Google Antigravity Cheminformatics Skills Cut Drug Discovery Time
Google Antigravity introduces Cheminformatics Skills that reduce drug discovery iteration time from days to an hour.
Google Antigravity now includes new Cheminformatics Skills designed to accelerate drug discovery workflows. These capabilities reduce iteration time from multiple days to just an hour. The skills are grounded in RDKit, ChEMBL, and PubChem resources. They allow an agent to extract molecules from literature documents and associate them with reported data. Additionally, agents can build predictive models using molecular machine learning capabilities, with guidance on feature sets and model architectures.
The workflow demonstrated previously required significant computational expertise and took multiple days. Google Antigravity allows researchers to export results in various formats ready for industry standard chemistry software packages. Proposed designs generated by the system must be synthesized and validated experimentally, as they are testable hypotheses rather than finished drugs.
Google offered 10,000 scientists the highest usage tier free of charge for six months starting from the article's publication date. A team including Filip Radlinski, Artem Sobolev, Victoria Johnston, Hannah Kiely-Collins, Zachary Wu, Jue Wang, Jack Dunger, Adriana Fernandez Lara, Ngân Vũ, Doug Fritz, Yunhan Xu, Sebastian Nowozin, and Pushmeet Kohli contributed to the project.
Sources
Every sentence of this story was checked against facts quoted from these articles. How we make the news
Spotted an error? Tell us
