Model Card for Hierarchical VQ VAE model for analysis of imaging-based ST data

<!-- Provide a quick summary of what the model is/does. -->

Pretrained checkpoints trained on Vizgen oncology ST dataset.

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

• Developed by: Dig Vijay Kumar Yarlagadda
• Model type: VQ-VAE

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository: https://github.com/digvijayky/hier_vq_vae_st
• Paper [optional]: https://openaccess.thecvf.com/content/ICCV2023W/BIC/html/Yarlagadda_Discrete_Representation_Learning_for_Modeling_Imaging-Based_Spatial_Transcriptomics_Data_ICCVW_2023_paper.html

Uses

Analysis of imaging-based spatial transcriptomics datasets such as MERFISH, SEQFISH and Xenium.

Direct Use

Analysis of Vizgen oncology dataset.

Downstream Use [optional]

Finetuning on any imaging-based ST data.

Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

Analysis of spot-based ST data Mapping of scRNA-seq to ST data

Compute Infrastructure

Model is trained on 4 A100 GPUs.

Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

APA:

If you use this checkpoint or model, please cite:

Dig Vijay Kumar Yarlagadda, Joan Massague, Christina S. Leslie. "Discrete Representation Learning for Modeling Imaging-based Spatial Transcriptomics Data". International Conference on Computer Vision, Bioimaging Computing workshop 2023.