Antonio de la Vega de León

This study evaluates if pre-training chemical language models on large compound datasets improves compound representation, finding that standard masked language modeling is insufficient.

This paper improves the assessment of deep learning models for drug-target interaction prediction by addressing dataset biases and proposing a more accurate evaluation framework.

The paper identifies 68 compounds that reduce versican b expression in zebrafish adgrg6 mutants and 41 that restore myelin basic protein gene expression, with 19 candidates potentially interacting directly with Adgrg6.