# Grape-Pi: graph-based neural networks for enhanced protein identification in proteomics pipelines

## TL;DR

Grape-Pi is a new graph-based neural network that improves protein identification accuracy in proteomics by using protein–protein interaction data.

## Contribution

A novel graph neural network model that integrates PPI data to enhance protein identification in proteomics pipelines.

## Key findings

- Grape-Pi improved AUC by 18% and 7% in yeast samples and 9% in gastric samples compared to traditional methods.
- Proteins identified by Grape-Pi showed high correlation with mRNA data and detected cancer-related proteins like MAP4K4 missed by conventional methods.

## Abstract

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.

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.

Grape-Pi is freely available at https://zenodo.org/records/11310518 and https://github.com/FDUguchunhui/GrapePi.