Batch integration data by danielStrobl · Pull Request #355 · openproblems-bio/openproblems

danielStrobl · 2022-04-13T10:07:16Z

Add immune cell dataset from Luecken et al., 2022 for batch integration task.

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

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: https://github.com/danielStrobl/SingleCellOpenProblems/runs/6011178735?check_suite_focus=true )
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) still waiting on run benchmark

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)

…leCellOpenProblems into batch-integration-data

LuckyMD

A few comments on the order of filtering in the immune data. Also, shouldn't this PR also include the task dataset functions from the batch integration graph task? In those, you should assign adata.X = adata.layers['log_scran'] again.

LuckyMD · 2022-04-13T10:24:14Z

I guess the PR should also be tested...

…leCellOpenProblems into batch-integration-data

codecov-commenter · 2022-04-20T16:55:59Z

Codecov Report

Merging #355 (ea1adef) into main (84c8287) will increase coverage by 0.37%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##             main     #355      +/-   ##
==========================================
+ Coverage   91.48%   91.86%   +0.37%     
==========================================
  Files          83       89       +6     
  Lines        1973     2064      +91     
  Branches      117      118       +1     
==========================================
+ Hits         1805     1896      +91     
  Misses        125      125              
  Partials       43       43

Flag	Coverage Δ
unittests	`91.86% <100.00%> (+0.37%)`	⬆️

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

Impacted Files	Coverage Δ
openproblems/data/immune_cells.py	`100.00% <100.00%> (ø)`
openproblems/data/pancreas.py	`100.00% <100.00%> (ø)`
.../_batch_integration/batch_integration_graph/api.py	`100.00% <100.00%> (ø)`
...gration/batch_integration_graph/datasets/immune.py	`100.00% <100.00%> (ø)`
...ation/batch_integration_graph/datasets/pancreas.py	`100.00% <100.00%> (ø)`
...tegration/batch_integration_graph/methods/bbknn.py	`100.00% <100.00%> (ø)`
...integration/batch_integration_graph/metrics/ari.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 84c8287...ea1adef. Read the comment docs.

…leCellOpenProblems into batch-integration-data

scottgigante-immunai · 2022-05-04T16:25:30Z

So this looks like it's all succeeded? The tower.nf logs strangely show the nextflow pipeline is still running, despite everything being complete.

danielStrobl · 2022-05-04T16:58:32Z

That's weird, run_benchmark is still shown as running on my branch, and has been so for 26 hours... not sure what's up with that

scottgigante-immunai · 2022-05-04T17:15:34Z

I'm looking into it, I think it's a nextflow bug (that I might have just fixed.)

danielStrobl · 2022-05-05T08:25:45Z

The issue seems to persist, still running for 5 hours

danielStrobl · 2022-05-05T14:38:00Z

scottgigante-immunai · 2022-05-05T14:47:21Z

Looking back through the logs, it looks like this only started happening on the self-hosted runner. Trying a reversion back to GH Actions for now.

…

On Thu, May 5, 2022 at 10:38 AM Daniel Strobl ***@***.***> wrote: [image: Screenshot 2022-05-05 at 16 32 47] <https://user-images.githubusercontent.com/50872326/166947775-357b903d-f489-4ede-a303-88b345b47b32.png> — Reply to this email directly, view it on GitHub <#355 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AUHCMAUI33SNA7IYC4WGSJTVIPMNJANCNFSM5TKEP2PQ> . You are receiving this because you commented.Message ID: ***@***.***>

…leCellOpenProblems into batch-integration-data

LuckyMD

few questions about the documentation and the testing that matches it, otherwise this is ready to go :). Nice job!

LuckyMD · 2022-05-10T23:06:40Z

+
+The `openproblems-python-batch-integration` docker container is used for the methods that
+can be installed without package conflicts. For R methods, the `openproblems-r-extras`
+container is used.


Need to add other docker containers here, or make a note to add them in the other, larger PR.

LuckyMD · 2022-05-10T23:07:16Z

+* `full_scaled`
+* `hvg_scaled`
+
+An example script can be found [here](methods/_example.py)


what is this example script meant to be?

LuckyMD · 2022-05-10T23:08:52Z

+def check_dataset(adata):
+    """Check that dataset output fits expected API."""
+
+    assert "X_uni" in adata.obsm


I assume this is old code and should now be a test for adata.layers['counts']?

Otherwise, this is not stated in the README and should be added... it seems to be used as a representation below for the sample_method function.

LuckyMD · 2022-05-10T23:09:43Z

+
+def check_method(adata):
+    """Check that method output fits expected API."""
+    assert "connectivities" in adata.obsp


Either check for "distances" as well, or remove this from the API description in the README.

LuckyMD · 2022-05-10T23:12:29Z

+* `adata.layers['counts']` with raw, integer UMI count data, and
+* `adata.obsp['uni_connectivities']` with an unintegrated connectivity matrix generated
+  by  `scanpy.pp.neighbors()`
+* `adata.X` with log-normalized data


need to add adata.obsm['X_uni'] as the PCA embedding of the unintegrated representation here.

…leCellOpenProblems into batch-integration-data

scottgigante-immunai · 2022-05-11T14:36:40Z

Woohoo!

