How Molecular Networks operate part1

Abstract: Protein subcellular localization is an important factor in normal cellular processes and dis- ease. 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 an- notations from curated pathway databases. We also perform a case study where we con- struct biological pathways and predict localizations of human fibroblasts undergoing viral infection.