利用多来源数据来解决药物敏感性预测中药物基因组数据集之间的不一致性
Xiaodi Li1, Trisha Das1,2, Kritib Bhattarai1,3
1Department of Artificial Intelligence and Informatics Research, Mayo Clinic, Rochester, MN, USA.
AMIA ... Annual Symposium proceedings. AMIA Symposium
|February 23, 2026
概括
本研究介绍了聚合学习 (AL),这是一个计算模型,通过从多个药物基因组学数据集中的不一致性中学习来改善药物反应预测. 这种新的方法提高了生物标志物识别的模型准确性和通用性.
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
- 生物医学数据科学是生物医学数据科学.
背景情况:
- 药物基因组学数据集对于生物标志物识别和药物反应预测至关重要.
- 现有的模型往往表现不佳,原因是由于瘤间异质性,实验变异和细胞亚型复杂性的不一致性.
- 这些不一致性限制了预测模型的概括性.
研究的目的:
- 通过有效地从多个药物基因组学数据集的不一致性中学习来增强药物反应预测的计算模型.
- 通过解决数据变异来提高预测模型的准确性和通用性.
主要方法:
- 提出了一种基于聚合学习 (AL) 的新计算模型.
- 该AL模型被训练在三个药物基因组数据集的重叠不一致的数据点上:癌症细胞系百科全书 (CCLE),癌症药物敏感性基因组学 (GDSC2) 和癌症-genomics.org (gCSI).
- 将AL模型的性能与四种基线方法进行比较:选择更好 (SB),结果平均值 (RA),数据结合 (CD) 和模型平均值 (MA).
主要成果:
- 与基线方法相比,聚合学习 (AL) 模型显示出更高的性能.
- 获得较低的平均绝对误差 (MAE) 分数:CCLE-GDSC的0.090,CCLE-gCSI的0.096和GDSC-gCSI的0.081.
- 结果表明,明确解决数据集不一致性的方法显著提高了预测准确度.
结论:
- 解决药物基因组学数据集内部和跨数据集的不一致性对于改善药物反应预测模型至关重要.
- 拟议的综合学习 (AL) 模型为可靠和可概括的药物反应预测提供了一个有希望的解决方案.
- 这种方法有可能通过更准确的生物标志物识别和治疗选择来推进个性化医疗.
相关概念视频
Pharmacogenomics: Identification of New Drug Targets
29
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...
29
Pharmacogenetics and Pharmacogenomics: Overview
51
Pharmacogenetics and pharmacogenomics examine how genetic factors influence an individual's response to drugs. While pharmacogenetics focuses on the impact of specific genetic variants on drug effects, pharmacogenomics takes a broader approach, studying how genetic variation across populations contributes to differences in drug responses. These fields aim to explain why individuals may experience varying levels of efficacy or adverse reactions to the same medication.Variability in drug...
51
Pharmacogenetics of Drug Metabolism: Overview
32
Genetic polymorphism in drug metabolism is crucial to the inter-individual variability observed in drug responses. Drug metabolism primarily involves the chemical modification of drugs and other xenobiotics to enhance their elimination by increasing their polarity. Two main classes of enzymes mediate this biotransformation process: Phase I enzymes, primarily cytochrome P450s, catalyze oxidation and reduction reactions, while other enzymes, such as esterases, mediate hydrolysis, and Phase II...
32
Analysis of Population Pharmacokinetic Data
843
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...
843
Principles of Pharmacogenetics: Types of Genetic Variants
29
The human genome is over 99.9% identical between individuals, yet genetic differences exist at millions of bases. The human genome contains approximately 3 million variant positions per individual, many of which are heterozygous, contributing to genetic diversity and individual traits. Genetic variations include single-nucleotide polymorphisms (SNPs), insertions, deletions, and copy number variations (CNVs).SNPs, the most common variation, involve single-base changes in DNA. These can be...
29
Pharmacogenetic Phenotypes: Alterations in Pharmacokinetics, Drug Targets and Biologic Milieu
26
Genetic variations significantly influence drug response through pharmacokinetics, receptor interactions, and biologic milieu modifications. Pharmacokinetic alterations impact drug metabolism and clearance, affecting efficacy and toxicity. Variants in drug-metabolizing enzymes, such as CYP2C9 and CYP2C19, alter drug activation and elimination. For example, CYP2C9 loss-of-function variants require lower warfarin doses to prevent excessive bleeding, while CYP2C19 variants reduce clopidogrel...
26


