Scientists at Baylor College of Medicine have used artificial intelligence and high-throughput proteomics to discover a new class of molecular glues that neutralise a protein linked to blood cancers and autoimmune diseases.

The study, led by Dr. Jin Wang and published in Nature Communications in 2026, targets a protein called VAV1, an important regulator of immune cell function.

Molecular glues work like matchmakers inside cells: they bring a harmful protein into contact with the cell's natural disposal machinery, which then destroys the target.

Instead of blocking a protein's function, the strategy eliminates it entirely, which researchers say could produce a more complete therapeutic effect.

The team screened a library of molecules using high-throughput proteomics, a technology that can assess thousands of proteins at once. The analysis revealed compounds including NGT-201-12 that caused VAV1 levels to drop while affecting relatively few other proteins.

They then built GluePlex, a computational workflow combining AI-based protein-structure prediction with physics-based modelling, to optimise the compounds without needing an experimental structure of the complex.

Follow-up studies showed the degradation depended on the proteasome and cereblon, a component of the cell's protein-degradation pathway.

The work shows how AI structural modelling can guide chemists early in drug design.