Wildly variable retained barcode list
See original GitHub issueHello, I just tried out CellBender on 21 datasets of 10x v2 single nuclei data that should be generally comparable (Cell Ranger retains ~1500-3500 barcodes in each) but I got wildly variable results with CellBender.
I used the following parameters: expected-cells = 5000
, total-droplets-included = 15000
, epochs = 1500
.
The number of barcodes retained by CellBender (from the output.csv
file) are below. I’m surprised to see do many datasets with the maximum number of 15k, as well as 2 datasets with 0. Could this be a result of overfitting because I did 1500 epochs? In the output.pdf
I noticed that only a train score is provided, so it’s hard to diagnose overfit…
Here are the knee plots in case they help diagnose things. All datasets are pretty similar.
15000
15000
15000
15000
6001
5430
11420
0
11426
5448
6628
15000
8731
7871
7454
7139
0
15000
6024
8564
9622
Issue Analytics
- State:
- Created 3 years ago
- Comments:8 (4 by maintainers)
Yes I do believe there is something funky with the data I’m working with. It is a single nuclei dataset of C. elegans, with a new dissociation protocol. It seems to have a lot of background (which is odd since nuclei are washed).
Thanks for the help. I’ll give another shot with cellbender next time I have a less problematic dataset.
By the way, the latent space for that “hard” example above looks like this:![image](https://user-images.githubusercontent.com/10214815/95130239-4609cb80-072a-11eb-99a6-3df669a21a80.png)
To me, your latent space being a sort of formless blob seems to be another possible hint that there may be some kind of a quality control failure. It’s not definitive of course… for some experiments without much cellular diversity, the latent space will tend to just look like a blob.