Victoria Ruiz‐Serra

This paper evaluates Evo 2's in-context learning capabilities on genomic sequences, finding strong performance on short sequences but degradation with length, and no benefit from model scaling.

This study introduces CM2.0, a coevolution-based method to predict species-specific PPIs, revealing conserved and species-specific interactions in E. coli, S. enterica, and S. aureus.

3Dmapper maps annotated protein positions and variants to protein structures efficiently and reliably for large-scale genomic data analysis.

FrustraEvo calculates and quantifies the conservation of local energetic frustration in protein families to identify evolutionary stability and functional constraints.

The paper analyzes local energetic frustration in protein families to uncover stability and function constraints, demonstrating its application to SARS-CoV-2 and poorly characterized proteins.

This study quantifies how AlphaFold's structural models increase human proteome coverage from 48% to 76% and reduce the dark proteome from 26% to 10%.

This study identifies specificity determining positions in SARS-CoV-2 and other β-CoVs spike proteins that encode host receptor usage through sequence and structural analysis.