🔬 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
0.9541
🌋 Hot Springs
0.9541
🌋 Hot Springs
0.9540
🧊 Permafrost
0.9540
🧊 Permafrost
0.9540
🌋 Hot Springs
0.9540
🌋 Hot Springs
0.9539
🌋 Hot Springs
0.9539
🌋 Hot Springs
0.9538
🌋 Hot Springs
0.9538
🌋 Hot Springs
0.9537
🌋 Hot Springs
0.9536
🌋 Hot Springs
0.9535
🌋 Hot Springs
0.9535
🌋 Hot Springs
0.9534
🌋 Hot Springs
0.9534
🌋 Hot Springs
0.9534
🌋 Hot Springs
0.9532
🌋 Hot Springs
0.9532
🌋 Hot Springs
0.9531
🧊 Permafrost
0.9530
🌋 Hot Springs
0.9530
🌋 Hot Springs
0.9530
🧊 Permafrost
0.9530
📚 Understanding the metrics