Happy to see our AlphaGenome model published in @Nature today and on the cover of this week’s issue. 🧬
AlphaGenome is an AI model for understanding the non-coding genome – the 98% of DNA that's crucial for health and disease but doesn't code for proteins.
AlphaGenome is an AI model for understanding the non-coding genome – the 98% of DNA that's crucial for health and disease but doesn't code for proteins.
Jan 28, 2026 · 4:35 PM UTC
11
30
236
10,283
Since launching the API last summer, 3,000+ researchers across 160 countries have used AlphaGenome to study gene regulation and advance disease research.
Excited to see what the community discovers with the model code and weights now available for non-commercial research.
Excited to see what the community discovers with the model code and weights now available for non-commercial research.
1
1
24
1,154
Read the full announcement: [deepmind.google/blog/alphageno…]
1
2
23
1,074
Access the code and weights: [github.com/google-deepmin…]
1
2
11
1,210
Watch a deep dive from the team behind AlphaGenome: [youtu.be/V8lhUqKqzUc]
1
6
13
1,711
@pushmeet @Nature You can understand this @Nature paper in seconds chat.pageindex.ai/share/chat/cmk…
0
0
1
80
@pushmeet @Nature I'm excited, as always, to see what you've done. But I have to say that you've gone overboard with this: "the 98% of DNA that's crucial for health and disease but doesn't code for proteins." There's evidence only that a small percentage of the non-coding DNA impacts fitness.
0
0
0
82
