🔬 AMP Candidates
646 computationally predicted antimicrobial peptide candidates
🧬 About these candidates
Each candidate was identified by mining extreme-environment metagenomes with ESM-2, a protein language model trained on 250M sequences. Candidates pass multi-stage filtering: biophysical scoring, novelty screening against 863K known AMPs (APD3 + DRAMP + AMPSphere), hemolysis risk prediction, and structural validation via AlphaFold2.
⚠️ All candidates are computationally predicted — no experimental validation has been performed.
🧊 Permafrost
0.9844
🧊 Permafrost
0.9843
🧊 Permafrost
0.9843
🧊 Permafrost
0.9840
🧊 Permafrost
0.9837
🧊 Permafrost
0.9832
🧊 Permafrost
0.9831
🧊 Permafrost
0.9829
🧊 Permafrost
0.9829
🧊 Permafrost
0.9827
🧊 Permafrost
0.9825
🧊 Permafrost
0.9823
🧊 Permafrost
0.9820
🧊 Permafrost
0.9820
🧊 Permafrost
0.9820
🧊 Permafrost
0.9819
🧊 Permafrost
0.9816
🧊 Permafrost
0.9815
🧊 Permafrost
0.9813
🧊 Permafrost
0.9812
🧊 Permafrost
0.9811
🧊 Permafrost
0.9809
🧊 Permafrost
0.9801
🧊 Permafrost
0.9800
📚 Understanding the metrics