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
0.9451
π Hot Springs
0.9451
π Hot Springs
0.9451
π Hot Springs
0.9451
π Hot Springs
0.9450
π Hot Springs
0.9450
π Hot Springs
0.9449
π Hot Springs
0.9449
π Hot Springs
0.9449
π Hot Springs
0.9449
π Hot Springs
0.9448
π Hot Springs
0.9446
π Hot Springs
0.9446
π Hot Springs
0.9445
π Hot Springs
0.9445
π Hot Springs
0.9445
π Hot Springs
0.9444
π Hot Springs
0.9444
π Hot Springs
0.9444
π Hot Springs
0.9443
π Hot Springs
0.9443
π Hot Springs
0.9442
π Hot Springs
0.9441
π Hot Springs
0.9441
π Understanding the metrics