# Supported modalities

As of March 2026, only the modalities below are supported by K-Pro Data Model:

* Clinical data
* Molecular data:
  * Bulk RNA seq 
  * Single / nuclei cell RNA seq 
  * Spatial transcriptomics (VisiumSD)
  * Whole Exome Sequencing 
  * Proteomics 
* Histology - slide annotation linked to a patient

{% hint style="info" %}
Extra modalities / technologies are available upon request. By default K-Pro expects to receive processed data (in the format of count matrixes for example for bulk and single cell data), however Owkin has also developed in-house processing pipeline that can process raw files for both bulk RNAseq, Chromium single-cell and Visium spatial sequencing.
{% endhint %}

#### Clinical data

Standard clinical data formats are supported (.csv, .tsv, .xlsx, …).

#### Molecular data

Here is a table of supported modalities and source formats.

| **Modalities**          | **Formats**                                                                                           |
| ----------------------- | ----------------------------------------------------------------------------------------------------- |
| Bulk RNAseq             | Count matrix (.txt / .tsv / .csv); AnnData (.h5ad)                                                    |
| Single cell RNAseq      | Matrix Market (.mtx + .tsv); HDF5 (.h5); AnnData (.h5ad); Seurat object (.rds)                        |
| Spatial transcriptomics | Matrix Market (.mtx + barcodes.tsv + features.tsv); HDF5 (.h5); AnnData (.h5ad); Seurat object (.rds) |
| WES / WGS               | VCF                                                                                                   |
| Proteomics              | Normalized intensity matrix (.txt / .tsv / .csv); AnnData (.h5ad)                                     |

#### Imaging data

Here is a table of supported modalities and formats.

| **Modalities**             | **Formats**                                 |
| -------------------------- | ------------------------------------------- |
| Histology (H\&E WSI)       | .tif, .tiff, .svs, .dcm, .svs, .ndpi, .mrxs |
| Immunohistochemistry (IHC) | .tif, .tiff, .svs, .dcm, .svs, .ndpi, .mrxs |

Note that Owkin developed several imaging processing pipelines that can be applied to imaging data, including:

* Cell segmentation and cell annotation via the [HIPE](https://arxiv.org/abs/2508.09926) model . Resulting cell-type quantifications are then saved (format: .csv) and used by K pro.
* IHC score extraction with proprietary models (*e.g.*, HER2 score, NMR, etc.). Resulting patient-level scores are then saved and used by K-pro.

Self Supervised Features extraction via [Foundation Models](https://arxiv.org/html/2501.16239v1#S4): slides are divided into tiles from which latent representations are computed, saved (format: .npy)