🔬 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
0.9090
🌋 Hot Springs
0.9089
🌋 Hot Springs
0.9087
🧊 Permafrost
0.9087
🌋 Hot Springs
0.9086
🌋 Hot Springs
0.9086
🧊 Permafrost
0.9084
🧊 Permafrost
0.9083
🧊 Permafrost
0.9083
🌋 Hot Springs
0.9083
🌋 Hot Springs
0.9081
🌋 Hot Springs
0.9080
🌋 Hot Springs
0.9080
🧊 Permafrost
0.9080
🌋 Hot Springs
0.9080
🌋 Hot Springs
0.9080
🌋 Hot Springs
0.9079
🌋 Hot Springs
0.9078
🌋 Hot Springs
0.9078
🧊 Permafrost
0.9077
🌋 Hot Springs
0.9076
🌋 Hot Springs
0.9076
🧊 Permafrost
0.9076
🧊 Permafrost
0.9076
📚 Understanding the metrics