AI Insight
This study demonstrates that label noise in training data significantly limits the accuracy of predicting T cell receptor binding to peptide-MHC complexes, a crucial interaction for immune responses. Using an AlphaFold3-based structural modeling pipeline combined with a cluster-based denoising algorithm to remove mislabeled data points, the researchers achieved state-of-the-art prediction performance, improving binder ranking accuracy by more than 70% compared to using the full noisy dataset. The structural approach outperformed both AlphaFold2.3-based and sequence-only methods, performing comparably to top competition submissions.
Why it matters
Accurate prediction of TCR-peptide-MHC binding specificity is essential for developing effective immunotherapies and vaccines. This work identifies data quality as a major bottleneck in the field and provides a practical solution that could accelerate the design of TCR-based cancer treatments and improve vaccine development by enabling better prediction of which T cell receptors will respond to specific disease targets.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
T cell receptor (TCR) binding to peptides presented by major histocompatibility complex (MHC) molecules is a key step in T cell activation, and forms the basis of adaptive immunity. Predicting this specificity is therefore essential to developing effective TCR-based immunotherapies and vaccines. Despite its clinical relevance, predicting TCR-pMHC specificity for previously unseen peptides remains an open problem, with structural modeling so far the only strategy showing any predictive power in this setting. In this study, we find that this limited performance is substantially driven by label noise in the data used to train and evaluate these methods, an effect that has so far been largely underexplored. Using an AlphaFold3-based pipeline adapted for TCR-pMHC structural modeling, we achieve state-of-the-art specificity prediction, outperforming AlphaFold2.3-based and sequence based methods, and performing at par with the leading Immrep2025 competition submission. Combining this pipeline with a cluster-based denoising algorithm, we show that removing mislabeled points from a large specificity dataset increased binder ranking accuracy by more than 70% relative to the full dataset. Together, these results highlight label noise as a major factor limiting the performance that any method in this field can achieve, and show that combining structural modeling with label denoising substantially improves TCR-pMHC specificity prediction, making such approaches an attractive complement to current sequence-based approaches for refining TCR target selection.