用于肿瘤测序数据上突变特征检测复现的 FAIR 平台
基因组学
2023-06-05 v1
摘要
本文提出一个可移植、保护隐私、浏览器内的平台,用于从靶向基因面板生成的稀疏测序数据可复现地评估突变特征检测方法。该平台旨在通过遵循 FAIR 原则(使其可发现、可访问、可互操作、可重用)来解决突变特征研究中的可复现性挑战。我们的方法聚焦于特定突变特征(如 SBS3)的检测,这些特征已与特定诱变过程相关联。该平台依赖公开可用数据、模拟、下采样技术和机器学习算法来生成训练数据与标签,并训练和评估模型。我们平台的关键成就是其透明性、可重用性和隐私保护性,使研究人员和临床医生能够分析突变特征,并保证无任何数据在客户端机器之外流通。
引用
@article{arxiv.2306.01634,
title = {A FAIR platform for reproducing mutational signature detection on tumor sequencing data},
author = {Aaron Ge and Tongwu Zhang and Clara Bodelon and Montserrat Garcia-Closas and Jonas Almeida and Jeya Balasubramanian},
journal= {arXiv preprint arXiv:2306.01634},
year = {2023}
}
备注
Our proposed in-browser platform is publicly available under the MIT license at https://aaronge-2020.github.io/Sig3-Detection/. No data leaves this privacy-preserving environment, which can be cloned or forked and served from other domains with no restrictions. All the code and relevant data used to create this platform can be found at https://github.com/aaronge-2020/Sig3-Detection