🔬 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
0.9309
🌋 Hot Springs
0.9306
🌋 Hot Springs
0.9305
🌋 Hot Springs
0.9305
🧊 Permafrost
0.9305
🌋 Hot Springs
0.9305
🌋 Hot Springs
0.9305
🌋 Hot Springs
0.9305
🌋 Hot Springs
0.9304
🧊 Permafrost
0.9303
🌋 Hot Springs
0.9301
🌋 Hot Springs
0.9301
🌋 Hot Springs
0.9300
🌋 Hot Springs
0.9299
🌋 Hot Springs
0.9299
🌋 Hot Springs
0.9298
🌋 Hot Springs
0.9298
🌋 Hot Springs
0.9297
🌋 Hot Springs
0.9296
🧊 Permafrost
0.9296
🧊 Permafrost
0.9296
🌋 Hot Springs
0.9296
🌋 Hot Springs
0.9296
🌋 Hot Springs
0.9295
📚 Understanding the metrics