以物理知识为基础的人工智能与化学主方程动态,用于驱动基因亚克隆检测和风险标签
Komlan Atitey1, Caitlin E Hughes2, Joseph C Fusco3
1Biostatistics and Computational Biology Branch, National Institute of Environmental Health Sciences (NIEHS), 111 T W Alexander Dr Rall Building, Research Triangle Park, NC 27709, United States.
Computational and structural biotechnology journal
|November 14, 2025
概括
我们开发了magicSubclonal,这是一种用于识别癌症转录组中的罕见细胞亚克隆的新框架. 这种方法通过整合基因动态和临床结果来改善亚克隆发现和风险预测.
科学领域:
- 计算生物学 计算生物学
- 基因组学就是基因组学.
- 系统生物学 系统生物学
背景情况:
- 亚克隆群体显著影响癌症进展和治疗结果.
- 由于信号稀释,在批量转录组中解决罕见的亚克隆是具有挑战性的.
- 现有的方法往往缺乏动态建模或表达式定义状态,导致不稳定的签名.
研究的目的:
- 介绍magicSubclonal,一个基于物理的框架,用于子克隆发现和风险预测.
- 为了整合驱动基因动态,使用化学主方程来提高亚克隆分辨率.
- 开发一种可靠的方法,将子克隆状态与临床结果联系起来.
主要方法:
- 利用化学主方程来建模驱动基因动力学,估计基因表达的衰变,爆发启动和爆发大小.
- 开发了一种自动化方法,用于选择稀有状态分离的最佳时间点.
- 综合的驱动器定时状态与非驱动器基因使用虚假发现率控制和通过稳定Cox/物流模型分配临床风险.
主要成果:
- magicSubclonal在多种癌症队列 (卵巢,肺,乳腺) 中展示了可信的参数估计 (例如,半衰期) 和精确校准的预测.
- 与sciClone,NMF,ss-Deconv和MM等现有方法相比,在识别子克隆驱动器相关性 (SDRS) 和预测准确性 (ROC,精度回忆) 中取得了卓越的性能.
- 在低虚假阳性率和早期召回方面,性能增长尤其显著,这表明超出静态混合模型的信号检测能力得到了增强.
结论:
- magicSubclonal通过将随机驱动动力学与人口异质性相结合,提供可解释和可重复的子克隆发现.
- 该框架通过将评估与临床结果挂,提供了强大的风险标签.
- 灵敏度分析证实了模型对爆发发起和大小的依赖,用于短期预测,而衰变在更长的时间尺度上变得更加关键.
相关概念视频
Non-equilibrium in the Cell
4.0K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.0K
Pharmacogenomics: Identification of New Drug Targets
129
Advances in genomics have profoundly influenced drug discovery by increasing both the speed and accuracy of pharmaceutical development. Pharmacogenomics, which examines how genetic variation influences drug response, facilitates the identification of novel therapeutic targets and enables patient stratification for personalized treatment. These strategies contribute to improved drug efficacy, minimized adverse effects, and more efficient clinical trial design.Mapping genetic differences...
129


