Exploring noise in TCR specificity data through supervised learning
Sebastian Nymann Deleuran, Yogesh Basavaraju, Ruta Matuleviciute, Kristoffer Haurum Johansen, Sine Reker Hadrup, Morten Nielsen
This paper introduces a supervised learning denoising method to identify low-quality labels in TCR specificity data, improving model reliability by filtering noisy examples.
bioRxiv · Oct 8, 2026 · PreprintBioinformatics