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
0.9118
π Hot Springs
0.9116
π Hot Springs
0.9114
π Hot Springs
0.9112
π Hot Springs
0.9112
π Hot Springs
0.9111
π Hot Springs
0.9111
π Hot Springs
0.9110
π Hot Springs
0.9110
π Hot Springs
0.9110
π Hot Springs
0.9109
π Hot Springs
0.9109
π Hot Springs
0.9109
π Hot Springs
0.9108
π Hot Springs
0.9106
π Hot Springs
0.9106
π Hot Springs
0.9106
π Hot Springs
0.9105
π Hot Springs
0.9102
π Hot Springs
0.9100
π Hot Springs
0.9100
π Hot Springs
0.9100
π Hot Springs
0.9098
π Hot Springs
0.9098
π Understanding the metrics