🔬 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
0.9684
🌋 Hot Springs
0.9682
🌋 Hot Springs
0.9681
🌋 Hot Springs
0.9680
🧊 Permafrost
0.9680
🧊 Permafrost
0.9680
🌋 Hot Springs
0.9680
🌋 Hot Springs
0.9680
🌋 Hot Springs
0.9679
🌋 Hot Springs
0.9678
🧊 Permafrost
0.9678
🌋 Hot Springs
0.9678
🧊 Permafrost
0.9677
🧊 Permafrost
0.9677
🌋 Hot Springs
0.9677
🧊 Permafrost
0.9677
🧊 Permafrost
0.9677
🌋 Hot Springs
0.9676
🌋 Hot Springs
0.9675
🌋 Hot Springs
0.9673
🌋 Hot Springs
0.9673
🌋 Hot Springs
0.9672
🌋 Hot Springs
0.9672
🧊 Permafrost
0.9671
📚 Understanding the metrics