从细胞系转移到单细胞的学习方法的综合评估对药物反应预测的预测
IEEE transactions on computational biology and bioinformatics
|December 8, 2025
概括
这项研究将转移学习模型用于预测单细胞药物反应的基准. 它为选择和设计模型提供了指导,以改善精准医学和药物开发.
科学领域:
- 计算生物学是一种计算生物学.
- 药物基因组学 药物基因组学
- 生物技术是生物技术.
背景情况:
- 药物反应预测对于精准医学至关重要,但面临复杂性和成本等挑战.
- 单细胞测序为瘤异质性和耐药性提供了洞察力,突出了单细胞水平预测的需要.
- 单细胞药物敏感性数据的稀缺性阻碍了监督学习模型的开发.
研究的目的:
- 为单细胞药物反应预测提供转移学习模型的首次全面评估.
- 通过评估将知识从批量数据转移到单细胞环境中的方法来解决数据缺口.
- 为选择和设计单细胞药基因组学预测模型提供方法指导.
主要方法:
- 使用转移学习对具有代表性的单细胞药物反应预测模型的全面评估.
- 多维分析包括转移机制,特征对齐策略和预测性能.
- 使用公开可用的数据集进行实证基准测试.
主要成果:
- 系统地比较各种转移学习方法来预测单细胞药物反应.
- 识别功能调整和知识转移的有效策略.
- 对不同模型和数据集的预测性能的评估.
结论:
- 该研究为单细胞药物反应预测模型的选择和设计提供了有价值的方法指导.
- 为推进临床可行的单细胞药物基因组学奠定了基础.
- 强调转移学习的潜力,以克服单细胞药物敏感性预测中的数据稀缺性.
相关概念视频
Factors Affecting Drug Response: Overview
When it comes to infants and young children, they are typically administered smaller doses of medication in comparison to adults. This is primarily because their organ functions still need to fully develop, meaning their bodies are not as efficient at metabolizing or eliminating drugs. Additionally, their blood-brain barrier is more permeable than in adults. As a result, high concentrations of drugs can easily penetrate the central nervous system (CNS), potentially leading to neurological...
Methods for Studying Drug Absorption: In vitro
In vitro experiments are crucial for understanding the transport and absorption of drugs through biological materials. These studies employ varied methods such as the diffusion cell method, the everted sac technique, and the everted ring technique.
The diffusion cell method uses a two-compartment cell, including a donor compartment with the drug solution, which simulates the environment where the drug is applied, and a receptor compartment with a buffer solution, which simulates the environment...
The diffusion cell method uses a two-compartment cell, including a donor compartment with the drug solution, which simulates the environment where the drug is applied, and a receptor compartment with a buffer solution, which simulates the environment...
Drug Product Performance: In Vitro–In Vivo Correlation
In pharmaceutical development, it's crucial to establish a predictive in vitro–in vivo correlation (IVIVC) for two or more formulations to gain a comprehensive understanding of release properties. IVIVC reduces the need for costly in vivo studies and facilitates the establishment of meaningful dissolution specifications with significant cost savings and decreased regulatory burden. Furthermore, a meaningful IVIVC should predict Cmax and AUC within 20%, aligning with FDA guidance while adhering...


