Jorge Soria‐Bustos

This paper demonstrates a personalized SNAP-TIL therapy platform that improves TIL efficacy by enriching them with neoantigen-reactive T-cells, achieving high CD3+ cell content and significant tumor growth inhibition in preclinical models.

The paper introduces MHCIIFold-GNN, a method combining structural modeling and graph neural networks to predict CD4 T cell epitopes, achieving state-of-the-art performance.

The paper introduces CRESTA, a method to analyze CD4 T cell epitope specificities and phenotypes, revealing diverse responses to Mycobacterium tuberculosis.

The paper shows that Lrp activates aroX and npsA genes involved in tilivalline biosynthesis in K. oxytoca, reducing cytotoxicity in its absence.