Targeted proteomics data interpretation with DeepMRM.
Targeted proteomics data interpretation with DeepMRM.
复制标题
DOI：
10.1016/j.crmeth.2023.100521
复制
发表时间：
2023-07-24
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
靶向蛋白质组学在临床蛋白质组学中得到了广泛的应用，然而，研究人员往往花费大量的时间进行人工数据解释，这阻碍了这种方法的可转移性、重复性和可扩展性。我们介绍了DeepMRM，这是一个基于深度学习算法的目标检测软件包，开发的目的是将目标蛋白质组数据分析中的人工干预降至最低。DeepMRM在内部和公共数据集上进行了评估，显示出与社区标准工具Skyline相比具有更高的准确性。为了促进广泛采用，我们为DeepMRM整合了一个独立的图形用户界面，并将其算法作为外部工具集成到Skyline软件包中。DeepMRM在目标蛋白质组数据解释中利用人工智能进行目标检测DeepMRM在量化精度方面优于Skyline DeepMRM显示跨MRM、PRM和DIA数据的稳健性能DeepMRM作为Windows桌面应用程序和Skyline外部工具可用于临床蛋白质组学，靶向蛋白质组方法如多反应监测(MRM)或平行反应监测(PRM)被广泛使用，但其应用经常受到劳动密集型和容易出错的手动数据解释的阻碍。现有的计算方法虽然有用，但往往需要相当程度的人工干预或诱饵转移方法，限制了临床蛋白质组学分析的吞吐量和效率。为了应对这些挑战，我们开发了DeepMRM，这是一种靶向蛋白质组学数据解释包，有助于高通量分析，并增强临床环境中靶向蛋白质组学的重复性和可扩展性。Park等人。介绍了DeepMRM，这是一个利用深度学习进行目标检测的软件包，可以最大限度地减少目标蛋白质组学数据分析中的人工干预。DeepMRM促进了高通量分析，并提高了临床环境中目标蛋白质组学的重复性和可扩展性。
Targeted proteomics is widely utilized in clinical proteomics; however, researchers often devote substantial time to manual data interpretation, which hinders the transferability, reproducibility, and scalability of this approach. We introduce DeepMRM, a software package based on deep learning algorithms for object detection developed to minimize manual intervention in targeted proteomics data analysis. DeepMRM was evaluated on internal and public datasets, demonstrating superior accuracy compared with the community standard tool Skyline. To promote widespread adoption, we have incorporated a stand-alone graphical user interface for DeepMRM and integrated its algorithm into the Skyline software package as an external tool. DeepMRM utilizes AI for object detection in targeted proteomics data interpretation DeepMRM outperforms Skyline in quantification accuracy DeepMRM shows robust performance across MRM, PRM, and DIA data DeepMRM is available as a Windows desktop application and a Skyline external tool In clinical proteomics, targeted proteomics approaches like multiple-reaction monitoring (MRM) or parallel-reaction monitoring (PRM) are widely used, but their application is often hampered by labor-intensive and error-prone manual data interpretation. Existing computational methods, while helpful, often demand a substantial degree of manual intervention or decoy-transition approaches, constraining the throughput and efficiency of clinical proteomics assays. To address these challenges, we developed DeepMRM, a targeted proteomics data interpretation package that facilitates high-throughput analysis and enhances the reproducibility and scalability of targeted proteomics in clinical settings. Park et al. present DeepMRM, a software package leveraging deep learning for object detection to minimize manual intervention in targeted proteomics data analysis. DeepMRM promotes high-throughput analysis and enhances the reproducibility and scalability of targeted proteomics in clinical settings.