BigHat’s design platform, ‘Milliner’, integrates a high-speed characterization with machine learning technologies to engineer antibodies with more complex functions and better biophysical properties: an approach that could help reduce the difficulty of optimizing antibodies and other therapeutic proteins.
Merck, known as MSD outside the US and Canada, says the agreement with BigHat will help it expand its strategy of applying artificial intelligence and machine learning across drug discovery.
Searching for better antibodies
While next-generation antibody therapies promise improved safety and efficacy; developing such advanced molecules with conventional techniques can be difficult, costly, and slow. BigHat believes its AI-enabled antibody design platform offers the essential technologies to quickly and reliably create these breakthrough therapies.
Founded in 2019, BigHat believes its tech can lead to the design of safer, more effective antibody therapies via its use of machine learning and synthetic biology. It integrates a wet lab for high-speed characterization with machine learning technologies to guide the search for better antibodies.
The San Francisco biotech has a broad pipeline of wholly-owned and partnered therapeutic programs spanning indications such as cancer, inflammation, and infectious disease; and has raised over $100m from investors.
Under the collaboration, BigHat and Merck will collaborate to optimize up to three proteins by leveraging BigHat’s platform to synthesize, express, purify, and characterize molecules.
The agreement with Merck brings BigHat a ‘major step closer’ to its goal of three to five collaborations with leading biopharma companies, complementing an internal therapeutic pipeline. In January, BigHat completed the first stage of an undisclosed research collaboration and licensing agreement with Amgen: which it welcomed as validating the capabilities of its platform.
