Keep your collection contributing to discovery.

Years of careful collection and preservation can support studies that nobody anticipated when the tissue was stored. Making that material available for new molecular questions gives researchers another reason to return to the archive and build collaborations around it.

Aurora predicts spatial gene expression from digitised H&E slides, so researchers can investigate patterns across the collection while the remaining tissue stays available for experiments. Even when a block has been exhausted, its image can continue to contribute.

The archivePredictedMeasuredA new questionpicks out a fewA handful goon to an assay

Keep the collection active as research moves on

  1. Explore

    Let the collection answer questions it was never built for

    Predicted gene maps let researchers investigate a collection by molecular patterns as well as its existing catalogue. A group studying a new candidate gene can look across earlier cases and develop a proposal around material it might otherwise have overlooked.

    Built onOut-of-the-box predictionComparative spatial analysis

  2. Explore

    Keep a sample in research after its block is gone

    An exhausted block can still leave a digitised slide suitable for predicted spatial gene expression. Including that image in a new computational study preserves a role for the sample and the work that went into collecting it.

    Built onOut-of-the-box prediction

  3. Extend

    Give earlier measurements a place in the tissue

    Paired bulk RNA and H&E images let earlier molecular studies contribute to questions about particular tissue regions.

    Revisit existing bulk RNA findings in their tissue context, using sample-matched profiles to inform predicted gene maps.

    Built onSample-matched bulk RNAOut-of-the-box prediction

    The web upload does not take a bulk profile. It goes in through the Python package and the API, on the Academic Research route.Learn about Academic Research

  4. Look ahead

    Protect rare tissue for the experiment that needs it

    Researchers can investigate predicted patterns before requesting additional sections, then identify the cases and regions that serve their question. This gives you a clearer basis for discussing access to scarce material and preserving it for purposeful follow-up.

Discuss the research your collection could support

Biobanks, pathology archives and the groups that curate them.

Academic and non-profit research collections can use Academic Standard. Commercial use may be subject to separate terms. Contact us before preparing a large collection.

Explore how an archive can support another study

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)
  2. [2]Nonchev K, Dawo S, Silina K, Koelzer VH, Rätsch G. TCGA Virtual Spatial Transcriptomics Atlas. Hugging Face. Dataset, 2026. https://huggingface.co/datasets/ratschlab/TCGA_virtual_spatial_transcriptomics_atlas (opens in a new tab)