🔬 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
0.9734
🌋 Hot Springs
0.9734
🧊 Permafrost
0.9734
🌋 Hot Springs
0.9733
🌋 Hot Springs
0.9733
🌋 Hot Springs
0.9733
🌋 Hot Springs
0.9733
🌋 Hot Springs
0.9733
🌋 Hot Springs
0.9732
🌋 Hot Springs
0.9732
🌋 Hot Springs
0.9731
🌋 Hot Springs
0.9731
🌋 Hot Springs
0.9731
🌋 Hot Springs
0.9729
🌋 Hot Springs
0.9729
🌋 Hot Springs
0.9729
🌋 Hot Springs
0.9728
🌋 Hot Springs
0.9726
🌋 Hot Springs
0.9726
🧊 Permafrost
0.9725
🧊 Permafrost
0.9725
🧊 Permafrost
0.9724
🌋 Hot Springs
0.9724
🧊 Permafrost
0.9724
📚 Understanding the metrics