# nuTCRacker: Predicting the Recognition of HLA‐I–Peptide Complexes by αβTCRs for Unseen Peptides

## TL;DR

nuTCRacker is a deep learning method that predicts which peptides a T-cell receptor can recognize, even for peptides not seen in training data.

## Contribution

nuTCRacker introduces a novel deep learning approach to predict αβTCR recognition of HLA-I–peptide complexes for unseen peptides with reasonable accuracy.

## Key findings

- nuTCRacker achieves an AUC > 0.7 for around a third of unseen peptides using a large curated dataset.
- Successful predictions require similar peptides and TCRs in the training data for the same HLA-I molecule.
- The method outperforms benchmarked approaches for predicting αβTCR-peptide-HLA-I affinity.

## Abstract

The ability to predict which antigenic peptide(s) the αβTCR of a given CD8+ T‐cell clone can recognise would represent a quantum leap in the understanding of T‐cell repertoire selection and development of targeted cell‐mediated immunotherapies. Current methods fail to make accurate predictions for antigenic peptides not present in the training dataset. Here, we propose a novel deep learning method called nuTCRacker that makes accurate predictions for a subset of unseen peptides, with an AUC > 0.7 for around a third of peptides evaluated using a large dataset compiled from curated public resources. An additional evaluation was undertaken using a small cellula‐validated dataset of αβTCR peptides associated with cancer. Our analysis suggests that it is possible to make useful predictions for an unseen peptide provided the training dataset contains: many samples with the same HLA class I molecule as that bound to the peptide; at least one peptide that is similar to the target peptide; and a small number of αβTCRs that are similar to those bound to the unseen peptide of interest.

nuTCRacker aims to predict unseen αβTCR‐peptide‐HLA‐I affinity. Predictions are successful for only a subset of unseen peptides although they are better than the benchmarked methods. Predictions are tested on both novel and published T cell assays.