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
0.8742
π Hot Springs
0.8742
π Hot Springs
0.8741
π Hot Springs
0.8741
π Hot Springs
0.8739
π Hot Springs
0.8739
π Hot Springs
0.8738
π Hot Springs
0.8733
π Hot Springs
0.8731
π Hot Springs
0.8731
π Hot Springs
0.8730
π Hot Springs
0.8730
π Hot Springs
0.8729
π Hot Springs
0.8728
π Hot Springs
0.8727
π Hot Springs
0.8726
π Hot Springs
0.8726
π Hot Springs
0.8724
π Hot Springs
0.8724
π Hot Springs
0.8723
π Hot Springs
0.8723
π Hot Springs
0.8723
π Hot Springs
0.8723
π Hot Springs
0.8723
π Understanding the metrics