Single Cell Data for Clustering and Pseudotime Goodness-of-Fit Evaluation

<p dir="ltr">The zhengmix4 dataset is from,</p><p dir="ltr">nature.com/articles/ncomms14049</p><p dir="ltr">and includes 10X scRNA-seq readouts from human PBMCs. It can be used to evaluate clustering methods. It contains contains 3555 cells with 1556 genes.</p><p dir="ltr">The pseuodtime_example dataset is a synthetic dataset from dyngen.</p><p dir="ltr">nature.com/articles/s41467-021-24152-2</p><p dir="ltr">It is simulated along a linear trajectory The dataset contains 500 cells and 155 genes, and its ground-truth pseudotime values are saved in the <code>pseudotime</code> column of the <code>anndata.obs</code> dataframe.</p>