Graph algorithms for predicting subcellular localization at the pathway level

TL;DR

This paper introduces graph algorithms, including neural networks and probabilistic models, to predict protein localization within biological pathways, capturing dynamic cellular processes influenced by biological context.

Contribution

It presents a novel approach of using graph-based models for pathway-level localization prediction, integrating large-scale data and providing a case study on viral infection.

Findings

Graph neural networks outperform other models in localization prediction.

Pathway-based localization prediction enhances understanding of cellular dynamics.

Case study demonstrates practical application in viral infection analysis.

Abstract

Protein subcellular localization is an important factor in normal cellular processes and disease. While many protein localization resources treat it as static, protein localization is dynamic and heavily influenced by biological context. Biological pathways are graphs that represent a specific biological context and can be inferred from large-scale data. We develop graph algorithms to predict the localization of all interactions in a biological pathway as an edge-labeling task. We compare a variety of models including graph neural networks, probabilistic graphical models, and discriminative classifiers for predicting localization annotations from curated pathway databases. We also perform a case study where we construct biological pathways and predict localizations of human fibroblasts undergoing viral infection. Pathway localization prediction is a promising approach for integrating publicly available localization data into the analysis of large-scale biological data.