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
0.8960
π Hot Springs
0.8959
π Hot Springs
0.8958
π Hot Springs
0.8958
π Hot Springs
0.8958
π Hot Springs
0.8957
π Hot Springs
0.8957
π Hot Springs
0.8956
π Hot Springs
0.8955
π Hot Springs
0.8955
π Hot Springs
0.8954
π Hot Springs
0.8954
π Hot Springs
0.8953
π Hot Springs
0.8951
π Hot Springs
0.8950
π Hot Springs
0.8948
π Hot Springs
0.8947
π Hot Springs
0.8947
π Hot Springs
0.8947
π Hot Springs
0.8946
π Hot Springs
0.8946
π Hot Springs
0.8946
π Hot Springs
0.8945
π Hot Springs
0.8944
π Understanding the metrics