Resolution of Recursive Data Corruption to Transform T-cell Epitope Discovery

This preprint studies data contamination in MHC-I epitope discovery. It audits predictor-derived labels, reframes prediction as protein-centric learning to rank, and introduces deepMHCflare for clean-data evaluation.

Links:

• Paper (bioRxiv)

Recommended citation: Preibisch, G., Tyrolski, M., Kucharski, P., Giziński, S., Grzegorczyk, P., Moon, S., Kim, S., Zaro, B., & Gambin, A. (2026). Resolution of recursive data corruption to transform T-cell epitope discovery. bioRxiv, 2026.03.30.710191. https://doi.org/10.64898/2026.03.30.710191
Download Paper | Download Slides