First compiled: May 22, 2017. Updated: March 28, 2018.
Thanks to M. Lotfollahi for running some of these computations!
Visualizing and Clustering 1.3M neurons
This uses the 1.3M neurons dataset from 10x Genomics.
If you have at least 30 GB of memory, run cluster.py to produce the following result producing in 6 hours on a small server using at most 2-3 2.4 GHz cores. If you subsample to 130K cells, this takes 16 min. The tSNE computation took about 4 hours using 8 cores. The clustering result is available here.
For simply plotting precomputed results on your laptop, use plot.ipynb, which does not require much memory.
For quick tests, see cluster_20K.ipynb for a notebook that processes dataset that has been subsampled to 20K by 10x.