Machine learning-based prediction of cross-immunity
Vivien Erzsébet Resch, László Tóth, Anita Rácz, Dezső Virok, Gábor Paragi · 2026
Read Machine learning-based prediction of cross-immunity by Vivien Erzsébet Resch, László Tóth, Anita Rácz, Dezső Virok, Gábor Paragi (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13561412.txt.
Description
Vivien Erzsébet Resch, László Tóth, Anita Rácz, Dezső Virok, and Gábor Paragi test whether machine learning can predict when one T cell will react to several similar targets. Their study was published in twenty twenty-six. This cross-reaction, called cross-immunity, is a basic trait of the adaptive immune system.
The team trained sorting models on small sets of lab data for short peptide targets, each nine building blocks long. Mixing two ways of describing the peptides worked best: a similarity table approach and shape-based descriptors. Each method carries its own noise, and the mix cancels some of it out. They also checked how much the chemical content of the descriptions drove the predictions. Better cross-immunity forecasts could aid vaccine and immune therapy design.
Catalog record
| CREATOR | Vivien Erzsébet Resch, László Tóth, Anita Rácz, Dezső Virok, Gábor Paragi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |