Google DeepMind adds Cheminformatics Skills to Antigravity

Google DeepMind introduced a suite of Cheminformatics Skills for Google Antigravity, turning the agent surface into a workbench for drug discovery tasks. The skills pair a language model that handles workflow orchestration and scientific reasoning with deterministic chemistry tools built on RDKit, plus connectors to ChEMBL and PubChem, so an agent can extract molecules from literature and catalogs and reconcile different structure formats.

In a published walkthrough, the agent worked from crizotinib and lorlatinib analogues: it gathered thousands of compounds, filtered out solvents and buffers, ran matched molecular pair analysis, trained potency models, and proposed rigidified macrocycles with synthesis routes, a cycle the team says took about an hour. Results export to standard chemistry software. The authors note designs are testable hypotheses, limited by sparse data and assay noise.