Alexis Molina

This paper introduces a decomposition framework for perturbation response prediction, showing that aligning models with biological priors improves generalization across unseen perturbations and cell lines.

PickPocket identifies ligand-binding residues across proteomes using evolutionary and geometric data, finding unannotated sites and improving drug discovery.

This study combines AI/physics-based computation and phage display to design high-affinity Affilin(R) proteins targeting HER3, achieving successful theranostic candidates with high affinity and stability.

This paper introduces a small-scale protein language model that achieves comparable performance to larger models with significantly reduced computational requirements.

RADI improves the computational efficiency of direct-coupling analysis by reducing the alphabet size, achieving faster execution with comparable or better accuracy than traditional methods.