Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes
Genomic foundation models such as Evo 2 learn rich sequence representations, but their value for biosecurity screening is largely unexplored. We ask how much biosecurity-relevant signal is linearly accessible in these representations by training minimal linear and attention probes on frozen Evo 2 layer-26 activations, without fine-tuning the underlying model. Across held-out metagenomic test sets, the probes detect antimicrobial resistance (AMR) with strong discrimination: a linear probe reaches a region-level ROC-AUC of 0.888 (mean-pool), rising to 0.977 with a single-head attention probe. Th
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 53%Data-driven surrogates of rational design enable antimicrobial peptide optimization →
- PossiblePossibly related (embedding) · 51%Scientists Use Machine Learning to Uncover Antibiotic Peptides Buried Inside Prion Proteins - IFLScience →
- PossiblePossibly related (embedding) · 48%Efficient evidence-based genome annotation with EviAnn - Nature →
- LinkedLinked via arxiv author · 85%Jeremy Guntoro →
“Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes”
- LinkedLinked via arxiv author · 85%Alexander Dack →
“Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes”
- LinkedLinked via arxiv author · 85%Dylan Danno →
“Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes”
- LinkedLinked via arxiv author · 85%Michaela Jančovičová →
“Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes”
- LinkedLinked via arxiv author · 85%Križan Jurinović →
“Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes”