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
0.9288
π Hot Springs
0.9288
π Hot Springs
0.9286
π Hot Springs
0.9285
π Hot Springs
0.9285
π Hot Springs
0.9285
π Hot Springs
0.9284
π Hot Springs
0.9283
π Hot Springs
0.9283
π Hot Springs
0.9282
π Hot Springs
0.9279
π Hot Springs
0.9279
π Hot Springs
0.9279
π Hot Springs
0.9279
π Hot Springs
0.9279
π Hot Springs
0.9278
π Hot Springs
0.9277
π Hot Springs
0.9276
π Hot Springs
0.9276
π Hot Springs
0.9276
π Hot Springs
0.9275
π Hot Springs
0.9275
π Hot Springs
0.9274
π Hot Springs
0.9274
π Understanding the metrics