π¬ AMP Candidates
2,065 computationally predicted antimicrobial peptide candidates
𧬠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.
β οΈ All candidates are computationally predicted β no experimental validation has been performed.
π Hot Springs
0.9496
π Hot Springs
0.9496
π Hot Springs
0.9495
π Hot Springs
0.9495
π Hot Springs
0.9495
π Hot Springs
0.9494
π Hot Springs
0.9494
π Hot Springs
0.9494
π Hot Springs
0.9493
π Hot Springs
0.9493
π Hot Springs
0.9491
π Hot Springs
0.9490
π Hot Springs
0.9490
π Hot Springs
0.9490
π Hot Springs
0.9490
π Hot Springs
0.9489
π Hot Springs
0.9489
π Hot Springs
0.9488
π Hot Springs
0.9488
π Hot Springs
0.9484
π Hot Springs
0.9483
π Hot Springs
0.9482
π Hot Springs
0.9482
π Hot Springs
0.9481
π Understanding the metrics