Frequently Asked Questions
Common questions about virtual spatial transcriptomics and the Aurora platform.
The basics
What is virtual spatial transcriptomics?
Virtual spatial transcriptomics predicts spatial gene expression from H&E images, without requiring a new spatial assay to generate the prediction. Researchers can use the results to form hypotheses and decide what to validate experimentally. Predictions remain computational estimates, not assay measurements.
How many genes are covered in the virtual spatial transcriptomics?
DeepSpot-M predicts the full protein-coding transcriptome: the same 19,338 genes for every tissue and disease, and every result includes all of them. It can also predict non-coding RNAs, such as tRNAs, lncRNAs, rRNAs and miRNAs, which standard 10x Visium largely misses because it captures only polyadenylated RNA. These are not part of a standard result, so contact us if your project needs them.
Workflow and results
How long does processing take?
Timing varies by submission and current demand. We'll email you when your results are ready. You can follow a submission to Aurora Direct on the Track page, and in Aurora Intelligence each slide's status shows in your workspace.
Is there a limit on the number of spatial tiles?
On Academic Standard, yes. After quality filtering, each image is limited to 50,000 tiles. If your image produces more tiles, the system automatically selects the densest contiguous square region to preserve spatial context for downstream analysis. The original tile count and subsampling status are displayed on your results page. Other access sets its limits by agreement.
What format are the results in?
Each result includes a predicted expression matrix (.h5ad.gz), a spatial analysis report and a quality-control report. Spatial gene maps are also available in the results view.
Can I get predictions at my own spot coordinates, for example to compare with Visium?
Yes. With Aurora Direct, under Advanced on the upload page, add a table for each image: a barcode and each spot's pixel row and column (pxl_row_in_fullres, pxl_col_in_fullres), or Space Ranger's tissue_positions.csv as it is. The coordinates must be pixel positions in the full-resolution image you upload. 10x's tissue_hires_image.png and tissue_lowres_image.png are previews, not the image to use. Results come back keyed by your barcodes, so you can compare them with your own measurements.
Your data
Where is the data stored and preprocessed?
Uploaded images, generated results and account information are stored on infrastructure in Switzerland, and analyses run there. Cloudflare may process website traffic outside Switzerland; see the Privacy Policy for details.
How is my data kept private?
Uploaded data and generated results are confidential and are not made publicly available. With Aurora Direct, you retrieve a submission with its unique ID and your verified email address, and in Aurora Intelligence your data stays in your workspace. Members of our research team can access the data as reasonably necessary to operate the platform, generate results, carry out directly related research and develop Aurora's models and services, as described in the Terms. Commercial data is used only as your agreement allows.
How is my data kept secure?
Your data is protected at every stage. It is encrypted in transit and in backups, kept separate from every other account and workspace, and our safeguards are monitored around the clock.
Can Aurora use the data I upload?
Under academic access, the data you upload and its results may help improve Aurora's models and services. Your data is never made public. Commercial data is used only as your agreement allows. The Terms have the details.
Access
Can I use Aurora from Python or a script instead of the browser?
Yes. The API and the Python package let you submit samples and read predictions without the browser. Programmatic access is requested in Aurora Intelligence: sign in, open Settings, then API keys.
Related Paper
Request programmatic access (opens in a new tab)How many images can I analyse?
Academic Standard starts with 3 images, and rating a result adds one image to your allowance. Other access sets its allowance by agreement. If you would like to analyse more, get in touch and tell us a little about your project. We can discuss the appropriate route for your work.
Commercial access
How does commercial access work?
Commercial access is coming soon. Commercial evaluation and use are governed by a written agreement with Aurora. Commercial R&D is for individual researchers, and Enterprise for teams and organisations. Tell us about your work, and we can discuss the arrangement that fits it.
How is commercial data handled?
Commercial data is used only as your agreement allows. It is kept confidential and never made public.
Support and citation
How do I cite this work?
If you use our platform or find our work valuable, please cite:
@article{nonchev2026deepspotm,
author = {Nonchev, Kalin and Dawo, Sebastian and Silina, Karina and Koelzer, Viktor H and R{\"a}tsch, Gunnar},
title = {DeepSpot-M: A Multimodal Foundation Model for Transcriptome-Wide Virtual Spatial Transcriptomics from Histology},
year = {2026},
journal = {medRxiv},
note = {Preprint},
doi = {10.64898/2026.06.19.26356060},
url = {https://www.medrxiv.org/content/10.64898/2026.06.19.26356060v1}
}Under academic access, attribution and citation are required in any publication that uses results from Aurora. Commercial access follows its agreement.
How can I report an issue or request support?
If you encounter any issues on the platform or need additional support, please use our contact form to submit a detailed description of the problem or request.
Ready to try it yourself?
Academic and non-profit
Biotech, pharma and industry