🔬 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
0.8918
🌋 Hot Springs
0.8918
🧊 Permafrost
0.8917
🧊 Permafrost
0.8917
🌋 Hot Springs
0.8915
🌋 Hot Springs
0.8915
🌋 Hot Springs
0.8914
🌋 Hot Springs
0.8914
🌋 Hot Springs
0.8912
🧊 Permafrost
0.8912
🧊 Permafrost
0.8911
🌋 Hot Springs
0.8911
🌋 Hot Springs
0.8910
🌋 Hot Springs
0.8910
🧊 Permafrost
0.8910
🌋 Hot Springs
0.8910
🌋 Hot Springs
0.8909
🌋 Hot Springs
0.8908
🌋 Hot Springs
0.8907
🌋 Hot Springs
0.8906
🌋 Hot Springs
0.8906
🌋 Hot Springs
0.8906
🌋 Hot Springs
0.8905
🌋 Hot Springs
0.8905
📚 Understanding the metrics