🔬 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
0.9134
🌋 Hot Springs
0.9132
🌋 Hot Springs
0.9131
🌋 Hot Springs
0.9130
🌋 Hot Springs
0.9129
🧊 Permafrost
0.9128
🌋 Hot Springs
0.9127
🌋 Hot Springs
0.9127
🧊 Permafrost
0.9127
🧊 Permafrost
0.9126
🌋 Hot Springs
0.9124
🌋 Hot Springs
0.9121
🌋 Hot Springs
0.9120
🌋 Hot Springs
0.9120
🌋 Hot Springs
0.9120
🌋 Hot Springs
0.9119
🌋 Hot Springs
0.9119
🧊 Permafrost
0.9119
🌋 Hot Springs
0.9118
🌋 Hot Springs
0.9116
🧊 Permafrost
0.9116
🧊 Permafrost
0.9116
🧊 Permafrost
0.9115
🌋 Hot Springs
0.9114
📚 Understanding the metrics