Chunhui Gu, Seyyed Mahmood Ghasemi, Yining Cai, Johannes F Fahrmann, James P Long, Hiroyuki Katayama, Chong Wu, Jody Vykoukal, Jennifer B Dennison, Samir Hanash, Kim-Anh Do, Ehsan Irajizad
{"title":"Grape-Pi: graph-based neural networks for enhanced protein identification in proteomics pipelines.","authors":"Chunhui Gu, Seyyed Mahmood Ghasemi, Yining Cai, Johannes F Fahrmann, James P Long, Hiroyuki Katayama, Chong Wu, Jody Vykoukal, Jennifer B Dennison, Samir Hanash, Kim-Anh Do, Ehsan Irajizad","doi":"10.1093/bioadv/vbaf095","DOIUrl":null,"url":null,"abstract":"<p><strong>Motivation: </strong>Protein identification via mass spectrometry (MS) is the primary method for untargeted protein detection. However, the identification process is challenging due to data complexity and the need to control false discovery rates (FDR) of protein identification. To address these challenges, we developed a graph neural network (GNN)-based model, Graph Neural Network using Protein-Protein Interaction for Enhancing Protein Identification (Grape-Pi), which is applicable to all proteomics pipelines. This model leverages protein-protein interaction (PPI) data and employs two types of message-passing layers to integrate evidence from both the target protein and its interactors, thereby improving identification accuracy.</p><p><strong>Results: </strong>Grape-Pi achieved significant improvements in area under receiver-operating characteristic curve (AUC) in differentiating present and absent proteins: 18% and 7% in two yeast samples and 9% in gastric samples over traditional methods in the test dataset. Additionally, proteins identified via Grape-Pi in gastric samples demonstrated a high correlation with mRNA data and identified gastric cancer proteins, like MAP4K4, missed by conventional methods.</p><p><strong>Availability and implementation: </strong>Grape-Pi is freely available at https://zenodo.org/records/11310518 and https://github.com/FDUguchunhui/GrapePi.</p>","PeriodicalId":72368,"journal":{"name":"Bioinformatics advances","volume":"5 1","pages":"vbaf095"},"PeriodicalIF":2.8000,"publicationDate":"2025-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12096076/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bioinformatics advances","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/bioadv/vbaf095","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"MATHEMATICAL & COMPUTATIONAL BIOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Motivation: Protein identification via mass spectrometry (MS) is the primary method for untargeted protein detection. However, the identification process is challenging due to data complexity and the need to control false discovery rates (FDR) of protein identification. To address these challenges, we developed a graph neural network (GNN)-based model, Graph Neural Network using Protein-Protein Interaction for Enhancing Protein Identification (Grape-Pi), which is applicable to all proteomics pipelines. This model leverages protein-protein interaction (PPI) data and employs two types of message-passing layers to integrate evidence from both the target protein and its interactors, thereby improving identification accuracy.
Results: Grape-Pi achieved significant improvements in area under receiver-operating characteristic curve (AUC) in differentiating present and absent proteins: 18% and 7% in two yeast samples and 9% in gastric samples over traditional methods in the test dataset. Additionally, proteins identified via Grape-Pi in gastric samples demonstrated a high correlation with mRNA data and identified gastric cancer proteins, like MAP4K4, missed by conventional methods.
Availability and implementation: Grape-Pi is freely available at https://zenodo.org/records/11310518 and https://github.com/FDUguchunhui/GrapePi.
目的：通过质谱法（MS）进行蛋白质鉴定是检测非靶向蛋白质的主要方法。然而，由于数据复杂性和需要控制蛋白质鉴定的错误发现率（FDR），鉴定过程具有挑战性。为了解决这些挑战，我们开发了一种基于图神经网络（GNN）的模型，即graph neural network using Protein-Protein Interaction for enhance Protein Identification (Grape-Pi)，该模型适用于所有蛋白质组学管道。该模型利用蛋白质-蛋白质相互作用（PPI）数据，并采用两种类型的消息传递层来整合来自目标蛋白质及其相互作用者的证据，从而提高识别精度。结果：在区分存在和不存在的蛋白质方面，葡萄派在受体工作特征曲线下的面积（AUC）上取得了显著的改善：在两个酵母样本中分别提高了18%和7%，在胃样本中提高了9%。此外，通过Grape-Pi在胃样品中鉴定出的蛋白质与mRNA数据高度相关，并鉴定出了传统方法无法识别的胃癌蛋白，如MAP4K4。可用性和实现：可以在https://zenodo.org/records/11310518和https://github.com/FDUguchunhui/GrapePi免费获得Grape-Pi。
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
