Paragraph - Antibody paratope prediction using Graph Neural Networks with minimal feature vectors

1SummaryThe development of new vaccines and antibody therapeutics typically takes several years and requires over $1bn in investment. Accurate knowledge of the paratope (antibody binding site) can speed up and reduce the cost of this process by improving our understanding of antibody-antigen binding. We present Paragraph, a structure-based paratope prediction tool that outperforms current state-of-the-art tools using simpler feature vectors and no antigen information. AvailabilitySource code is freely available at www.github.com/oxpig Contactdeane@stats.ox.ac.uk Supplementary informationSupplementary data are available at bioRxiv online.