Morph2Mol · H&E workbench

Single-cell transcriptome prediction and Stage 2 embeddings from an H&E region.

Tissue

Select the matching tissue. Choose Global if it is not listed. These choices come from the loaded fusion weights; reference retrieval still uses the full bank.

Pancreas demo

Free shared GPU · ≤512 nuclei. Queue and daily per-visitor quota apply; signed-in Hugging Face users get more quota when using this Space on huggingface.co. Use the command-line pipeline for whole slides or larger regions. Input copies are removed after processing; results are cleaned after approximately one hour while the app runs. Hugging Face/Gradio upload caches may remain until their cleanup cycle.

Gene to visualize

Each gene is standardized across all cells in this image, for every tissue. Switching genes uses no GPU time.

Research use only. Expression values are predictions, not measured counts or a diagnosis. Nuclear boundaries are not complete cell boundaries. Morph2Mol uses UNI2-h (Mahmood Lab), scGPT and Cellpose-SAM; see their original publications and terms.