🔬 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
0.9413
🧊 Permafrost
0.9413
🧊 Permafrost
0.9411
🌋 Hot Springs
0.9411
🌋 Hot Springs
0.9411
🌋 Hot Springs
0.9411
🌋 Hot Springs
0.9411
🌋 Hot Springs
0.9409
🌋 Hot Springs
0.9408
🧊 Permafrost
0.9407
🧊 Permafrost
0.9407
🌋 Hot Springs
0.9406
🌋 Hot Springs
0.9406
🧊 Permafrost
0.9405
🌋 Hot Springs
0.9405
🌋 Hot Springs
0.9404
🧊 Permafrost
0.9404
🧊 Permafrost
0.9402
🧊 Permafrost
0.9402
🌋 Hot Springs
0.9402
🧊 Permafrost
0.9402
🌋 Hot Springs
0.9401
🌋 Hot Springs
0.9400
🧊 Permafrost
0.9400
📚 Understanding the metrics