Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Holistic normalization, feat selection, dimreduction, (iterative) lsi implementation #189

Open
wants to merge 64 commits into
base: main
Choose a base branch
from
Open
Changes from 1 commit
Commits
Show all changes
64 commits
Select commit Hold shift + click to select a range
1ef6091
[r] add tf-idf and log normalization functions
immanuelazn Dec 12, 2024
98675d0
[r] fix normalization tests
immanuelazn Dec 12, 2024
2f83ae6
[r] add in requested changes
immanuelazn Dec 14, 2024
6381f74
[r] removed unused variable
immanuelazn Dec 14, 2024
8e80dc5
[r] add feature selection methods
immanuelazn Dec 15, 2024
c50ead2
[r] update select_features_by_dispersion() to reflect archr defaults
immanuelazn Jan 10, 2025
13c3760
[r] add lsi, var feature selection
immanuelazn Oct 31, 2024
36a8983
[r] add lsi, variable feature selection
immanuelazn Nov 4, 2024
2be2efe
[r] parametrize z_score_norm, create temp option to return more info …
immanuelazn Nov 7, 2024
dccc3a5
[r] add test case for LSI comparing to archr
immanuelazn Nov 7, 2024
183dd40
[r] clean up var gene selection, lsi docstring
immanuelazn Nov 7, 2024
4972f34
[r] add variable gene selection test
immanuelazn Nov 7, 2024
e4d5cb0
[r] provide more colour to scanpy feat selection test
immanuelazn Nov 7, 2024
99470e0
[r] cleanup real data tests
immanuelazn Nov 7, 2024
3bf8914
[r] clean up lsi, var features docstrings
immanuelazn Nov 8, 2024
a7c6179
[r] add in more lsi real data tests
immanuelazn Nov 8, 2024
acf35b2
[r] remove unused variable from `lsi()`
immanuelazn Nov 18, 2024
47256db
[r] add requested changes
immanuelazn Dec 2, 2024
004499a
[r] fix requested changes
immanuelazn Dec 2, 2024
dd80165
[r] fix lsi docstring, idf_ logic
immanuelazn Dec 3, 2024
8891981
[r] replace z-score norm with corr cutoffs
immanuelazn Dec 7, 2024
1e7c6d0
[r] update LSI to use norm, feature selection helpers
immanuelazn Jan 9, 2025
e9c302e
[r] update `NEWS.md`
immanuelazn Jan 10, 2025
7ed6bd7
[r] remove test artifacts
immanuelazn Jan 10, 2025
199ae82
Update docs
bnprks Jan 11, 2025
2911cf1
Merge branch 'main' into ia/normalizations
bnprks Jan 11, 2025
553f262
Update NEWS
bnprks Jan 11, 2025
7511f0b
Update docs
bnprks Jan 11, 2025
d67b7db
[r] add logging, partial args
immanuelazn Jan 13, 2025
435724b
[r] add partial args to normalizations
immanuelazn Jan 14, 2025
8dbe8e5
[r] create mechanism for partial calls on explicit args
immanuelazn Jan 14, 2025
21af3f9
Merge branch 'ia/normalizations' into ia/feature-selection
immanuelazn Jan 14, 2025
067b540
[r] add partial calls, update feature selection docs
immanuelazn Jan 14, 2025
5e49504
Update docs
bnprks Jan 11, 2025
453215f
[ci] add update to apt-get (#164)
immanuelazn Dec 17, 2024
3c99a01
[r] Fix articles index to include manuscript draft (#170)
bnprks Dec 17, 2024
5a8a335
[r] Fix type confusion in `pseudobulk_matrix()` and clean up `paralle…
bnprks Dec 21, 2024
8e0603b
[r] 0.3.0 release announcement (#177)
bnprks Dec 22, 2024
4391202
[r] Improve error printing in `call_peaks_macs` (#175)
bnprks Jan 9, 2025
f1232b0
[r][cpp] Support writing AnnData dense matrices (#166)
ycli1995 Jan 9, 2025
bb7f5e2
Update NEWS
bnprks Jan 11, 2025
765a0cb
Update docs
bnprks Jan 11, 2025
3a33209
[r] add partial args to normalizations
immanuelazn Jan 14, 2025
891868c
[r] create mechanism for partial calls on explicit args
immanuelazn Jan 14, 2025
00922d7
[r] add partial calls, update feature selection docs
immanuelazn Jan 14, 2025
4e27f5d
[r] add lsi, variable feature selection
immanuelazn Nov 4, 2024
ebebad4
[r] update LSI to use norm, feature selection helpers
immanuelazn Jan 9, 2025
b1ab04c
[r] add iterative LSI implementation
immanuelazn Jan 10, 2025
1ae19b2
Merge branch 'ia/feature-selection' into ia/lsi
immanuelazn Jan 18, 2025
76f4c7d
[r] change check for `pseudobulk_matrix()` to use whole number instea…
immanuelazn Jan 10, 2025
5e3a7fe
[r] update feature selection documentation
immanuelazn Jan 18, 2025
2e11ccd
Merge branch 'ia/lsi' into ia/lsi-iterative
immanuelazn Jan 18, 2025
16d5344
[r] reorder assertions, add new partial func system
immanuelazn Jan 24, 2025
87eb430
[r] change behaviour of num_feats default args, write docs
immanuelazn Jan 24, 2025
613b0df
Merge branch 'ia/feature-selection' into ia/lsi
immanuelazn Jan 24, 2025
6c4285b
[r] fix binned dispersion naming
immanuelazn Jan 25, 2025
69eea78
Merge branch 'ia/lsi' into ia/lsi-iterative
immanuelazn Jan 25, 2025
04f67f2
[r] change normalize text for feature selection
immanuelazn Jan 25, 2025
4d17557
[r] add iterative LSI
immanuelazn Jan 27, 2025
5289f39
[r] add rcpphnsw to imports
immanuelazn Jan 27, 2025
19e96d3
[r] fix num_feats logic in feature selection
immanuelazn Jan 27, 2025
eefb33d
[r] add blurb about partials in normalize
immanuelazn Jan 27, 2025
e010069
[r] update NEWS
immanuelazn Jan 27, 2025
1265088
[r] update feature selection docs
immanuelazn Jan 27, 2025
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
[r] remove test artifacts
immanuelazn committed Jan 10, 2025
commit 7ed6bd7d59074faaef6016a431acff31e3d5a2ba
5 changes: 3 additions & 2 deletions r/tests/testthat/test-singlecell_utils.R
Original file line number Diff line number Diff line change
@@ -192,11 +192,11 @@ test_that("Feature selection by bin variance works", {
# Test only that outputs are reasonable. There is a full comparison in `tests/real_data/` that compares implementation to Seurat
res_table <- select_features_by_bin_variance(mat, num_feats = 10, n_bins = 5, threads = 1)
res_table_t <- select_features_by_bin_variance(t(mat), num_feats = 10, n_bins = 5, threads = 1)
browser()
res_feats <- res_table %>% dplyr::filter(highly_variable) %>% dplyr::pull(names)
res <- mat[res_feats,]
res_feats_t <- res_table_t %>% dplyr::filter(highly_variable) %>% dplyr::pull(names)
res_t <- t(mat[,res_feats_t])

expect_equal(nrow(res), 10)
expect_equal(ncol(res), 26)
expect_equal(nrow(res_t), 10)
@@ -220,4 +220,5 @@ test_that("LSI works", {
expect_equal(nrow(lsi_res_t), 5)
expect_equal(ncol(lsi_res_t), nrow(mat))
expect_equal(lsi_res, lsi_res_proj)
})
})