Methods

Methods

Building the physical harness that teaches AI to connect lab experiments to human drug outcomes.

Methods

We experimentally measure the full life cycle of a drug, linking exposure and metabolism to cellular biology and human outcomes.

Methods

Scientists meticulously annotate and curate our experimental data to make it ready for AI training.

Methods

Every experiment is rigorously evaluated with Axiom's suite of proprietary quality control tools.

Data Readiness

Keeping track of all compounds

Data Readiness

Ingestion Pipeline

Data across different assays

Ingestion Pipeline

Model Evaluation

Grading model performance

Model Evaluation

Model Leaderboard

Tracking model performance

Model Leaderboard

Image Segmentation

Mask & Quality Control

Image Segmentation

Methods

We extract early, subtle biological signals from our experimental data to predict human outcomes.

Steatosis

Lipid Droplet Accumulation

Hoechst (Nuclei) LipTOX (Neutral Lipids)

ER Stress

BIP/GRP78 Expression

Hoechst (Nuclei) BIP/GRP78 (ER Stress)

Cholestasis

Bile Canaliculi Loss

Hoechst (Nuclei) Phalloidin (Actin)

Lysosomal Disruption

Lipofuscin Buildup

Hoechst (Nuclei) Lysosomal (Autofluorescence)

Mitochondria

Fission and Fusion

Hoechst (Nuclei) Mitotracker

Cytotoxicity

Nuclei Loss and Morphology

Hoechst (Nuclei)

Methods

Our mechanistic reasoning agents use thousands of clinical reference molecules to translate subtle signals into actionable drivers of human risk.

Method

End-to-end clinical outcomes powered by integrated experimental data and AI-driven mechanistic reasoning.

Very high PPB (97th %ile) combined with very low clearance (11th %ile) suggests prolonged drug exposure to hepatocytes. This profile matches withdrawn NSAIDs fenclozic acid (PPB 99th, clearance 3rd %ile) and benoxaprofen (PPB 98th, clearance 5th %ile) that showed delayed-onset hepatotoxicity.

Very high PPB (97th %ile) combined with very low clearance (11th %ile) suggests prolonged drug exposure to hepatocytes. This profile matches withdrawn NSAIDs fenclozic acid (PPB 99th, clearance 3rd %ile) and benoxaprofen (PPB 98th, clearance 5th %ile) that showed delayed-onset hepatotoxicity.

Very high PPB (97th %ile) combined with very low clearance (11th %ile) suggests prolonged drug exposure to hepatocytes. This profile matches withdrawn NSAIDs fenclozic acid (PPB 99th, clearance 3rd %ile) and benoxaprofen (PPB 98th, clearance 5th %ile) that showed delayed-onset hepatotoxicity.

Very high PPB (97th %ile) combined with very low clearance (11th %ile) suggests prolonged drug exposure to hepatocytes. This profile matches withdrawn NSAIDs fenclozic acid (PPB 99th, clearance 3rd %ile) and benoxaprofen (PPB 98th, clearance 5th %ile) that showed delayed-onset hepatotoxicity.

Clinical Risk Assessment

Axiom generates end-to-end clinical risk assessments powered by integrated experimental data and AI-driven mechanistic reasoning.

Publications

Axiom's Data & Evidence

Understand drug toxicity before it reaches humans.