Merck and Protillion Target Antibody Discovery with $510M Milestone Deal

Merck & Co. is integrating "lab-in-the-loop" automation into its drug discovery pipeline through a new partnership with Protillion Biosciences. The collaboration, which includes a multi-target discovery and license agreement, could generate up to $510 million in milestone payments for the AI-based design company.

The deal centers on Protillion’s Prot-MaP™ platform, a technology designed to facilitate AI-based optimization of therapeutic antibodies. By combining Merck’s global expertise in therapeutics with this on-chip discovery platform, the partnership aims to identify optimized biologics with complex profiles, such as multi-target specificity and pH-dependent sweeping. These specific therapeutic profiles remain difficult to achieve using traditional methods.

The technical advantage lies in how Protillion handles data. The Prot-MaP platform uses a continuous feedback loop of experimental wet-lab data to drive AI optimization. It enables the generation of tens of millions of clusters of immobilized proteins directly on an Illumina DNA sequencing flow cell through efficient tethered in situ transcription and translation. This process allows for the quantitative analysis of protein libraries, characterizing millions of variants per run while avoiding model overfitting.

This move signals a shift in how large-cap pharmaceutical companies are approaching the "wet-lab" bottleneck. Protillion, which was organized in 2019, is moving beyond pure software AI to provide the massive, just-in-time quantitative antibody binding datasets required for protein design AI. The platform's ability to generate megascale datasets directly on sequencing flow cells addresses a fundamental requirement for training reliable biological models.

For Merck, the strategy is clear: reduce the uncertainty of antibody engineering by utilizing a platform that bridges the gap between computational prediction and physical validation. For Protillion, this agreement validates a business model where high-throughput biochemical interrogation serves as the essential fuel for the next generation of protein design.

The industry should watch whether this "lab-in-the-loop" architecture becomes the standard requirement for any AI-driven biotech seeking large-scale pharmaceutical partnerships.