PBMC10k

Tutorial on 10x multiome dataset

Installation

git clone https://github.com/kimmo1019/scDEC.git

Downloaded PBMC10k dataset which has been formatted as input of scDEC from the a cloud server. Note that it should be located in the datasets folder. The cell label annotated by a 10x R&D team is also provided (labels_annot.txt).

Run scDEC

python main_clustering.py --data PBMC10k --K 14 --dx 6 --dy 50 --no_label --mode 3

The results will be saved in the results/PBMC10k folder.

Analyze results

python eval.py --data PBMC10k

Visualization

The visualization of latent features will be saved as scDEC_embedding.png in the results/PBMC10k folder.

Clustering results

The inferred cluster label will be saved as scDEC_cluster.txt in the same results folder. Each row denotes the predicted cluster id of each cell.

The latent features learned by scDEC will be saved as scDEC_embedding.csv.