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
0.8723
π Hot Springs
0.8719
π Hot Springs
0.8719
π Hot Springs
0.8717
π Hot Springs
0.8717
π Hot Springs
0.8716
π Hot Springs
0.8716
π Hot Springs
0.8715
π Hot Springs
0.8715
π Hot Springs
0.8715
π Hot Springs
0.8714
π Hot Springs
0.8714
π Hot Springs
0.8714
π Hot Springs
0.8714
π Hot Springs
0.8713
π Hot Springs
0.8713
π Hot Springs
0.8711
π Hot Springs
0.8711
π Hot Springs
0.8708
π Hot Springs
0.8705
π Hot Springs
0.8704
π Hot Springs
0.8703
π Hot Springs
0.8702
π Hot Springs
0.8702
π Understanding the metrics