Javier Arsuaga

Bacteriophage host prediction using a genome language model

This paper evaluates a genome language model for predicting bacteriophage hosts using embeddings, finding it effective for narrowing host candidates and capturing broad evolutionary relationships when combined with existing methods.

PURPL is associated with adverse clinical outcome in Luminal A breast cancer

The paper identifies PURPL as a long non-coding RNA associated with poor clinical outcomes in Luminal A breast cancer through copy number, expression, and survival analyses across multiple cohorts.

Scratch-AID: A Deep-learning Based System for Automatic Detection of Mouse Scratching Behavior with High Accuracy

Scratch-AID automatically detects and quantifies mouse scratching behavior with high accuracy, outperforming manual methods in various itch models and drug screening applications.