🔬 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
0.9048
🧊 Permafrost
0.9047
🌋 Hot Springs
0.9046
🌋 Hot Springs
0.9046
🌋 Hot Springs
0.9046
🌋 Hot Springs
0.9045
🧊 Permafrost
0.9045
🌋 Hot Springs
0.9045
🧊 Permafrost
0.9045
🌋 Hot Springs
0.9044
🌋 Hot Springs
0.9043
🌋 Hot Springs
0.9040
🌋 Hot Springs
0.9040
🌋 Hot Springs
0.9039
🌋 Hot Springs
0.9036
🌋 Hot Springs
0.9036
🧊 Permafrost
0.9035
🌋 Hot Springs
0.9035
🌋 Hot Springs
0.9034
🌋 Hot Springs
0.9034
🌋 Hot Springs
0.9033
🌋 Hot Springs
0.9033
🧊 Permafrost
0.9032
🌋 Hot Springs
0.9030
📚 Understanding the metrics