π¬ AMP Candidates
2,713 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
0.8833
π Hot Springs
0.8833
π§ Permafrost
0.8832
π Hot Springs
0.8832
π Hot Springs
0.8831
π Hot Springs
0.8829
π Hot Springs
0.8829
π Hot Springs
0.8829
π Hot Springs
0.8828
π Hot Springs
0.8828
π Hot Springs
0.8828
π Hot Springs
0.8827
π Hot Springs
0.8825
π Hot Springs
0.8825
π§ Permafrost
0.8823
π Hot Springs
0.8822
π Hot Springs
0.8822
π§ Permafrost
0.8822
π Hot Springs
0.8821
π Hot Springs
0.8820
π§ Permafrost
0.8820
π Hot Springs
0.8820
π Hot Springs
0.8820
π§ Permafrost
0.8819
π Understanding the metrics