Benchmarking TCR–pMHC structure prediction: a unified evaluation and CDR3-based functional insights
Jiadong Lu, Xinyuan Zhu, Xinting Hu, Cheng Zhang, Fuli Feng · 2026
Read Benchmarking TCR–pMHC structure prediction: a unified evaluation and CDR3-based functional insights by Jiadong Lu, Xinyuan Zhu, Xinting Hu, Cheng Zhang, Fuli Feng (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-13240595.txt.
Description
Jiadong Lu and four co-authors benchmarked tools that predict how immune receptors meet their targets, in a 2026 paper. T cell receptors latch onto peptide pieces shown by body cells. That meeting is central to immune defense. New AI tools can model the meeting at atomic scale, but users lacked fair comparisons.
The team tested thirteen models on seventy complexes none had seen. Tools that use sequence alignments beat other kinds on accuracy. One leading model stood out in particular. The authors found a confidence score for a key receptor loop in its output. That score predicted both structure quality and real binding effects. Using it to rerank guesses raised top-hit success. It also caught most mutation effects on binding strength in their checks.
Catalog record
| CREATOR | Jiadong Lu, Xinyuan Zhu, Xinting Hu, Cheng Zhang, Fuli Feng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |