🔬 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
0.9146
🧊 Permafrost
0.9146
🌋 Hot Springs
0.9146
🌋 Hot Springs
0.9145
🌋 Hot Springs
0.9145
🌋 Hot Springs
0.9145
🧊 Permafrost
0.9144
🌋 Hot Springs
0.9144
🌋 Hot Springs
0.9143
🧊 Permafrost
0.9142
🌋 Hot Springs
0.9141
🌋 Hot Springs
0.9141
🌋 Hot Springs
0.9140
🧊 Permafrost
0.9140
🧊 Permafrost
0.9140
🌋 Hot Springs
0.9140
🌋 Hot Springs
0.9138
🧊 Permafrost
0.9138
🧊 Permafrost
0.9137
🧊 Permafrost
0.9137
🌋 Hot Springs
0.9136
🌋 Hot Springs
0.9136
🌋 Hot Springs
0.9135
🌋 Hot Springs
0.9135
📚 Understanding the metrics