🔬 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
0.8980
🌋 Hot Springs
0.8979
🧊 Permafrost
0.8978
🌋 Hot Springs
0.8978
🌋 Hot Springs
0.8976
🌋 Hot Springs
0.8976
🌋 Hot Springs
0.8976
🌋 Hot Springs
0.8975
🧊 Permafrost
0.8974
🧊 Permafrost
0.8974
🌋 Hot Springs
0.8973
🌋 Hot Springs
0.8972
🌋 Hot Springs
0.8972
🧊 Permafrost
0.8972
🌋 Hot Springs
0.8971
🌋 Hot Springs
0.8971
🌋 Hot Springs
0.8971
🧊 Permafrost
0.8970
🌋 Hot Springs
0.8967
🌋 Hot Springs
0.8966
🌋 Hot Springs
0.8966
🧊 Permafrost
0.8966
🌋 Hot Springs
0.8966
🌋 Hot Springs
0.8964
📚 Understanding the metrics