🔬 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
0.9426
🌋 Hot Springs
0.9425
🧊 Permafrost
0.9424
🧊 Permafrost
0.9424
🧊 Permafrost
0.9424
🌋 Hot Springs
0.9423
🌋 Hot Springs
0.9420
🌋 Hot Springs
0.9420
🌋 Hot Springs
0.9420
🌋 Hot Springs
0.9420
🌋 Hot Springs
0.9419
🌋 Hot Springs
0.9419
🌋 Hot Springs
0.9418
🌋 Hot Springs
0.9418
🌋 Hot Springs
0.9417
🌋 Hot Springs
0.9417
🧊 Permafrost
0.9417
🌋 Hot Springs
0.9416
🌋 Hot Springs
0.9415
🌋 Hot Springs
0.9415
🌋 Hot Springs
0.9415
🧊 Permafrost
0.9415
🌋 Hot Springs
0.9415
🌋 Hot Springs
0.9414
📚 Understanding the metrics