至关重要.
- 为了证明ML在分析MD轨迹中对抗病毒药物开发的实用性.
主要方法:
- 开发和测试使用Cp149四度体和二次体间方向的三级结构性质的分类ML模型.
- 利用基于蛋白质残留物之间的直接和反向接触距离的模型.
- 从MD模拟数据中比较ML模型在分类apo和两个不同的CAM-bound状态中的性能.
主要成果:
- 所有开发的ML模型都在区分apo和两个CAM-bound状态方面取得了很高的准确性.
- 三级结构和残留距离模型确定了与分类相关的不同关键四度体区域.
- 该研究成功地证明了ML的应用,用于比较MD轨迹和理解结构过渡.
结论:
- 分类ML模型是区分HBV囊组合状态的有效工具.
- 这些模型可以增强对控制核囊组装的结构过渡的理解.
- 开发的ML方法可以帮助设计和开发针对HBV和其他病毒系统的更强大的抗病毒CAM.
相关概念视频
00:56Viral Structure
61.6K
Viruses are extraordinarily diverse in shape and size, but they all have several structural features in common. All viruses have a core that contains a DNA- or RNA-based genome. The core is surrounded by a protective coat of proteins called the capsid. The capsid is composed of subunits called capsomeres. The capsid and genome-containing core are together known as the nucleocapsid.
61.6K
02:41Protein Complex Assembly
10.5K
Proteins can form homomeric complexes with another unit of the same protein or heteromeric complexes with different types. Most protein complexes self-assemble spontaneously via ordered pathways, while some proteins need assembly factors that guide their proper assembly. Despite the crowded intracellular environment, proteins usually interact with their correct partners and form functional complexes.
Many viruses self-assemble into a fully functional unit using the infected host cell to...
Many viruses self-assemble into a fully functional unit using the infected host cell to...
10.5K