Improved proteasomal cleavage prediction with positive-unlabeled learning

TL;DR

This paper introduces a novel proteasomal cleavage predictor trained with positive-unlabeled learning, leveraging an expanded dataset to achieve state-of-the-art accuracy, thereby enhancing epitope vaccine design.

Contribution

It presents a new proteasomal cleavage prediction model using positive-unlabeled learning and an expanded dataset, advancing the accuracy over existing methods.

Findings

Achieved state-of-the-art proteasomal cleavage prediction accuracy.

Utilized positive-unlabeled learning to handle ambiguous negative samples.

Enabled more precise epitope vaccine development.

Abstract

Accurate in silico modeling of the antigen processing pathway is crucial to enable personalized epitope vaccine design for cancer. An important step of such pathway is the degradation of the vaccine into smaller peptides by the proteasome, some of which are going to be presented to T cells by the MHC complex. While predicting MHC-peptide presentation has received a lot of attention recently, proteasomal cleavage prediction remains a relatively unexplored area in light of recent advancesin high-throughput mass spectrometry-based MHC ligandomics. Moreover, as such experimental techniques do not allow to identify regions that cannot be cleaved, the latest predictors generate decoy negative samples and treat them as true negatives when training, even though some of them could actually be positives. In this work, we thus present a new predictor trained with an expanded dataset and the solid theoretical underpinning of positive-unlabeled learning, achieving a new state-of-the-art in proteasomal cleavage prediction. The improved predictive capabilities will in turn enable more precise vaccine development improving the efficacy of epitope-based vaccines. Pretrained models are available on GitHub