Google Unveils New AI Models for Drug Discovery

# Google # txgemma

At a health-focused event in New York on Tuesday, Google unveiled its latest project, TxGemma, a set of "open" AI models aimed at revolutionizing drug discovery. These models, set to be released through Google's Health AI Developer Foundations program later this month, are designed to process both standard text and the intricate structures of various therapeutic entities such as chemicals, molecules, and proteins. Karen DeSalvo, Google's chief health officer, emphasized the potential impact of TxGemma in a blog post shared with TechCrunch. She noted, "The development of therapeutic drugs from concept to approved use is a long and expensive process, so we're working with the wider research community to find new ways to make this development more efficient." Researchers can leverage TxGemma to predict crucial properties of potential new therapies, such as their safety and effectiveness. However, Google has not yet clarified whether the licensing for these models will permit commercial use, customization, or fine-tuning. TechCrunch has reached out for further details and will update the story if Google responds. The promise of AI transforming drug discovery is not new. Numerous companies, including Google's own spin-out Isomorphic Labs, have touted AI's potential to speed up the initial stages of research and development. Despite some successes, AI has yet to deliver a complete solution in the lab. High-profile clinical trial failures have plagued companies like Exscientia and BenevolentAI in recent years, and the accuracy of leading AI systems like Google DeepMind's AlphaFold 3 can be inconsistent. Despite these challenges, both big pharma and investors remain optimistic about AI's future in drug discovery. Isomorphic Labs, with its partnerships with Eli Lilly and Novartis, anticipates beginning testing on its AI-designed drugs this year. The sector is bustling with activity, with over 460 AI startups focused on drug discovery and investors having committed around $60 billion to the field so far.

Related article

Comments (32)