BioMap has entered a strategic collaboration with Sanofi to co-develop AI modules for biotherapeutic drug discovery, leveraging BioMap’s AI platform.
Traditional AI methods require vast amounts of labeled data to make accurate predictions. However, in life science, labeled data are often in short supply. BioMap’s foundational models enable one large model, trained on ubiquitous unlabeled data, to inform multiple downstream task models. This approach enables superior prediction from limited data in a range of therapeutic areas, including immunology, neurology, oncology, and rare diseases.
Leveraging BioMap’s custom-built foundational models and AI knowledge, as well as Sanofi’s proprietary data, computational innovations in protein engineering, and biologics development experience, both parties aim to create advanced AI models and protein Large Language Models that will enable biologics design and multiparametric optimisation.
BioMap’s Chief Technology Officer, Le Song, said: “We have built what is essentially a biological map of proteins using data sets from public and private sources to inform our foundational models. Utilising automation and integrated workflows to enhance the collection of high-quality data, we can catalyse the process of new hit discovery and lead optimisation.”
“By combining Sanofi’s proprietary data sets, digital infrastructure, AI and data science capabilities, and drug development expertise with BioMap’s protein Large Language Models, high-performance computing, and deep understanding of AI, we can optimise the process of discovery and development of breakthrough biotherapeutics,” said Matt Truppo, Global Head of Research Platforms at Sanofi. “Our collaboration with BioMap further underscores Sanofi’s commitment to becoming the first pharma company powered by AI at scale.”