Add dimred task/datasets descriptions

[lazappi]

Submission type

• This submission adds a new dataset
• This submission adds a new method
• This submission adds a new metric
• This submission adds a new task
• This submission adds a new Docker image
• This submission fixes a bug (link to related issue: )
• This submission adds a new feature not listed above
• This submission adds new documentation

Testing

• This submission was written on a forked copy of SingleCellOpenProblems
• GitHub Actions "Run Benchmark" tests are passing on this base branch of this pull request (include link to passed test: )
• If this pull request is not ready for review (including passing the "Run Benchmark" tests), I will open this PR as a draft (click on the down arrow next to the "Create Pull Request" button)

Submission guidelines

• This submission follows the guidelines in our Contributing document
• I have checked to ensure there aren't other open Pull Requests for the same update/change

PR review checklist

This PR will be evaluated on the basis of the following checks:

• The task addresses a valid open problem in single-cell analysis
• The latest version of master is merged and tested
• The methods/metrics are imported to __init__.py and were tested in the pipeline
• Method and metric decorators are annotated with paper title, year, author, code version, and date
• The README gives an outline of the methods, metrics and datasets in the folder
• The README provides a satisfactory task explanation (for new tasks)
• The sample test data is appropriate to test implementation of all methods and metrics (for new tasks)

[lazappi]

This is a draft because I still need to add something for the Nestorowa 2016 dataset. The current description says this is human data but the only paper with this name I could find is https://doi.org/10.1182/blood-2016-05-716480 which is mouse. @mvinyard I think you added this originally, do you know what is correct?

Also, it would be great to have a way to add a DOI for each dataset. Trying to find papers just from the year and name is a pain.

Also also, should these descriptions go in the main dataset files rather than the task-specific file (to avoid having to duplicate stuff/having slightly different info)?

[LuckyMD]

At the moment we only have decorators in the task-specific dataset functions. But it's a good point that this could go into the data loaders. I'm not sure what the considerations are there w.r.t. where the decorator function is run (in which image). And how easily we can then use the text in the task outputs.

[scottgigante-immunai]

At the moment we only have decorators in the task-specific dataset functions. But it's a good point that this could go into the data loaders

I don't think this should programmatically go into the dataset loaders, since e.g. pancreas_batch and pancreas_random would need difference descriptions but both come from the same loader. However, our dataset loader functions are extremely poorly documented, e.g. I have no idea what paper / cell type / technology pancreas actually comes from, and no idea how the figshare file was generated.

A good start would be to follow the dataset loader name template in CONTRIBUTING:

This file name should match [First Author Last Name]_[Year Published]_short_Description_of_data.py. E.g. the dataset of zebrafish embryos perturbed with CRISPR published in 2018 by Wagner et al. becomes Wagner_2018_zebrafish_embryo_CRISPR.py

[mvinyard]

This is a draft because I still need to add something for the Nestorowa 2016 dataset. The current description says this is human data but the only paper with this name I could find is https://doi.org/10.1182/blood-2016-05-716480 which is mouse. @mvinyard I think you added this originally, do you know what is correct?

I believe that's correct, @lazappi - let me know how I can help- thanks!

[lazappi]

That DOI is the correct reference (so this is actually mouse data)?

[scottgigante-immunai]

Yes, I think that's right. FYI I have an open PR to include a DOI/reference for all dataset loaders so this doesn't happen again: #500

[mvinyard]

You are correct, @lazappi. This is mouse data. Thanks!

[codecov]

Codecov Report

Merging #490 (f254b9d) into main (3c1dec5) will increase coverage by 0.04%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##             main     #490      +/-   ##
==========================================
+ Coverage   94.04%   94.08%   +0.04%     
==========================================
  Files         113      114       +1     
  Lines        2906     2927      +21     
  Branches      150      150              
==========================================
+ Hits         2733     2754      +21     
  Misses        118      118              
  Partials       55       55              

Flag	Coverage Δ
unittests	94.08% <100.00%> (+0.04%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
openproblems/data/mouse_blood_olssen_labelled.py	100.00% <ø> (ø)
..._reduction/datasets/mouse_blood_olssen_labelled.py	100.00% <ø> (ø)
.../dimensionality_reduction/datasets/tenx_5k_pbmc.py	100.00% <ø> (ø)
...lems/tasks/spatial_decomposition/methods/destvi.py	100.00% <100.00%> (ø)

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 63fb80a...f254b9d. Read the comment docs.

[scottgigante-immunai]

@LuckyMD are you happy to approve this?