CD4+ and CD8+ T cell classification

Question

[pgangaitkar]

Hello,

I want to classify CD4+ and CD8+ T cell using Machine learning approach. I am unable to find dataset having rows (Instances), columns (Features), and labels (.CSV or .XSL) format. Kindly help me out, How to or from where to download the dataset? so that I can processed my work.

Please help me.

Thanking You

[antonioggsousa]

Sorry, but you need to be more specific. Which type of data are you looking for? What do you mean by rows (Instances)? Are you looking for proteomics, single-cell RNA-seq, etc?

There are many types of omics data sets that can potentially be used from machine learning. You need to be more specific.

If you're looking for single-cell RNA-seq data (cells x genes, where the entries represent gene expression values - measurements) you can perhaps start by a recent resource made available by the Teichmann lab & colleagues about the Immune Tissue Cell Atlas:

• paper: Domínguez Conde et al., 2022

• jupyter notebooks (with analysis): https://github.com/Teichlab/TissueImmuneCellAtlas

• processed data (to download): https://www.tissueimmunecellatlas.org/

• classification tool (developed by them): CellTypist

I hope this helps,

António

[pgangaitkar]

Thank You for your valuable comment. Basically, I am not from the Biological/ Chemical field. I am a student of Computer science. So I don't have much knowledge about this. I need a dataset (feature vector) containing some rows having CD4+ cell and some are CD8+ cells, Columns indicate that number of features. So that I can apply my AI approach and build a prediction model.

[antonioggsousa]

In that case you can try to use the data set above. It is perhaps not the most simple example to start from, but it is a comprehensive data set that provides many cell types at different hierarchical resolutions that you can use to filter down to the cell types that you are interested in.