Proteome encoded determinants of protein sorting into extracellular vesicles

• DOI: 10.1101/2023.02.01.526570
• Publication Date: 2023-02-06T04:35:16Z
• Authors: Katharina Waury; Dea Gogishvili; Rienk Nieuwland; Madhurima Chatterjee; Charlotte E. Teun...; Sanne Abeln
• Keywords: Proteome; Extracellular Vesicles; Palmitoylation; Extracellular vesicles; Sequence (biology); UniProt

Abstract Extracellular vesicles (EVs) are membranous structures released by cells into the extracellular space and thought to be involved in cell-to-cell communication. While EVs their cargo promising biomarker candidates, protein sorting mechanisms of proteins remain unclear. In this study, we ask if it is possible determine EV association based on sequence. Additionally, what most important determinants for association. We answer these questions with explainable AI models, using human proteome data from databases train validate model. It essential correct datasets contaminants introduced coarse isolation workflows experimental bias caused mass spectrometry. show that indeed predict sequence: a simple sequence-based model predicting achieved an area under curve 0.77±0.01, which increased further 0.84±0.00 when incorporating curated post-translational modification (PTM) annotations. Feature analysis shows associated stable, polar, structured low isoelectric point compared non-EV proteins. PTM annotations emerged as features classification; specifically palmitoylation one prevalent unique Palmitoylation nitrosylation sites especially determined very strict protocols, indicating they could potentially serve quality control criteria future studies. This computational study offers effective predictor extensive characterisation can explain individual factors contribute