🔬 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
0.8818
🌋 Hot Springs
0.8818
🧊 Permafrost
0.8816
🌋 Hot Springs
0.8815
🌋 Hot Springs
0.8815
🌋 Hot Springs
0.8814
🌋 Hot Springs
0.8813
🌋 Hot Springs
0.8813
🌋 Hot Springs
0.8813
🧊 Permafrost
0.8812
🌋 Hot Springs
0.8812
🌋 Hot Springs
0.8812
🌋 Hot Springs
0.8810
🌋 Hot Springs
0.8810
🌋 Hot Springs
0.8806
🌋 Hot Springs
0.8806
🌋 Hot Springs
0.8806
🧊 Permafrost
0.8805
🧊 Permafrost
0.8804
🧊 Permafrost
0.8803
🧊 Permafrost
0.8803
🌋 Hot Springs
0.8803
🌋 Hot Springs
0.8802
🌋 Hot Springs
0.8802
📚 Understanding the metrics