🔬 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
0.9633
🌋 Hot Springs
0.9632
🌋 Hot Springs
0.9632
🧊 Permafrost
0.9631
🧊 Permafrost
0.9631
🌋 Hot Springs
0.9630
🌋 Hot Springs
0.9630
🌋 Hot Springs
0.9630
🌋 Hot Springs
0.9630
🌋 Hot Springs
0.9630
🌋 Hot Springs
0.9629
🌋 Hot Springs
0.9628
🌋 Hot Springs
0.9628
🌋 Hot Springs
0.9627
🌋 Hot Springs
0.9627
🧊 Permafrost
0.9626
🧊 Permafrost
0.9626
🌋 Hot Springs
0.9626
🧊 Permafrost
0.9626
🌋 Hot Springs
0.9625
🌋 Hot Springs
0.9624
🧊 Permafrost
0.9624
🌋 Hot Springs
0.9623
🌋 Hot Springs
0.9623
📚 Understanding the metrics