Multi-objective Peptide Design on GLP-1R 1.0 (test)
9.698Binding AffinityA2D2 w/o quality
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| A2D2 w/o qualityModel length constraint=Any, Optimization strategy=AJD loss fine-tuned, Quality predictor configuration=None2026.06 | 9.698 | 25.033 | 83 | 84.9 | 61.8 | 7.272 | |
| A2D2 w/ both qualityModel length constraint=Any, Optimization strategy=AJD loss fine-tuned, Quality predictor configuration=both quality predictor optimization2026.06 | 9.52 | 29.167 | 85.4 | 84 | 60.1 | 7.209 | |
| Off-Policy RL (Fixed)Model length constraint=Fixed, Optimization strategy=Off-policy RL fine-tuning, Iterations=5002026.06 | 9.377 | 48.767 | 68.4 | 80.4 | 24.7 | 7.019 | |
| Multi-Objective Guidance (Fixed)Model length constraint=Fixed, Optimization strategy=Inference-time multi-objective guidance, Guidance Model=PepTune2026.06 | 8.897 | — | 72.1 | 89.6 | 21.4 | 7.111 | |
| Pre-trained (Fixed)Model length constraint=Fixed, Optimization strategy=Unconditional2026.06 | 8.781 | 32.446 | 70.7 | 90.1 | 21.5 | 7.145 | |
| Pre-trained (Any)Model length constraint=Any, Optimization strategy=Unconditional2026.06 | 8.008 | 10.064 | 68.9 | 85.1 | 16.9 | 7.185 |