从公共药物基因组数据集中识别有意义的药物反应生物标志物,并使用生物信息可解释的神经网络
Maoxin Ran1, Shao-Lin Zhang2, Kin Yip Tam1
1Faculty of Health Sciences, University of Macau, Avenida de Universidade, Taipa, Macao Special Administrative Region of China.
Computational biology and chemistry
|September 7, 2025
概括
一个新的稀疏神经网络K-net识别了癌症药物耐药性的关键生物标志物. 这种可解释的模型有助于优化癌症治疗策略,通过揭示亚型特定的抗性机制.
科学领域:
- 药物基因组学 药物基因组学
- 计算生物学 计算生物学
- 癌症研究 癌症研究
背景情况:
- 下一代测序的进步已经从癌症细胞系中产生了大量的药物基因组数据集.
- 药物反应的预测模型往往缺乏生物解释性,充当"黑子".
- 确定药物反应的可靠生物标志物对于个性化癌症治疗至关重要.
研究的目的:
- 利用癌细胞系数据开发一种可解释的药物反应预测模型.
- 确定与药物反应相关的关键生物标志物,特别是EGFR信号通路.
- 将开发模型的性能与现有的可解释算法进行比较.
主要方法:
- 利用开源药物反应数据和KEGG通路信息.
- 开发了一个稀疏神经网络模型,命名为K-net.net.
- 分析了耐药与敏感细胞系中的生物标志物分布.
- 进行模拟扰动分析以验证生物标志物的相关性.
- 将K-net与拉索逻辑回归和随机森林分类器进行比较.
主要成果:
- 在识别与 osimertinib 反应相关的生物标志物方面,K-net 的表现优于其他算法.
- 确定了关键生物标志物,包括KRAS和TP53突变,以及AKT3过度表达.
- 揭示了这些生物标志物与 osimertinib 耐药性之间的关联.
- 发现了亚型特定的生物标志物:肺腺癌 (LUAD) 中的KRAS突变和小细胞肺癌 (SCLC) 中的AKT3过度表达.
结论:
- K-net有效地识别了用于药物反应预测的关键生物标志物.
- 该模型提供了有意义的生物解释,克服了"黑子"的限制.
- 这些发现有助于通过精确的生物标志物识别优化癌症治疗策略.
更多相关视频
08:31Biosensor-based High Throughput Biopanning and Bioinformatics Analysis Strategy for the Global Validation of Drug-protein Interactions
Published on: December 1, 2020
5.5K
09:47Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
1.7K
相关概念视频
Analysis of Population Pharmacokinetic Data
682
Analysis of population pharmacokinetic data involves studying the behavior of drugs within diverse populations to understand their pharmacokinetic parameters. Traditional pharmacokinetic methods typically involve collecting samples from a few individuals and estimating these parameters. While these methods are commonly used, they have limitations in capturing the variability in drug response among individuals or heterogeneous populations. Population pharmacokinetics is employed to address these...
682
Measurement of Bioavailability: Pharmacodynamic Methods
236
Pharmacodynamic methods provide insights into a drug's effects on physiological processes over time and play a crucial role in understanding bioavailability and therapeutic efficacy. These methods can be broadly classified into acute pharmacological and therapeutic response approaches, each with distinct mechanisms and applications.The acute pharmacological response method directly correlates a drug's physiological effects, such as ECG or pupil diameter changes, to its time course in the body.
236
