🔬 AMP Candidates
2,713 computationally predicted antimicrobial peptide candidates
🧬 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.
⚠️ All candidates are computationally predicted — no experimental validation has been performed.
🧊 Permafrost
0.9564
🌋 Hot Springs
0.9563
🌋 Hot Springs
0.9563
🧊 Permafrost
0.9563
🌋 Hot Springs
0.9562
🌋 Hot Springs
0.9562
🌋 Hot Springs
0.9561
🌋 Hot Springs
0.9560
🌋 Hot Springs
0.9559
🧊 Permafrost
0.9559
🌋 Hot Springs
0.9558
🌋 Hot Springs
0.9558
🧊 Permafrost
0.9557
🧊 Permafrost
0.9557
🌋 Hot Springs
0.9557
🌋 Hot Springs
0.9557
🧊 Permafrost
0.9556
🌋 Hot Springs
0.9556
🌋 Hot Springs
0.9556
🌋 Hot Springs
0.9555
🌋 Hot Springs
0.9555
🧊 Permafrost
0.9555
🧊 Permafrost
0.9555
🌋 Hot Springs
0.9553
📚 Understanding the metrics