Lys Sanz Moreta

This study reconstructs a time-calibrated hummingbird phylogeny, finding stepwise diversification in the Andes rather than a monophyletic Andean clade.

AptaBERT predicts aptamer binding interactions with proteins and small molecules, achieving high ROC-AUC scores and outperforming existing models.

Dromi is a Python package that computes similarity measures among vector-encoded sequences, including positional weights, for use in sequence machine learning tasks.

BIFROST generates high-quality protein structure fragments using a Deep Markov Model, faster and with less input than current methods.

LYS scripts automate the mapping of positively selected sites from PAML analysis onto protein structures and generate publication-quality visualizations.

This paper introduces THESEUS-PP, a probabilistic programming approach for protein structure superposition that uses Bayesian models to account for correlated atom positions and heteroscedasticity.