feat: stalign with a fit apply pattern. Also foundation for imputation by selmanozleyen · Pull Request #1195 · scverse/squidpy

selmanozleyen · 2026-06-01T08:21:50Z

Continuation of #1162

for more information, see https://pre-commit.ci

…leyen/squidpy into feat/spatial_neighbours

for more information, see https://pre-commit.ci

…leyen/squidpy into feat/spatial_neighbours

for more information, see https://pre-commit.ci

…leyen/squidpy into feat/spatial_neighbours

for more information, see https://pre-commit.ci

…leyen/squidpy into feat/spatial_neighbours

codecov · 2026-06-11T08:39:19Z

Codecov Report

❌ Patch coverage is 45.00000% with 308 lines in your changes missing coverage. Please review.
✅ Project coverage is 74.71%. Comparing base (55572c4) to head (30e14cf).

Files with missing lines	Patch %	Lines
...ntal/_methods/align_samples/_stalign_impl/_core.py	0.00%	156 Missing ⚠️
...l/_methods/align_samples/_stalign_impl/_helpers.py	0.00%	73 Missing ⚠️
...tal/_methods/align_samples/_stalign_impl/_tools.py	51.94%	37 Missing ⚠️
...experimental/_methods/align_landmarks/_landmark.py	84.12%	6 Missing and 4 partials ⚠️
...py/experimental/_methods/align_samples/_stalign.py	37.50%	9 Missing and 1 partial ⚠️
src/squidpy/experimental/tl/_align/_api.py	72.22%	9 Missing and 1 partial ⚠️
src/squidpy/experimental/_methods/_protocols.py	66.66%	2 Missing and 3 partials ⚠️
src/squidpy/experimental/tl/_align/_io.py	93.90%	3 Missing and 2 partials ⚠️
src/squidpy/experimental/_methods/_registry.py	94.59%	1 Missing and 1 partial ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1195      +/-   ##
==========================================
- Coverage   76.55%   74.71%   -1.84%     
==========================================
  Files          63       73      +10     
  Lines        9067     9627     +560     
  Branches     1521     1590      +69     
==========================================
+ Hits         6941     7193     +252     
- Misses       1541     1837     +296     
- Partials      585      597      +12

Files with missing lines	Coverage Δ
src/squidpy/experimental/_methods/_families.py	`100.00% <100.00%> (ø)`
src/squidpy/experimental/_methods/_registry.py	`94.59% <94.59%> (ø)`
src/squidpy/experimental/_methods/_protocols.py	`66.66% <66.66%> (ø)`
src/squidpy/experimental/tl/_align/_io.py	`93.90% <93.90%> (ø)`
...experimental/_methods/align_landmarks/_landmark.py	`84.12% <84.12%> (ø)`
...py/experimental/_methods/align_samples/_stalign.py	`37.50% <37.50%> (ø)`
src/squidpy/experimental/tl/_align/_api.py	`72.22% <72.22%> (ø)`
...tal/_methods/align_samples/_stalign_impl/_tools.py	`51.94% <51.94%> (ø)`
...l/_methods/align_samples/_stalign_impl/_helpers.py	`0.00% <0.00%> (ø)`
...ntal/_methods/align_samples/_stalign_impl/_core.py	`0.00% <0.00%> (ø)`

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

timtreis · 2026-06-16T13:49:56Z

+    "AlignResult",
+    "StitchParams",
+    "TilingQCParams",
+  "assign_stitch_groups",


timtreis · 2026-06-16T13:52:03Z

+            # element we register a transform on so `output_mode="copy"` leaves the input untouched.
+            element = sd_deepcopy(element)
+            getattr(out, etype)[name] = element
+        set_transformation(element, sd_affine, to_coordinate_system=target_cs)


breaks if the element already has a transformation, you need to Sequence them

existing = get_transformation(element, to_coordinate_system=moving_cs) set_transformation(element, Sequence([existing, sd_affine]), to_coordinate_system=target_cs)

timtreis · 2026-06-16T13:53:19Z

+    radius = int(np.ceil(float(np.max(blur_values)) * 4.0))
+    denom = 2.0 * (dx * blur_values * 2.0) ** 2
+
+    for x_i, y_i in zip(x, y, strict=False):


How many points do we have? Should probably rasterize

timtreis · 2026-06-16T13:54:28Z

+    p: float = 2.0,
+    expand: float = 2.0,
+    nt: int = 3,
+    niter: int = 5000,


Can we do some form of early stopping or do we always have to train for 5k steps? Might be too much/too little depending on data

timtreis · 2026-06-16T13:55:29Z

+    return data_ref.tables[ref_key], sdata_query.tables[query_key], sdata_query, query_key
+
+
+def get_coords(adata: AnnData, spatial_key: str) -> np.ndarray:


Claude:

get_coords materializes coords up to 3× per align() (_io.py:71; called at _api.py:83,84 and again _io.py:97). np.asarray(..., dtype=float) forces a float64 copy each time. Thread the already-computed query_xy into writeback_obs and avoid the forced upcast when the array is already suitable.

