Lucía Barbadilla-Martínez

The paper defines an extended translation initiation sequence (eTIS) and shows that a deep-learning model trained on eTIS features accurately predicts translation initiation, revealing that the Kozak sequence is not optimal and identifying conserved nucleotides that enhance initiation efficiency.

This study uses sequence-based deep learning models to identify functional promoter mutations in cancer, finding enrichment in known and novel cancer genes.

This paper introduces PARM, a deep learning model trained on MPRA data to predict human promoter activity and identify TF binding preferences, revealing positional and functional differences in regulatory grammar.