Vibeleaderboard
← All Intel
Intel / post

DeepMind's AlphaGenome Atlas already finding disease-causing DNA variants

Source
x.com
Date
GoogleDeepMind@GoogleDeepMind
Thread · 5 parts

Researchers at @BroadInstitute, @UniofExeter, and beyond are already using AlphaGenome Atlas to better identify potential disease-causing DNA variants and interpret their role. 🧵

Scientists at @BroadInstitute search for the underlying causes of unexplained rare disease cases, but the list of possible mutations is vast. Using Atlas, researchers pinpointed a critical mutation in the DNM1 gene, which was confirmed and validated in the lab.

A pipette tip dips into clear liquid within a petri dish. Colorful DNA bands are visible below the surface in the background.

In collaboration with the @UniofExeter, researchers used AlphaGenome Atlas to analyze data from 54,000+ @uk_biobank participants. They found: 📈 A 22%+ boost in detecting rare genetic signals 🎯 It uncovered new DNA variants influencing the abundance of PLA2G7, a protein linked to metabolic health.

Top-down view of a laboratory centrifuge rotor with numbered sample slots.

Every second, millions of genome switches dictate how our cells function and adapt. 🧬 Working with @ScienceStowers, Atlas mapped 2,500+ regulatory patterns uncovering the DNA sequences that act as biological switches and volume dials to turn gene activity up or down across hundreds of cell types.

Fluorescent microscope view of numerous blue cell nuclei scattered against a black background.
Read the full thread on X

Context

Google DeepMind released AlphaGenome Atlas, a database it first introduced earlier this month that precomputes the predicted regulatory effect of nearly every possible single-letter change across the human genome. In a follow-up thread, DeepMind reports early external uses: researchers at the Broad Institute used Atlas to narrow down candidate mutations behind an unexplained rare disease case, then confirmed and validated in lab experiments a specific mutation in the DNM1 gene. Working with the University of Exeter on genetic data from more than 54,000 UK Biobank participants, researchers using Atlas found a reported 22%-plus increase in detecting rare genetic signals and identified new DNA variants linked to the abundance of PLA2G7, a protein connected to metabolic health. These are DeepMind's own accounts of external collaborators' findings, not independently published, peer-reviewed papers reviewed here, so the exact magnitude of the reported improvements is not independently verified.

More from GoogleDeepMind
Recommended reads
Comments

Checking sign-in…

Loading comments…