arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.21201q-bio.GN
收藏

一种用于评估46种多基因风险评分工具的协调基准框架,考虑实施意识,适用于二元和连续表型

A harmonized benchmarking framework for implementation-aware evaluation of 46 polygenic risk score tools across binary and continuous phenotypes

The University of Queensland(昆士兰大学);Baker Heart and Diabetes Institute(贝克心脏与糖尿病研究所)

Muhammad Muneeb, David B. Ascher

AI总结:

本文提出了一种协调的基准框架,评估46种PRS工具在七种二元UK Biobank表型和一种连续性表型下的性能,考虑了统计假设、输入要求和实现复杂性,发现没有单一方法最优。

摘要:

多基因风险评分(PRS)工具在统计假设、输入要求和实现复杂性方面差异显著,使直接比较困难。我们开发了一种协调的、考虑实施的基准框架,评估46种PRS工具在七种二元UK Biobank表型和一种连续性表型下的性能,采用三种模型配置:null、PRS-only和PRS加协变量。该框架整合了标准化预处理、工具特定执行、超参数探索和统一的下游评估,使用五折交叉验证在高性能计算基础设施上进行。除了预测性能外,我们还评估了运行时间、内存使用、输入依赖性和失败模式。在40个表型-折组合上的Friedman检验确认了工具排名的显著差异(χ²=102.29,p=2.57×10⁻¹¹),没有单一方法在所有情况下最优。这些发现提供了一种可重复的PRS比较框架,证明工具性能不仅受统计方法影响,还受表型架构、预处理选择、协变量结构、计算需求、软件稳健性和实际实施限制的影响。

英文摘要:

Polygenic risk score (PRS) tools differ substantially in statistical assumptions, input requirements, and implementation complexity, making direct comparison difficult. We developed a harmonized, implementation-aware benchmarking framework to evaluate 46 PRS tools across seven binary UK Biobank phenotypes and one continuous trait under three model configurations: null, PRS-only, and PRS plus covariates. The framework integrates standardized preprocessing, tool-specific execution, hyperparameter exploration, and unified downstream evaluation using five-fold cross-validation on high-performance computing infrastructure. In addition to predictive performance, we assessed runtime, memory use, input dependencies, and failure modes. A Friedman test across 40 phenotype--fold combinations confirmed significant differences in tool rankings ($χ^2 = 102.29$, $p = 2.57 \times 10^{-11}$), with no single method universally optimal. These findings provide a reproducible framework for comparative PRS evaluation and demonstrate that tool performance is shaped not only by statistical methodology but also by phenotype architecture, preprocessing choices, covariate structure, computational demands, software robustness, and practical implementation constraints.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