🔬 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
0.9013
🌋 Hot Springs
0.9012
🌋 Hot Springs
0.9011
🌋 Hot Springs
0.9011
🌋 Hot Springs
0.9011
🧊 Permafrost
0.9010
🧊 Permafrost
0.9010
🌋 Hot Springs
0.9010
🌋 Hot Springs
0.9009
🌋 Hot Springs
0.9008
🌋 Hot Springs
0.9006
🌋 Hot Springs
0.9006
🌋 Hot Springs
0.9006
🌋 Hot Springs
0.9005
🌋 Hot Springs
0.8999
🌋 Hot Springs
0.8998
🌋 Hot Springs
0.8997
🧊 Permafrost
0.8997
🧊 Permafrost
0.8994
🧊 Permafrost
0.8994
🌋 Hot Springs
0.8993
🌋 Hot Springs
0.8992
🌋 Hot Springs
0.8991
🧊 Permafrost
0.8991
📚 Understanding the metrics