Merge pull request #5 from maren-ha/muon

merge muon

.github/workflows/ci.yml

@@ -0,0 +1,33 @@
+# [.github/workflows/CI.yml]
+name: CI
+on:
+  push:
+    branches:
+      - main
+      - muon
+    tags: '*'
+  pull_request:
+jobs:
+  test:
+    name: Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        version:
+          - '1.7'
+        os:
+          - ubuntu-latest
+          - macOS-latest
+          # - windows-latest
+        arch:
+          - x64
+    steps:
+      - uses: actions/checkout@v1
+      - uses: julia-actions/setup-julia@latest
+        with:
+          version: ${{ matrix.version }}
+          arch: ${{ matrix.arch }}
+      - uses: julia-actions/julia-runtest@latest
+      - uses: julia-actions/julia-uploadcodecov@latest
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

Project.toml

@@ -14,6 +14,7 @@ HDF5 = "f67ccb44-e63f-5c2f-98bd-6dc0ccc4ba2f"
 JLD2 = "033835bb-8acc-5ee8-8aae-3f567f8a3819"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 Loess = "4345ca2d-374a-55d4-8d30-97f9976e7612"
+Muon = "446846d7-b4ce-489d-bf74-72da18fe3629"
 ProgressMeter = "92933f4c-e287-5a05-a399-4b506db050ca"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 SliceMap = "82cb661a-3f19-5665-9e27-df437c7e54c8"

README.md

@@ -1,6 +1,8 @@
 # README
 
 [![](https://img.shields.io/badge/docs-stable-blue.svg)](https://maren-ha.github.io/scVI.jl/)
+[![codecov](https://codecov.io/gh/maren-ha/scVI.jl/branch/muon/graph/badge.svg?token=OXHPY0EI3E)](https://codecov.io/gh/maren-ha/scVI.jl)
+![example workflow](https://github.com/maren-ha/scVI.jl/actions/workflows/ci.yml/badge.svg)
 
 ![](logo/scvi-julia-logo.jpg)
 
@@ -62,7 +64,7 @@ subset_to_hvg!(adata, n_top_genes=1200, verbose=true)
 library_log_means, library_log_vars = init_library_size(adata)
 
 # initialise scVAE model 
-m = scVAE(size(adata.countmatrix,2);
+m = scVAE(size(adata.X,2);
         library_log_means=library_log_means,
         library_log_vars=library_log_vars
 )
@@ -104,30 +106,14 @@ Runtests can be executed via
 Pkg.test("scVI")
 ```
 
-This checks whether basic functionality works: loads the PBMC dataset, initialises a `scVAE` model and start training (just 2 epochs for the sake of checking and faster runtime). Further tests to be added. 
+For details, see the `test` subfolder. For further information on code coverage, click on the badge at the top of this README or follow [this link](https://codecov.io/gh/maren-ha/scVI.jl). Some files are not yet fully covered, but this is being worked on.
 
 ------------
 ## TODO 
 
-- [x] deploy docs
-- [ ] write tests
-- [ ] integration of [`Muon.jl`](https://scverse.org/Muon.jl/dev/objects/) for data handling 
+- [ ] update docs (Muon.jl integration)
+- [ ] complete runtests
 - [ ] support `gene_batch` and `gene_label` dispersion 
 - [ ] support categorical covariates (e.g., batch information)
-- [x] turn `data` and `scvis` into submodules
-- [x] fix library size integration 
-- [x] add Gaussian generative distribution
-- [x] add Bernoulli generative distribution 
-- [x] refactor data processing
-	- [x] re-write `PBMC.jl`
-	- [x] re-write `Tasic.jl`
-	- [x] add preprocessing: 
-		- [x] log-transform 
-		- [x] sqrt-transform
-		- [x] re-scaling
-		- [x] PCA
-		- [x] UMAP 
-		- [x] filtering
-	- [x]  add docstrings
 
 Contributions, reporting of bugs and unexpected behaviour, missing functionalities, etc. are all very welcome, please do get in touch!

src/data/FileIO.jl → data/FileIO.jl

@@ -144,7 +144,7 @@ write_h5ad(adata, "output.h5")
 """
 function write_h5ad(adata::AnnData, filename::String)
     file = h5open(filename, "w")
-    file["countmatrix"] = adata.countmatrix
+    file["countmatrix"] = adata.X
     for field in fieldnames(typeof(adata))
         if (field ∈ [:countmatrix, :celltypes]) || (isnothing(getfield(adata, field)))
             continue

data/Tasic_celltypes.txt

@@ -0,0 +1,21 @@
+Vip	Mybpc1
+L4	Ctxn3
+L2/3	Ptgs2
+L2	Ngb
+Pvalb	Gpx3
+Ndnf	Cxcl14
+L5a	Batf3
+SMC	Myl9
+Astro	Aqp4
+L5	Ucma
+Micro	Ctss
+Endo	Xdh
+Sst	Cbln4
+L6b	Serpinb11
+Sncg	
+Igtp	
+Oligo	96*Rik
+Smad3	
+OPC	Pdgfra
+L5b	Tph2
+L6a	Sla