Multi-Modal Foundation · MahmoodLab
SEAL
A pathology foundation model for whole-slide image representation, cancer classification, and biomarker tasks.
What SEAL is
SEAL is a pathology foundation model developed by the Mahmood Lab for computational applications across medicine and biology.
The model provides whole-slide image representations to support downstream analytical tasks, specifically cancer classification and biomarker evaluation.
Key facts
- Category
- Pathology foundation model
- Fields
- Medicine, biology
What you can use it for
- Whole-slide image representation
- Generating feature representations from histopathology whole-slide images for computational pathology workflows.
- Cancer classification
- Performing downstream slide-level cancer classification and evaluation.
- Biomarker tasks
- Evaluating and predicting biological markers directly from whole-slide image representations.
Run it here
We list this model but cannot run it yet: gated on the Hub — never run past a gate the user did not accept.
Everything on this page still applies. Running it needs a loader for this repository, not a bigger machine.
Strengths and limits
Good at
- Provides representations specifically designed for whole-slide histopathology images.
- Supports downstream evaluation across multiple applications, including cancer classification and biomarker discovery.
Inputs and outputs
You provide
Sequence or text
A protein or nucleotide sequence, or free text — whichever this model was trained on.
You get back
Mean-pooled representation, one vector per input.
Licence
Check the licence before commercial use · cc-by-nc-nd-4.0
This model is gated by its authors — its licence has to be accepted on the source repository before it will run.
Questions
Can I use SEAL commercially?
Check the licence before commercial use. This model is gated by its authors — its licence has to be accepted on the source repository before it will run.
Who developed SEAL?
SEAL was developed by the Mahmood Lab.
What are the primary applications of SEAL?
SEAL is applied to whole-slide image representation, cancer classification, and biomarker tasks.
Which scientific domains does SEAL cover?
SEAL is developed for research and computational tasks within medicine and biology.
Written from SEAL's own documentation (model card). Statements citing a figure that does not appear there are removed before publication. Licence and running details come from our registry.