Merge pull request #201 from DendrouLab/fc_cipy

Fc_ added integration01

.github/workflows/integration01-ci.yml

@@ -0,0 +1,100 @@
+name: Run integration01
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+env:
+  debug: 'true'
+
+jobs:
+  integration:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        os: ["ubuntu-latest"] # , "macos-latest", "windows-latest"
+        python-version: ["3.10"]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: File tree
+        if: env.debug == 'true'
+        run: tree
+
+      - uses: conda-incubator/setup-miniconda@v3
+        with:
+          miniforge-version: latest
+          auto-activate-base: true
+          auto-update-conda: true
+          channels: conda-forge
+          channel-priority: strict
+          activate-environment: pipeline_env
+          environment-file: pipeline_env.yaml
+# important: this patch is only to test if multivi integration works
+# issues are not related to panpipes https://discourse.scverse.org/t/error-when-training-model-on-m3-max-mps/1896/2
+# https://discourse.scverse.org/t/macbook-m1-m2-mps-acceleration-with-scvi/2075/4
+      - name: Install Panpipes
+        shell: bash -el {0}
+        run: |
+          pip install '.[multivipatch]' 
+          conda list
+
+      - name: Conda info
+        if: env.debug == 'true'
+        shell: bash -el {0}
+        run: conda info
+
+      - name: Conda list
+        if: env.debug == 'true'
+        shell: pwsh
+        run: conda list
+
+      # Note: all three files are renamed during the download to trim the "subsample_" prefix
+      - name: Preparing the data
+        run: |
+          mkdir -p teaseq/integration && cd teaseq/integration
+          curl -L -o teaseq.h5mu https://figshare.com/ndownloader/files/44796985
+
+      # Note: we run the following to test that the commands works
+      # However, the following task will replacing the file anyway
+      - name: Preparing the configuration file
+        shell: bash -el {0}
+        run: |
+          cd teaseq/integration
+          panpipes integration config
+
+      - name: Edit the submission file
+        run: |
+          cd teaseq/integration
+          curl -o pipeline.yml https://raw.githubusercontent.com/DendrouLab/panpipes/main/tests/integration_1/pipeline.yml  
+
+      - name: Replace template contents in configuration file
+        run: |
+          cd teaseq/integration
+          sed -i 's+/Users/fabiola.curion/Documents/devel/miniconda3/envs/pipeline_env+pipeline_env+g' pipeline.yml
+
+      - name: File tree
+        if: env.debug == 'true'
+        run: tree teaseq
+
+      - name: Review pipeline tasks
+        shell: bash -el {0}
+        run: |
+          cd teaseq/integration
+          panpipes integration show full --local
+
+      - name: Run pipeline tasks
+        shell: bash -el {0}
+        run: |
+          cd teaseq/integration
+          panpipes integration make full --local
+
+      - name: File tree
+        if: env.debug == 'true'
+        run: tree teaseq

panpipes/python_scripts/batch_correct_multivi.py

@@ -57,7 +57,7 @@
 sc.settings.autoshow = False
 sc.settings.figdir = args.figdir
 
-
+scvi.settings.seed = 1492
 # load parameters
 
 threads_available = multiprocessing.cpu_count()
@@ -71,17 +71,19 @@
 # ------------------------------------------------------------------
 L.info("Running multivi")
 
-# mdata = mu.read(args.scaled_anndata)
-# rna = mdata['rna'].copy()
-# atac = mdata['atac'].copy()
-rna= mu.read(args.scaled_anndata +"/" + "rna")
-atac= mu.read(args.scaled_anndata +"/" + "atac")
+mdata = mu.read(args.scaled_anndata)
+rna = mdata['rna'].copy()
+atac = mdata['atac'].copy()
 
+del mdata
 
 if check_for_bool(params["multimodal"]["MultiVI"]["lowmem"]):
-    L.info("subsetting atac to top 25k HVF")
+    if 'hvg' in atac.uns.keys():
+        L.info("subsetting atac to top HVF")
+        atac = atac[:, atac.var.highly_variable].copy()
+    L.info("calculating and subsetting atac to top 25k HVF")
     sc.pp.highly_variable_genes(atac, n_top_genes=25000)
-    atac = atac[:, atac.var.highly_variable]
+    atac = atac[:, atac.var.highly_variable].copy()
 
 
 
@@ -126,6 +128,15 @@
 L.info("concatenating modalities to comply with multiVI")
 # adata_paired = ad.concat([rna, atac], join="outer")
 # adata_paired.var = pd.concat([rna.var,atac.var])
+if rna.is_view:
+    L.info("RNA is view")
+    atac = rna.copy()
+if atac.is_view:
+    L.info("ATAC is view")
+    atac = atac.copy()
+
+L.info(atac.is_view)
+
 
 adata_paired = ad.concat([rna.T, atac.T]).T
 
@@ -223,14 +234,14 @@
     multivi_training_args={}
 else:
     multivi_training_args =  {k: v for k, v in params["multimodal"]['MultiVI']['training_args'].items() if v is not None}
-
+L.info("multivi training args")
 print(multivi_training_args)
 
 if params["multimodal"]['MultiVI']['training_plan'] is None:
     multivi_training_plan = {}
 else:
     multivi_training_plan =  {k: v for k, v in params["multimodal"]['MultiVI']['training_plan'].items() if v is not None}
-
+L.info("multivi training plan")
 print(multivi_training_plan)
 
 mvi.view_anndata_setup()

pyproject.toml

@@ -66,6 +66,11 @@ spatial = [
     "cell2location",
     "tangram-sc"
 ]
+
+multivipatch = [
+    "scvi-tools<=0.20.3",
+    "requests"
+]
 [project.scripts]
 panpipes = "panpipes:entry.main"