STProtein: predicting spatial protein expression from multi-omics data

2026-02-05

AI Summary

Spatial proteomics data remain scarce, hindering effective multi-omics integration with spatial transcriptomics. To address this limitation, this work proposes a novel approach that combines graph neural networks with multi-task learning to predict the spatial distribution of protein expression in tissues, leveraging readily available spatial transcriptomic and other multi-omics data. The method substantially alleviates the scarcity of protein measurements and achieves high-fidelity reconstruction of spatial protein expression patterns. Beyond enabling accurate imputation, the framework uncovers latent spatial gene–protein relationships, facilitates the discovery of novel biomarkers, and sheds light on functional “dark matter” within tissue architecture.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

The integration of spatial multi-omics data from single tissues is crucial for advancing biological research. However, a significant data imbalance impedes progress: while spatial transcriptomics data is relatively abundant, spatial proteomics data remains scarce due to technical limitations and high costs. To overcome this challenge we propose STProtein, a novel framework leveraging graph neural networks with multi-task learning strategy. STProtein is designed to accurately predict unknown spatial protein expression using more accessible spatial multi-omics data, such as spatial transcriptomics. We believe that STProtein can effectively addresses the scarcity of spatial proteomics, accelerating the integration of spatial multi-omics and potentially catalyzing transformative breakthroughs in life sciences. This tool enables scientists to accelerate discovery by identifying complex and previously hidden spatial patterns of proteins within tissues, uncovering novel relationships between different marker genes, and exploring the biological"Dark Matter".

Problem

• spatial proteomics
• data imbalance
• spatial multi-omics
• protein expression prediction
• spatial transcriptomics

Innovation

• spatial proteomics
• graph neural networks
• multi-task learning
• spatial transcriptomics
• multi-omics integration