Genome

YouTube ... Quora ...Google search ...Google News ...Bing News

• Life Sciences ... Evolutionary ... Bioinformatics ... Proteins ... AlphaGenome ... Genealogy ... Pharmaceuticals ... Drug Discovery
• Symbiotic Intelligence ... Bio-inspired Computing ... Neuroscience ... Connecting Brains ... Nanobots ... Molecular ... Neuromorphic
• Case Studies
  • Healthcare

AlphaGenome Atlas

• AlphaGenome Atlas

AlphaGenome Atlas is a massive 1-petabyte dataset, more than 30 times larger than the AlphaFold Database. When we expanded the AlphaFold Database in 2022, we grew the 3D structure information available from around 190K experimental structures to more than 200M structure predictions — covering nearly all catalogued proteins known to science. The database provided a portal that researchers with no coding experience could use, providing intuitive visualizations and making it easier to do large-scale protein structure analysis. It quickly became a crucial resource that drove discoveries across the life sciences and continues to accelerate researchers’ important work in countless fields.

This video features Google DeepMind researchers Natasha Latysheva and Kyle Taylor demonstrating the AlphaGenome Atlas skill within the Google Antigravity platform. This tool is designed to help researchers efficiently analyze and prioritize genomic variants (0:00-0:39).

Key Workflow Demonstrated:

Variant Fetching: The researchers use the agent to retrieve a list of variants within the HBB gene, specifically looking at intron 2 (0:56-1:16). Prioritization: The agent utilizes AVI (AlphaGenome Variant Impact) scores to rank variants based on their predicted molecular impact, allowing researchers to quickly identify high-interest hits (1:16-1:31).

Cross-referencing: The agent automates the process of adding ClinVar annotations to the variant list, helping to identify known pathogenic variants versus new, uncharacterized ones (1:51-2:03). Molecular Interpretation: Researchers can visualize structural ref/alt plots directly in the chat. This feature allows them to generate testable hypotheses—such as predicting if a specific variant leads to a new pseudo-exon inclusion—without requiring manual coding (2:18-2:44). By moving from high-level exploration to a prioritized biological hypothesis in just a few minutes, the AlphaGenome Atlas skill significantly streamlines genomic research (3:03-3:11).