Assigning protein subcellular distributions of vesicle associated tail‐anchored membrane proteins by image‐based machine learning

Abstract

Subcellular localization of proteins is a key feature of eukaryotes. Traditionally, co-staining with known marker proteins (antibody based or fluorescence fusion protein) or organelle-specific dyes (e.g., MitoTrackerTM) have been used to study subcellular localization of proteins of interest, followed by, a final inspection of the fluorescence microscope images by an experimentalist. However, human visual examination is inclined to bias and membrane proteins are trafficked in vesicles between subcellular locations such that assignment to a specific organelle can be misleading. As an alternative way to assign localization we generated a reference library of confocal micrographs of EGFP fusion proteins localized at key subcellular organelles in murine and human cell lines. Rather than assign the localization of an unknown protein to a specific organelle we consider which reference protein has the most similar subcellular distribution from image sets that are optically validated and comprise 789,011 and 523,319 individual human and murine cell images, respectively. Both morphology and statistical features were computed to enable automated assignment of the subcellular distribution for query proteins by machine learning algorithms with high accuracy. By means of this tool we investigate subcellular transport and distribution for model tail-anchored proteins with randomly mutated C-terminal targeting sequences for the endoplasmic reticulum and through out the secretory pathway.