Paige Predict: AI-Powered Biomarker Prediction

Accelerate your research, optimize scarce tissue, and enrich cohorts at scale with Paige Predict, an advanced AI application generating robust genomic insights in minutes.

From Image to Insight: Predict ~1,600 biomarkers from a single H&E slide

Paige Predict bridges the gap between pathology and genomics. Leveraging our state-of-the-art computational pathology foundation models, this AI application analyzes routine H&E images to predict the status of ~1,600 biomarkers across 505 genes.

For Research Use Only

Can Paige Predict…?

Search all biomarkers included with Paige Predict to find your target of interest.

    Key Benefits

    Accelerate biomarker screening across samples

    • Speed to insight: Provides probabilistic predictions in approximately 5 minutes to accelerate sample selection.

    • Smart triage: Streamline workflows and fast-track the right samples for confirmatory Next-Generation Sequencing (NGS), hotspot testing, IHC, and special stains.

    Receive genomic insights across cancer types

    • Maximize limited tissue: Predictions help researchers prioritize the use of tissue, protecting precious samples in indications where biopsy material is historically scarce (e.g., Non-Small Cell Lung Cancer).

    • Broad coverage: Uncover genomic patterns in less well-tested or rare indications (e.g., Melanoma, Endometrium) across multiple distinct cancer cohorts.

    Enrich cohorts for research at scale

    • Pre-screen at scale: Pre-screen large biobanks or sample cohorts for specific biomarkers of interest to identify relevant samples at scale.

    • Streamline trial design: Support research timelines and significantly reduce the time to enrollment in clinical studies by filtering out unlikely candidates before deploying costly molecular tests.

    Paige Predict features are for Research Use Only (RUO) and are not for use in diagnostic procedures. Paige Predict results are probabilistic predictions and should not be used to determine treatment eligibility or as evidence of actual biomarker status.

    Tempus deployment

    We have validated Paige Predict on 123 clinically relevant biomarkers and oncogenic molecular pathways, and it is in use with our xT assay to provide biomarker insights when tissue is insufficient for our solid tumor DNA sequencing workflows.

    Sample Tempus xT report for a non-small cell lung cancer specimen with insufficient tissue, showing Paige Predict biomarker predictions grouped by elevated, typical, and reduced likelihood.
    Paige Predict results are probabilistic predictions and should not be used to determine treatment eligibility or as evidence of actual biomarker status.

    Resources

    Abstract background with blurred light grey shapes and faint repeating letter patterns.

    Screen Them All: High-Throughput Pan-Cancer Genetic and Phenotypic Biomarker Screening from H&E Whole Slide Images

    Preprint on Paige Predict, developed using Virchow2 (2025).

    Abstract background with light grey tones, subtle blurs, and faint 'SUMMER SUPPLEMENT' text patterns.

    From image to insight: How Tempus is leveraging AI to advance biomarker screening at scale

    By leveraging Paige Predict to screen for genomic and phenotypic biomarkers, clinicians and researchers have rapid access to valuable information to prioritize testing and pre-screen patients at scale.

    Abstract digital background with light blue and grey shapes and subtle code-like text overlay.

    Solving cancer’s tissue scarcity problem: How Tempus uses AI models in pathology to transform tissue analysis

    Tempus AI research demonstrates how AI can analyze digitized pathology images to predict tissue sample viability for genomic testing, a task that pathologists struggle to perform consistently.

    Abstract background with blurred light grey shapes and faint repeating letter patterns.

    Tempus Announces the Launch of Paige Predict

    This is AI-enabled precision medicine

    This is the future of healthcare.