🔬 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
0.8862
🌋 Hot Springs
0.8862
🌋 Hot Springs
0.8862
🌋 Hot Springs
0.8862
🧊 Permafrost
0.8861
🌋 Hot Springs
0.8860
🌋 Hot Springs
0.8860
🧊 Permafrost
0.8859
🧊 Permafrost
0.8859
🌋 Hot Springs
0.8857
🌋 Hot Springs
0.8857
🌋 Hot Springs
0.8856
🧊 Permafrost
0.8855
🌋 Hot Springs
0.8855
🌋 Hot Springs
0.8855
🌋 Hot Springs
0.8854
🧊 Permafrost
0.8853
🌋 Hot Springs
0.8850
🌋 Hot Springs
0.8849
🌋 Hot Springs
0.8849
🌋 Hot Springs
0.8849
🧊 Permafrost
0.8847
🧊 Permafrost
0.8846
🌋 Hot Springs
0.8845
📚 Understanding the metrics