LabGenius, a London-based company, is revolutionizing the production of medical antibodies with a unique, AI-powered approach. Using machine learning algorithms and robotics, the company aims to automate the antibody discovery process, thus speeding up the traditionally slow process of antibody design.
Revolutionizing antibody discovery with AI
Previously a biscuit factory, LabGenius's South London facility now houses robotic arms, incubators, and DNA sequencing machines instead of mixers and ovens. Here, the company is developing an innovative approach to medical antibody engineering, powered by artificial intelligence. The firm uses machine learning algorithms to design antibodies that target specific diseases, while automated robotic systems build and grow these antibodies in the lab. The process requires minimal human supervision and significantly speeds up the traditionally slow and complex process of antibody design.
Human scientists typically start by identifying potential antibodies for a particular disease. With the infinite possible antibodies, this can be a tedious and time-consuming task. To address this, LabGenius has developed a machine learning model that can explore this vast space much quicker and more efficiently. The model starts with more than 700 initial options from a search space of 100,000 potential antibodies and automatically designs, builds, and tests them. This system significantly speeds up the search process and increases the chances of finding effective antibodies.
Finding unexpected solutions faster
Traditional protein engineering often involves small tweaks to a molecule that works a little bit, potentially ignoring better options elsewhere. LabGenius's machine learning approach, however, can yield unexpected antibody designs that humans may not have considered. Plus, it finds these solutions more quickly - taking just six weeks from setting up a problem to finishing the first batch. This approach challenges the conventional rules of thumb in protein engineering and opens up new possibilities in antibody design.
Potential for more effective treatments
According to James Field, founder and CEO of LabGenius, the company's automated approach could produce antibody treatments that are more effective or have fewer side effects than existing ones. The counterintuitive antibodies found using this approach are often distinct from those a human would design, potentially leading to better outcomes for patients. The company has already raised $28 million and is beginning to partner with pharmaceutical companies, offering its AI-powered services like a consultancy.