TCR-epitope interaction prediction on IMMREP25 unseen epitopes
0.513AUCTEIM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TEIMModel Category=External baselines, Scoring or Training Strategy=classifier head2026.06 | 0.513 | 0.113 | |
| TULIP-TCRModel Category=External baselines, Scoring or Training Strategy=generative MLM, native-vocabulary generative interface=true2026.06 | 0.506 | 0.114 | |
| iTCepModel Category=External baselines, Scoring or Training Strategy=classifier head2026.06 | 0.505 | 0.113 | |
| ImRexModel Category=External baselines, Scoring or Training Strategy=classifier head2026.06 | 0.503 | 0.11 | |
| TCR-T5Model Category=External baselines, Scoring or Training Strategy=generative MLM, native-vocabulary generative interface=true2026.06 | 0.501 | 0.121 | |
| LOGICA-PepModel Category=Contextualized backbone, Scoring or Training Strategy=peptide-anchored token scoring, native-vocabulary generative interface=true2026.06 | 0.5 | 0.111 | |
| LOGIMLMModel Category=Contextualized backbone, Scoring or Training Strategy=continued MLM, native-vocabulary generative interface=true2026.06 | 0.499 | 0.116 | |
| LOGICA-DualModel Category=Contextualized backbone, Scoring or Training Strategy=dual-anchor token scoring, native-vocabulary generative interface=true2026.06 | 0.499 | 0.111 | |
| LOGICA-TCRModel Category=Contextualized backbone, Scoring or Training Strategy=TCR-anchored token scoring, native-vocabulary generative interface=true2026.06 | 0.498 | 0.11 | |
| ERGO-IIModel Category=External baselines, Scoring or Training Strategy=classifier head2026.06 | 0.498 | 0.105 | |
| EPACTModel Category=External baselines, Scoring or Training Strategy=embedding contrastive2026.06 | 0.492 | 0.111 |