🔬 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
0.9519
🌋 Hot Springs
0.9519
🌋 Hot Springs
0.9519
🌋 Hot Springs
0.9519
🌋 Hot Springs
0.9518
🌋 Hot Springs
0.9518
🌋 Hot Springs
0.9517
🧊 Permafrost
0.9516
🧊 Permafrost
0.9515
🧊 Permafrost
0.9515
🧊 Permafrost
0.9515
🌋 Hot Springs
0.9514
🌋 Hot Springs
0.9514
🌋 Hot Springs
0.9514
🧊 Permafrost
0.9513
🌋 Hot Springs
0.9513
🌋 Hot Springs
0.9512
🌋 Hot Springs
0.9511
🧊 Permafrost
0.9510
🌋 Hot Springs
0.9509
🧊 Permafrost
0.9508
🌋 Hot Springs
0.9508
🌋 Hot Springs
0.9507
🌋 Hot Springs
0.9507
📚 Understanding the metrics