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
0.9427
π Hot Springs
0.9426
π Hot Springs
0.9426
π Hot Springs
0.9426
π Hot Springs
0.9426
π Hot Springs
0.9426
π Hot Springs
0.9425
π Hot Springs
0.9423
π Hot Springs
0.9420
π Hot Springs
0.9420
π Hot Springs
0.9420
π Hot Springs
0.9420
π Hot Springs
0.9419
π Hot Springs
0.9419
π Hot Springs
0.9418
π Hot Springs
0.9418
π Hot Springs
0.9417
π Hot Springs
0.9417
π Hot Springs
0.9416
π Hot Springs
0.9415
π Hot Springs
0.9415
π Hot Springs
0.9415
π Hot Springs
0.9415
π Hot Springs
0.9414
π Understanding the metrics