Agentic cheminformatics with Google Antigravity
Google DeepMind presents Cheminformatics Skills for Google Antigravity to speed up drug discovery workflows. An agent can search compounds and propose novel rigidified macrocycles.
What the article says
The skills are built on the open-source toolkit RDKit and connected to ChEMBL and PubChem. They let an AI agent retrieve and curate compound data from the literature, run matched molecular pair analysis and build potency prediction models. In a demo using the lung cancer drugs crizotinib and lorlatinib, the agent searched thousands of compounds, produced a curated set of 568, and proposed novel rigidified macrocycles with synthesis routes in about an hour.
The authors stress that computational designs are “testable hypotheses, not finished drugs” and require experimental validation. The skills are available through the Antigravity app’s Science plugin. DeepMind is also offering 10,000 scientists the highest usage tier free for six months, subject to eligibility and selection.
Read the official article AnnuIA profile
Summary written by AnnuIA in its own words from the official page of Google DeepMind. The content and rights belong to the publisher: please read the original article.