Google DeepMind AlphaGenome Atlas
In brief
Google DeepMind's AlphaGenome Atlas is a massive dataset predicting the outcomes of all 9 billion single-letter DNA changes 1, helping researchers prioritize disease variants using the AVI score 1.
Who can use it
Researchers and scientists can access AlphaGenome Atlas to evaluate genetic variants and accelerate research that helps diagnose rare disorders 1.
Does this affect you?
- DevelopersSoftware developers are not the primary users, though the model architecture and dataset are built for computational biology applications 1.
- Product managersProduct managers outside of specialized biotech or healthcare technology will find limited direct application in standard software roadmaps.
- FoundersFounders in biotech and pharmaceutical startups can leverage the dataset to speed up drug discovery pipelines and therapeutic targets 1.
- Everyday usersEveryday users do not use the tool directly, though it supports future improvements in personalized medicine and disease diagnosis 1.
How to start
Google DeepMind launched AlphaGenome in June 2025 and AlphaGenome Atlas in September, but did not publish official technical setup steps 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.