Overview / Usage

Squidpy introduces two main data representations to manage and store spatial omics data in a technology-agnostic way: a neighborhood graph from spatial coordinates and large-source tissue images acquired in spatial omics data .

We present Squidpy ported to Intel one API AI Analytics, a

Python framework that brings together tools from omics and image analysis to enable the scalable description of spatial molecular data, such as transcriptome or multivariate proteins.

Squidpy provides efficient infrastructure and numerous analysis methods that allow to efficiently store, manipulate and interactively visualize spatial omics data.

We port Squidpy to Intel AI Analytics toolkit.

Here we use Intel Devcloud to do the entire experiment

We are using Intel oneAPI AI Analytics to integrate omics dataset to all libraries.

​

Methodology / Approach

We are using Intel Devcloud

using the oneAPI AI analytics toolkit we are able to process the data and have brilliant visualizations

Here we use Intel Devcloud to do the entire experiment

We are using Intel oneAPI AI Analytics to integrate omics dataset to all libraries.

Steps

1)Initialize Intel Devcloud.

2)Start working with Intel AI Analytics toolkit.

3)Bring in Visium Data from Visium Dataset.

Visium Spatial Gene Expression is a next-generation molecular profiling solution for classifying tissue based on total mRNA. Map the whole transcriptome with the morphological context in FFPE or fresh frozen tissues to discover novel insights into normal development, disease pathology, and clinical translational research.

4)Apply logics in oneAPI AI analytics toolkit using the programming language Python to generate Spatial graphs while exploring image containers all within Intel Devcloud.

5)Applying the logic we arrive at doing the following using Intel AI Analytics toolkit.

Using varying plotting process inside Intel Devcloud

**we are able to know about **

1)Spatial neighbourhood

2)We get interactive visualizations

3)We are able to find Ligand-receptor interactions

4)We can do spatial statistics

5)We can extract image features

6)We can see Nuclei Segmentations

​

​

Technologies Used

Intel AI

Intel Devcloud

oneAPI AI analytics toolkit

Squidpy

anndata

Scanpy

VISIUM Data