🔬 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
0.9387
🧊 Permafrost
0.9387
🌋 Hot Springs
0.9387
🌋 Hot Springs
0.9387
🌋 Hot Springs
0.9386
🌋 Hot Springs
0.9386
🧊 Permafrost
0.9386
🌋 Hot Springs
0.9385
🌋 Hot Springs
0.9385
🌋 Hot Springs
0.9385
🌋 Hot Springs
0.9384
🌋 Hot Springs
0.9384
🌋 Hot Springs
0.9384
🌋 Hot Springs
0.9380
🧊 Permafrost
0.9380
🌋 Hot Springs
0.9379
🌋 Hot Springs
0.9379
🌋 Hot Springs
0.9378
🌋 Hot Springs
0.9377
🌋 Hot Springs
0.9377
🧊 Permafrost
0.9376
🌋 Hot Springs
0.9374
🌋 Hot Springs
0.9373
🧊 Permafrost
0.9372
📚 Understanding the metrics