🔬 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
0.9604
🌋 Hot Springs
0.9602
🧊 Permafrost
0.9602
🌋 Hot Springs
0.9602
🧊 Permafrost
0.9602
🌋 Hot Springs
0.9602
🌋 Hot Springs
0.9601
🌋 Hot Springs
0.9601
🌋 Hot Springs
0.9601
🌋 Hot Springs
0.9600
🧊 Permafrost
0.9600
🌋 Hot Springs
0.9599
🌋 Hot Springs
0.9599
🌋 Hot Springs
0.9598
🧊 Permafrost
0.9598
🌋 Hot Springs
0.9597
🌋 Hot Springs
0.9595
🧊 Permafrost
0.9595
🧊 Permafrost
0.9595
🧊 Permafrost
0.9595
🌋 Hot Springs
0.9594
🌋 Hot Springs
0.9594
🌋 Hot Springs
0.9594
🌋 Hot Springs
0.9593
📚 Understanding the metrics