🔬 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.
🌋 Hot Springs
0.9246
🌋 Hot Springs
0.9246
🌋 Hot Springs
0.9244
🌋 Hot Springs
0.9244
🌋 Hot Springs
0.9244
🧊 Permafrost
0.9244
🧊 Permafrost
0.9243
🧊 Permafrost
0.9243
🌋 Hot Springs
0.9243
🌋 Hot Springs
0.9242
🌋 Hot Springs
0.9242
🌋 Hot Springs
0.9242
🧊 Permafrost
0.9241
🌋 Hot Springs
0.9240
🧊 Permafrost
0.9239
🧊 Permafrost
0.9239
🌋 Hot Springs
0.9239
🌋 Hot Springs
0.9238
🌋 Hot Springs
0.9238
🌋 Hot Springs
0.9236
🌋 Hot Springs
0.9233
🌋 Hot Springs
0.9233
🌋 Hot Springs
0.9233
🌋 Hot Springs
0.9232
📚 Understanding the metrics