Ask the question your last study could not.

Research rarely ends with the question it started with. Aurora opens a new way to explore the tissue you already know—and follow the ideas that emerge from it.

With predicted spatial gene expression from H&E slides, the study you finished can take up the question it could not ask.

Submit a slideSee academic access
Virtual spatial transcriptomicsValidationHypotheses fromevery H&E slideThe strongest,measured by aspatial assay

Applications

Questions that outlive the study that raised them

  1. Explore

    The idea that arrived after the study ended

    A study's H&E slides already cover every case, and most of that tissue never reaches a measured experiment.

    Predicted expression on those slides lets a new idea run through the whole collection, including cases whose blocks are long gone.

    • Revisit a published cohort with a new molecular question
    • Compare samples that were never profiled, on the same genes
    • Set the old cohort beside your new one, gene for gene

    Built onOut-of-the-box predictionComparative spatial analysis

    DeepSpot-M predicts 19,338 protein-coding genes at every retained tile of a slide, from the H&E image alone.[1]

  2. Explore

    The observation that stayed with you

    A pattern you noticed in a section, and could only describe, can be put to the genes behind it on predicted expression.

    • Which genes vary most across the section?

      Spatially variable genes, ranked by Moran's I, in the spatial analysis report

    • Which regions carry different expression programmes?

      Clusters drawn on the tissue, with their marker genes, in the spatial analysis report

    • Which clusters sit next to each other in the tissue?

      Neighbourhood enrichment between clusters, in the spatial analysis report

    • How does one gene look on the tissue, and on the UMAP?

      Any predicted gene, on the tissue and on the UMAP, in the explorer, on the Academic Research route

    • What separates one region from another?

      Differential expression between two groups you select, in the explorer, on the Academic Research route

    Built onThe analysis report and the explorer

  3. Extend

    The result that pointed past the panel

    With our team, the panel you measured anchors predictions for the protein-coding genes it never carried, and the genes that failed quality control are restored.

    Each predicted gene lands on the spots your assay reported, marked as a prediction beside the measured columns.

    • Follow the gene your result pointed at, past the panel
    • Recover the genes your run lost, without cutting the section again
    • Adapt predictions to the slides you measured

    Built onPanel extensionRestore genesFinetune

    Arranged with our team, on the Academic Research Pro route.See Academic Research Pro

    The DeepSpot-M preprint demonstrates prediction for genes excluded from training.[1]

  4. Look ahead

    The question left open for the next study

    Explore a hypothesis on predicted expression across the slides a study already holds, and the next experiment can begin where the pattern is.

    • Check whether a spatial pattern appears before you plan to measure it
    • Choose the samples and regions a proposal will measure
    • Set aside a question the predicted data does not support

    Built onOut-of-the-box predictionThe analysis report and the explorer

Your route

Start with the slides you already have

If the analysis raises a hypothesis, use measured spatial profiling to test it.

University groups, institutes, hospitals and foundations working on their own cohorts.

Submit an H&E slide and read predicted spatial gene expression back, with no assay to book and no agreement to sign. Analysis is for academic and non-profit research. If your work sits between academic and commercial, ask before you prepare a slide.

Submit a slideSee access options

Worked examples

Followed through on real tissue

References

  1. [1]Nonchev K, Dawo S, Silina K, Koelzer VH, Rätsch G. DeepSpot-M: a multimodal foundation model for transcriptome-wide virtual spatial transcriptomics from histology. medRxiv. Preprint, 2026. https://doi.org/10.64898/2026.06.19.26356060 (opens in a new tab)