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
0.9045
π Hot Springs
0.9045
π Hot Springs
0.9044
π Hot Springs
0.9043
π Hot Springs
0.9040
π Hot Springs
0.9040
π Hot Springs
0.9039
π Hot Springs
0.9036
π Hot Springs
0.9036
π Hot Springs
0.9035
π Hot Springs
0.9034
π Hot Springs
0.9034
π Hot Springs
0.9033
π Hot Springs
0.9033
π Hot Springs
0.9030
π Hot Springs
0.9029
π Hot Springs
0.9029
π Hot Springs
0.9029
π Hot Springs
0.9028
π Hot Springs
0.9027
π Hot Springs
0.9025
π Hot Springs
0.9025
π Hot Springs
0.9024
π Hot Springs
0.9024
π Understanding the metrics