timtreis · 2026-06-16T13:56:32Z

  "zarr>=3",
 ]
+optional-dependencies.jax = [
+  "jax",


Shouldn't we have some lower bound?

selmanozleyen and others added 30 commits April 2, 2026 13:06

init

5c08081

doc clarifications

5847d84

don't expose the builders

179ba06

[pre-commit.ci] auto fixes from pre-commit.com hooks

e187aba

for more information, see https://pre-commit.ci

deduplicate

cdb5699

Merge branch 'feat/spatial_neighbours' of https://github.com/selmanoz…

847a46b

…leyen/squidpy into feat/spatial_neighbours

[pre-commit.ci] auto fixes from pre-commit.com hooks

69cda1a

for more information, see https://pre-commit.ci

arrange builders

fddc027

Merge branch 'feat/spatial_neighbours' of https://github.com/selmanoz…

a30988a

…leyen/squidpy into feat/spatial_neighbours

better behaviour

f194b10

move classes

ae1eba1

Merge branch 'main' into feat/spatial_neighbours

a86572b

cleanup

039b852

Merge branch 'feat/spatial_neighbours' of https://github.com/selmanoz…

4699993

…leyen/squidpy into feat/spatial_neighbours

[pre-commit.ci] auto fixes from pre-commit.com hooks

b5dcf9f

for more information, see https://pre-commit.ci

add docs

4c11adf

Merge branch 'feat/spatial_neighbours' of https://github.com/selmanoz…

2b937e9

…leyen/squidpy into feat/spatial_neighbours

remove leftover

ea1ce93

resolution in reolve func

ebb7fd5

reduce dup code

69a9394

deprecate invalid n_neighs

77755ed

expose new functions and deprecate the flat one

d8a8145

move branches to classes

2e75b3f

[pre-commit.ci] auto fixes from pre-commit.com hooks

8c1c2ef

for more information, see https://pre-commit.ci

remove radius abstraction

268d30c

Merge branch 'feat/spatial_neighbours' of https://github.com/selmanoz…

3f41243

…leyen/squidpy into feat/spatial_neighbours

add extensibility page

aa9734a

unprivate methods and add extensibility page

67bad43

give a better example

65fa245

apply signature suggestion

85bfdeb

selmanozleyen added 17 commits June 8, 2026 10:03

rename file and refactor

c9eb7e4

move files

77f3e7d

fix imports

57f9d21

fixes

5d69264

remove bloat code

6587efe

typr hints

e45e247

add tests

beb1476

reduce bloat

5eeb95d

reduce bloat

3c2ed02

remove useless file

1ea9996

fix

ee741ab

undo rasterize changes

ba91e4f

doc landmark

1d65f4a

remove bloat

a3da05a

docs

373ca02

doc debloatr

aaf48c7

expose result classes

4387a61

selmanozleyen requested a review from timtreis June 8, 2026 09:44

selmanozleyen added 2 commits June 11, 2026 10:25

refactoring, testing, typing and bug fix on copy mode

85df8fc

landmark is positional only now

599186f

selmanozleyen and others added 3 commits June 11, 2026 11:14

expose api

8cfc770

Merge branch 'main' into feat/experimental-fit-core

96bc445

Merge branch 'main' into feat/experimental-fit-core

30e14cf

timtreis reviewed Jun 16, 2026

View reviewed changes

Comment thread pyproject.toml

"zarr>=3",

]

optional-dependencies.jax = [

"jax",

timtreis Jun 16, 2026

Copy link
Copy Markdown

Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shouldn't we have some lower bound?

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: stalign with a fit apply pattern. Also foundation for imputation#1195

feat: stalign with a fit apply pattern. Also foundation for imputation#1195
selmanozleyen wants to merge 121 commits into
scverse:mainfrom
selmanozleyen:feat/experimental-fit-core

selmanozleyen commented Jun 1, 2026

Uh oh!

codecov Bot commented Jun 11, 2026 •

edited

Loading

Uh oh!

timtreis Jun 16, 2026

Uh oh!

timtreis Jun 16, 2026

Uh oh!

timtreis Jun 16, 2026

Uh oh!

timtreis Jun 16, 2026

Uh oh!

timtreis Jun 16, 2026 •

edited

Loading

Uh oh!

timtreis Jun 16, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

		return data_ref.tables[ref_key], sdata_query.tables[query_key], sdata_query, query_key


		def get_coords(adata: AnnData, spatial_key: str) -> np.ndarray:

Conversation

selmanozleyen commented Jun 1, 2026

Uh oh!

codecov Bot commented Jun 11, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

timtreis Jun 16, 2026

Choose a reason for hiding this comment

Uh oh!

timtreis Jun 16, 2026

Choose a reason for hiding this comment

Uh oh!

timtreis Jun 16, 2026

Choose a reason for hiding this comment

Uh oh!

timtreis Jun 16, 2026

Choose a reason for hiding this comment

Uh oh!

timtreis Jun 16, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

timtreis Jun 16, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

codecov Bot commented Jun 11, 2026 •

edited

Loading

timtreis Jun 16, 2026 •

edited

Loading