# Spatial Omics Data

### Spatial Omics Data

Spatial omics is a rapidly advancing field that combines molecular measurements—such as gene expression or protein abundance—with spatial context. These techniques allow researchers to study tissue microenvironments and cellular organization in high resolution.

Rexis supports encrypted spatial omics pipelines by enabling secure data storage, model fine-tuning, and reproducible evaluation—all without exposing raw molecular or imaging data.

![](https://lh7-rt.googleusercontent.com/slidesz/AGV_vUdas7e1glReK4aphIb7JiG1DnkulaEhMNOJ3jY34QX0kfRnGgqWRmG9cP72macOvUiJmfrpPCgTsOhVWt7xF_jPbN1G7kemWz4hfFWeWnJeIlgUkI6Qrf0K2lZzcDPGQFT6EbO8Hg=s2048?key=_t06K9zDHrDgeHDIPqC4uaCR)

***

#### Spatial Transcriptomics

Spatial transcriptomics methods preserve the spatial location of cells while measuring gene expression across intact tissue slices. This enables researchers to explore tissue structure and gene activity simultaneously.

**Data Support**

Spatial transcriptomics datasets are commonly stored in:

* **MTX** – sparse gene expression matrices
* **HDF5** – hierarchical storage for large-scale molecular profiles
* **CSV/TSV** – metadata and coordinate annotations

These are often paired with **high-resolution tissue images**.

Using **Equivariant Encryption (EE)**, Rexis enables:

* Encrypted storage and distributed processing
* Privacy-preserving analysis of gene expression patterns
* Secure collaboration across research labs

**Model Support**

Foundation models for spatial transcriptomics can perform:

* Spatial domain detection
* Cell-type deconvolution
* Context-aware gene imputation

We support **secure fine-tuning and evaluation on encrypted spatial transcriptomics data**.

* [**scGPT-spatial**](https://github.com/bowang-lab/scGPT-spatial)\
  A specialized foundation model pretrained on 30M spatial profiles. Supports deconvolution, contextualized imputation, and analysis of spatially resolved expression data.

***

#### Spatial Proteomics

Spatial proteomics measures the expression and localization of proteins across tissue sections, using techniques such as:

* **Imaging Mass Cytometry (IMC)**
* **Multiplexed Ion Beam Imaging (MIBI)**

These technologies detect dozens of proteins simultaneously, producing high-dimensional spatial maps of protein activity.

**Data Support**

Current formats vary but often include:

* **Multichannel images** – each channel represents one protein
* **Coordinate files** – spatial locations of each pixel or segmented cell

EE ensures that these **high-dimensional proteomics datasets remain encrypted during processing**, supporting:

* Secure storage and downstream analysis
* Multi-institution research collaborations
* Protection of patient-derived and proprietary biomarker data

**Model Support**

Foundation models applied to spatial proteomics can:

* Segment cells
* Map protein interactions
* Support spatially resolved single-cell analysis

We support **secure training and inference on encrypted spatial proteomics data**.

* [**DeepCell**](https://deepcell.com/)\
  A deep learning framework for analyzing spatially multiplexed protein data. Supports cell segmentation, feature extraction, and tissue organization modeling from multi-channel imaging.

***


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://rexis.gitbook.io/rexis/spatial-omics-data.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.