LuckyMD · 2022-05-11T17:08:12Z

Nice :). And by the deadline :D

* Update with to accomodate multimodal data * rename bash script

* Update with to accomodate multimodal data * rename bash script Former-commit-id: 3a811a7

danielStrobl and others added 13 commits April 12, 2022 15:04

initial commit datasets batch integration

7b26190

shorten long line

39b212c

pre-commit

925988c

keep raw counts in X

156f062

Merge branch 'batch-integration-data' of github.com:danielStrobl/Sing…

02ee3a5

…leCellOpenProblems into batch-integration-data

kill pytest after 2 fails for testing

c65ce8c

increase swap size

7fdde3d

set swap size

2d6ed85

swap

a1a1e24

fix syntax

514810d

change order of tests

46992ce

remove duplicate layer

57980fd

pre-commit

7759de6

LuckyMD requested changes Apr 13, 2022

View reviewed changes

Comment thread .trunk/out Outdated

Comment thread openproblems/data/immune_cells.py Outdated

Comment thread openproblems/data/immune_cells.py

Comment thread openproblems/data/immune_cells.py Outdated

Comment thread openproblems/data/pancreas.py

danielStrobl added 2 commits April 13, 2022 16:23

immune cell dataloader comments

ab247d5

Merge branch 'batch-integration-data' of github.com:danielStrobl/Sing…

4017aae

…leCellOpenProblems into batch-integration-data

danielStrobl marked this pull request as ready for review April 13, 2022 15:37

doc

099aacf

danielStrobl force-pushed the batch-integration-data branch from 2e569eb to 099aacf Compare April 20, 2022 10:05

danielStrobl and others added 2 commits April 20, 2022 17:58

add task dataloaders and subsampling immune

6d7ff95

pre-commit

5a74855

danielStrobl and others added 7 commits April 21, 2022 08:23

add batch integration to init py

42d844b

pre-commit

1d4901a

typo

3fc7cd8

Merge branch 'batch-integration-data' of github.com:danielStrobl/Sing…

7f08f69

…leCellOpenProblems into batch-integration-data

generate empty structure for metrics/methods

89aff82

init py root

125450a

metrics wrong folder

5901aeb

Merge branch 'master' into batch-integration-data

5d44aef

Merge branch 'main' into batch-integration-data

111a0c5

scottgigante-immunai and others added 10 commits May 5, 2022 21:02

Merge branch 'main' into batch-integration-data

cf5fc3e

Merge branch 'main' into batch-integration-data

774bec8

Merge branch 'main' into batch-integration-data

0f2aea4

change placeholder method to combat

283b0e1

pre-commit

6b68aa5

downstream pp

049e76b

reduce data correct import

8a91ada

Merge branch 'batch-integration-data' of github.com:danielStrobl/Sing…

f18102b

…leCellOpenProblems into batch-integration-data

pre-commit

cb28d48

Merge branch 'main' into batch-integration-data

f865ead

danielStrobl requested a review from LuckyMD May 10, 2022 14:59

LuckyMD added 2 commits May 11, 2022 00:47

grammar

c3ea3de

removed random and

c709fdc

LuckyMD approved these changes May 10, 2022

View reviewed changes

danielStrobl and others added 3 commits May 11, 2022 11:59

addressing comments

e1bad08

Merge branch 'batch-integration-data' of github.com:danielStrobl/Sing…

8c025b4

…leCellOpenProblems into batch-integration-data

Merge branch 'main' into batch-integration-data

ea1adef

danielStrobl merged commit afafab4 into openproblems-bio:main May 11, 2022

rcannood pushed a commit that referenced this pull request Sep 4, 2024

Update processing dataset metadata (#355)

3a811a7

* Update with to accomodate multimodal data * rename bash script

rcannood pushed a commit that referenced this pull request Sep 4, 2024

Update processing dataset metadata (#355)

04f2706

* Update with to accomodate multimodal data * rename bash script Former-commit-id: 3a811a7

Conversation

danielStrobl commented Apr 13, 2022 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Submission type

Testing

Submission guidelines

PR review checklist

Uh oh!

LuckyMD left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

LuckyMD commented Apr 13, 2022

Uh oh!

codecov-commenter commented Apr 20, 2022 • edited by codecov Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

scottgigante-immunai commented May 4, 2022

Uh oh!

danielStrobl commented May 4, 2022

Uh oh!

scottgigante-immunai commented May 4, 2022

Uh oh!

danielStrobl commented May 5, 2022

Uh oh!

danielStrobl commented May 5, 2022

Uh oh!

scottgigante-immunai commented May 5, 2022 via email

Uh oh!

LuckyMD left a comment

Choose a reason for hiding this comment

Uh oh!

LuckyMD May 10, 2022

Choose a reason for hiding this comment

Uh oh!

LuckyMD May 10, 2022

Choose a reason for hiding this comment

Uh oh!

LuckyMD May 10, 2022

Choose a reason for hiding this comment

Uh oh!

LuckyMD May 10, 2022

Choose a reason for hiding this comment

Uh oh!

LuckyMD May 10, 2022

Choose a reason for hiding this comment

Uh oh!

LuckyMD May 10, 2022

Choose a reason for hiding this comment

Uh oh!

scottgigante-immunai commented May 11, 2022

Uh oh!

LuckyMD commented May 11, 2022

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

danielStrobl commented Apr 13, 2022 •

edited

Loading

codecov-commenter commented Apr 20, 2022 •

edited by codecov Bot

Loading