AlphaGenome by Google DeepMind
In brief
AlphaGenome is a model from Google DeepMind that takes a partial DNA sequence of 1 million base pairs to make thousands of predictions 1. It helps researchers decode the genome and understand disease mechanisms 1.
Who can use it
AlphaGenome was launched in June 2025, followed by AlphaGenome Atlas in September and AlphaGenome 2 recently, though public setup instructions are not provided in the source text 1.
Does this affect you?
- DevelopersGenomics developers can utilize model architectures and datasets to build advanced computational biology applications 1.
- Product managersProduct managers in health tech can explore how variant impact scores accelerate clinical research and diagnostic workflows 1.
- FoundersFounders of biotech startups can leverage predictive genomics datasets to speed up drug discovery pipelines 1.
- Everyday usersEveryday users benefit indirectly through accelerated research into rare diseases and personalized medicine 1.
How to start
Google DeepMind has not published official step-by-step setup instructions or installation guides for AlphaGenome in the source text 1.
What you can build
Before you rely on it
Quick check
3 questionsAvailability
Sources
1 merged into this cardMore from Google

Tool Retrieval in the Gemini API
Gemini's Interactions API now supports on-demand loading of tool parameter schemas. Agents with large tool libraries can keep schemas out of context until needed, cutting input tokens, latency, and selection errors.

Computer use in Gemini app for Mac
Google added computer use to the Gemini app for Mac, letting Gemini automate multi-step tasks across local files, desktop apps, and the web in an isolated background window.