HR-SC - 一个学术开发的机器学习框架,用于对HRD阳性卵巢癌患者进行分类,并预测对olaparib的敏感性
L Beltrame1, L Mannarino2, A Sergi3
1Laboratory of Cancer Pharmacology, IRCCS Humanitas Research Hospital, Rozzano, Italy.
ESMO open
|May 20, 2025
概括
一个新的机器学习算法,同源复合特征分类器 (HR-SC),准确地预测卵巢癌患者的同源复合修复 (HRR) 状态,改善了对多 (ADP-ribose) 聚合酶抑制剂 (PARPi) 治疗的治疗选择.
科学领域:
- 在瘤学瘤学.
- 基因组学就是基因组学.
- 机器学习 机器学习
背景情况:
- 高度血清性卵巢癌 (OC) 患者具有同源复合修复 (HRR) 缺陷,受益于多 (ADP-ribose) 聚合酶抑制剂 (PARPi) 维持疗法.
- 目前用于识别HRR状态的方法具有很高的失败率和成本,需要创新的方法.
- 同源复合特征分类器 (HR-SC) 是为了解决这些局限性而开发的.
研究的目的:
- 开发和验证一种机器学习 (ML) 算法HR-SC,用于预测OC患者的HRR状态.
- 整合BRCA1/BRCA2状态和复制号签名,以改善HRR预测.
- 评估HR-SC的临床可行性和预测/预后作用.
主要方法:
- 来自两个国际临床试验 (PAOLA-1和MITO16A/MaNGO-OV2) 的569个DNA样本被测序.
- HR-SC经过培训,验证并使用BRCA1/BRCA2状态和注释的副本编号签名进行测试.
- 对HR-SC的表现进行了比较,并与预测和预后评估的既定方法进行了比较.
主要成果:
- 在验证 (数据集A:93.18%) 和测试 (数据集B:87.5%) 数据集中,HR-SC表现出高准确度.
- 灵敏度和特异性在90.16%至94.73%之间,故障率低 (6.4%和4%).
- 生存分析证实HR-SC具有显著的预测性 (PFS:HR=0.42,P<0.0001;OS:HR=0.63,P=0.036) 和预后性 (PFS:HR=0.56,P=0.0095) 作用.
结论:
- HR-SC是一种新的,临床上可行的解决方案,用于预测低失败率的OC患者的HRR状态.
- 该研究强调了ML在推进精确瘤学和个性化医学方面的重要性.
- 在卵巢癌中,HR-SC为优化PARPi治疗选择提供了一个有前途的工具.
相关概念视频
Homologous Recombination
58.9K
The basic reaction of homologous recombination (HR) involves two chromatids that contain DNA sequences sharing a significant stretch of identity. One of these sequences uses a strand from another as a template to synthesize DNA in an enzyme-catalyzed reaction. The final product is a novel amalgamation of the two substrates. To ensure an accurate recombination of sequences, HR is restricted to the S and G2 phases of the cell cycle. At these stages, the DNA has been replicated already and the...
58.9K
Hazard Ratio
785
The hazard ratio (HR) is a widely used measure in clinical trials to compare the risk of events, such as death or disease recurrence, between two groups over time. It reflects the ratio of hazard rates—the instantaneous risk of the event occurring—between a treatment group and a control group. This measure provides valuable insights into the relative effectiveness of a treatment by assessing how the risk of an event differs between the two groups.
For example, in a clinical trial...
For example, in a clinical trial...
785


