Protein
localization
BioGPU
The cellular biology runtime for AI agents
The cellular biology runtime for AI agents
AI agents experimentally resolve disease mechanisms and use that knowledge to guide the design of better therapeutics.
With The BioGPU, AI agents see how cellular biology works together
Most biological methods measure selected activities in isolation.
Visual Biology reveals hundreds of molecular activities in the same cellular context, showing how they interact and respond together.
Traditional Automated Laboratory
Multiple experimental workflows, potentially different conditions and modalities.
Anima BioGPU
Protein translocation
RNA granules
Cytoskeletal dynamics
Nuclear translocation
Mitochondrial state
↓
↓
Many biological mechanisms investigated together within the same cellular network and conditions.
A foundation model trained to see cellular biology.
Visual Biology Foundation Model
PATHWAY IMAGES
Visual representations of biological reality
-
Nuclear
translocation -
Phospho-
signaling -
Cytoskeletal
dynamics -
RNA
granules -
Mitochondrial
state -
Protein
interactions -
mRNA
localization
FOUNDATIONAL MODEL
Pathway-image-to-text
Trained on 2B+ pathway visualizations across 140 cell types and 25 diseases
TEXTUAL BIOLOGICAL STATEMENTS
Biological facts extracted from images
TDP43 accumulates in the cytoplasm.
mTOR signaling is hyperactivated.
Mitochondrial fragmentation increases.
RNA granule formation is enhanced.
Protein co-localization increases under perturbation X.
Nuclear translocation of TFs is enriched under condition Y.
It recognizes activity patterns across different proteins, phenotypes, and cellular systems, including visual patterns absent from its training examples.
AI-to-cell technology stack powered by a Visual Biology Foundation Model
BioGPU Agent designs experiments, runs them on the BioGPU, and learns from the results.
It resolves how molecular mechanisms interact, how their effects propagate across cellular networks, and how those networks respond to change.
BioGPU Agent
Visual Biology Tokens
-
Protein
localization -
Nuclear
translocation -
Phospho-
signaling -
Cytoskeletal
dynamics -
Mitochondrial
state -
RNA
granules -
Protein
interactions
FOUNDATION VISUAL BIOLOGY MODEL
1000+
Experiments at each iteration
Cells
Millions of cells across diseases,
conditions and perturbations
conditions and perturbations
Teach AI biology it has never seen before
Visual Biology Tokens bring newly discovered cellular activities and their biological meaning into AI.
With every experiment, AI learns more about cellular networks and uses that knowledge to design the next.
With every experiment, AI learns more about cellular networks and uses that knowledge to design the next.
FRONT: THE MEANING
Biological finding
VB-0001
Abnormal NUP62 distribution in both cytoplasm and nucleus reflects misregulated nuclear pore function and nucleocytoplasmic transport defects.
VB-0002
DDX6, SMNDC1, and ELAVL4 are identified as functionally relevant regulators of selection of the distal polyadenylation site in the SOD1 3'UTR.
front
VISUAL BIOLOGY TOKENS
THOUSANDS OF TOKENS
produced per experiment
Across pathways, cell types, conditions and diseases
back
BACK: THE EVIDENCE
Dynamic visual evidence
NUP62
H
D
DDX6,
SMNDC1,
ELAVL4
SMNDC1,
ELAVL4
si-Non-Targeting
si-DDX6
si-SMNDC1
si-ELAVL4
Take biological discovery in entirely new directions
New knowledge drives new hypotheses, reveals overlooked mechanisms, and opens paths to better drugs.
More Biology Per Experiment.
A richer view of cellular biology in a single experiment, capturing multiple mechanisms and their interactions together.
More Intelligence With Every Iteration.
Each experiment deepens the understanding of the cellular network, creating a learning loop that generates new hypotheses and guides the next experiment.
Experiment 1
Initial understanding
Initial understanding
Experiment 2
Deeper network understanding
Deeper network understanding
Experiment 3+
New hypotheses and directions
New hypotheses and directions
Experimental Learning Loop
Resolve Cellular Networks. Biology-Guided Drug Discovery.
Therapeutics
Biology Resolution
Experimentally resolve efficacy, resistance, mechanisms, safety biology and other therapeutic effects across modalities.
Target
Biology Resolution
Experimentally resolve what targets do, how they are regulated, and how they influence disease biology.
Disease
Biology Resolution
Experimentally resolve which pathways are active or inactive and which are driving disease across cellular contexts.
See AI Agents Become Experimental Cell Biologists
Book a meeting to learn more