Protein Sequence Generation on Target qB
83COMP.ProtGPT2 + RL (best run)
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| ProtGPT2 + RL (best run)Stage=RL, Criterion=lowest pool-mean JSD2026.06 | 83 | 0.0008 | 20 | |
| ProtGPT2 + RL (mean)Stage=RL, Seeds=102026.06 | 56.6 | 0.021 | 12.21 | |
| ProtGPT2 + Domain-Adapt. FTStage=Domain-Adaptive Fine-Tuning2026.06 | 20.7 | 0.051 | 8.25 | |
| Base ProtGPT2Stage=Base2026.06 | 5.4 | 0.202 | 3.71 |