🔬 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
0.9506
🌋 Hot Springs
0.9505
🌋 Hot Springs
0.9504
🧊 Permafrost
0.9504
🧊 Permafrost
0.9504
🧊 Permafrost
0.9504
🧊 Permafrost
0.9502
🌋 Hot Springs
0.9500
🧊 Permafrost
0.9500
🌋 Hot Springs
0.9500
🌋 Hot Springs
0.9500
🌋 Hot Springs
0.9500
🌋 Hot Springs
0.9498
🌋 Hot Springs
0.9498
🌋 Hot Springs
0.9498
🌋 Hot Springs
0.9497
🌋 Hot Springs
0.9496
🌋 Hot Springs
0.9496
🧊 Permafrost
0.9495
🧊 Permafrost
0.9495
🌋 Hot Springs
0.9495
🌋 Hot Springs
0.9495
🌋 Hot Springs
0.9495
🌋 Hot Springs
0.9494
📚 Understanding the metrics