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
0.8857
π Hot Springs
0.8857
π Hot Springs
0.8856
π Hot Springs
0.8855
π Hot Springs
0.8855
π Hot Springs
0.8854
π Hot Springs
0.8850
π Hot Springs
0.8849
π Hot Springs
0.8849
π Hot Springs
0.8849
π Hot Springs
0.8845
π Hot Springs
0.8845
π Hot Springs
0.8844
π Hot Springs
0.8844
π Hot Springs
0.8842
π Hot Springs
0.8842
π Hot Springs
0.8842
π Hot Springs
0.8842
π Hot Springs
0.8840
π Hot Springs
0.8840
π Hot Springs
0.8839
π Hot Springs
0.8838
π Hot Springs
0.8838
π Hot Springs
0.8838
π Understanding the metrics