Merge pull request #946 from jashapiro/jashapiro/seurat-convert

Initiate `seurat-conversion`

.github/workflows/docker_seurat-conversion.yml

@@ -0,0 +1,63 @@
+# This is a workflow to build the docker image for the seurat-conversion module
+#
+# Docker modules are run on pull requests when code for files that affect the Docker image have changed.
+# If other files are used during the Docker build, they should be added to `paths`
+#
+# At module initialization, this workflow is inactive, and needs to be activated manually
+
+name: Build docker image for seurat-conversion
+
+concurrency:
+  # only one run per branch at a time
+  group: "docker_seurat-conversion_${{ github.ref }}"
+  cancel-in-progress: true
+
+on:
+  # pull_request:
+  #   branches:
+  #     - main
+  #   paths:
+  #     - "analyses/seurat-conversion/Dockerfile"
+  #     - "analyses/seurat-conversion/.dockerignore"
+  #     - "analyses/seurat-conversion/renv.lock"
+  #     - "analyses/seurat-conversion/conda-lock.yml"
+  # push:
+  #   branches:
+  #     - main
+  #   paths:
+  #     - "analyses/seurat-conversion/Dockerfile"
+  #     - "analyses/seurat-conversion/.dockerignore"
+  #     - "analyses/seurat-conversion/renv.lock"
+  #     - "analyses/seurat-conversion/conda-lock.yml"
+  workflow_dispatch:
+    inputs:
+      push-ecr:
+        description: "Push to AWS ECR"
+        type: boolean
+        required: true
+
+jobs:
+  test-build:
+    name: Test Build Docker Image
+    if: github.event_name == 'pull_request' || (contains(github.event_name, 'workflow_') && !inputs.push-ecr)
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build image
+        uses: docker/build-push-action@v5
+        with:
+          context: "{{defaultContext}}:analyses/seurat-conversion"
+          push: false
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+  build-push:
+    name: Build and Push Docker Image
+    if: github.repository_owner == 'AlexsLemonade' && (github.event_name == 'push' || inputs.push-ecr)
+    uses: ./.github/workflows/build-push-docker-module.yml
+    with:
+      module: "seurat-conversion"
+      push-ecr: true

.github/workflows/run_seurat-conversion.yml

@@ -0,0 +1,62 @@
+# This is a workflow to run the seurat-conversion module
+#
+# Analysis modules are run based on three triggers:
+# - Manual trigger
+# - On pull requests where code in the module has changed
+# - As a reusable workflow called from a separate workflow which periodically runs all modules
+#
+# At initialization, only the manual trigger is active
+
+name: Run seurat-conversion analysis module
+env:
+  MODULE_PATH: analyses/seurat-conversion
+  AWS_DEFAULT_REGION: us-east-2
+
+concurrency:
+  # only one run per branch at a time
+  group: "run_seurat-conversion_${{ github.ref }}"
+  cancel-in-progress: true
+
+on:
+  workflow_dispatch:
+  # workflow_call:
+  # pull_request:
+  #   branches:
+  #     - main
+  #   paths:
+  #     - analyses/seurat-conversion/**
+  #     - "!analyses/seurat-conversion/Dockerfile"
+  #     - "!analyses/seurat-conversion/.dockerignore"
+  #     - .github/workflows/run_seurat-conversion.yml
+
+jobs:
+  run-module:
+    if: github.repository_owner == 'AlexsLemonade'
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+
+      - name: Set up R
+        uses: r-lib/actions/setup-r@v2
+        with:
+          r-version: 4.4.0
+          use-public-rspm: true
+
+      - name: Set up pandoc
+        uses: r-lib/actions/setup-pandoc@v2
+
+      - name: Set up renv
+        uses: r-lib/actions/setup-renv@v2
+        with:
+          working-directory: ${{ env.MODULE_PATH }}
+
+      # Update this step as needed to download the desired data
+      - name: Download test data
+        run: ./download-data.py --test-data --format SCE
+
+      - name: Run analysis module
+        run: |
+          cd ${MODULE_PATH}
+          # run module script(s) here

analyses/seurat-conversion/.Rprofile

@@ -0,0 +1,4 @@
+# Don't activate renv in an OpenScPCA docker image
+if (Sys.getenv('OPENSCPCA_DOCKER') != 'TRUE') {
+  source('renv/activate.R')
+}

analyses/seurat-conversion/.dockerignore

@@ -0,0 +1,8 @@
+# Ignore everything by default
+*
+
+# Include specific files in the docker environment
+!/renv.lock
+!/requirements.txt
+!/environment.yml
+!/conda-lock.yml

analyses/seurat-conversion/.gitignore

@@ -0,0 +1,7 @@
+# Results should not be committed
+/results/*
+!/results/README.md
+
+# Ignore the scratch directory (but keep it present)
+/scratch/*
+!/scratch/.gitkeep

analyses/seurat-conversion/Dockerfile

@@ -0,0 +1,26 @@
+# A template docker file for creating a new analysis
+# Docker image for the hello-R analysis
+FROM bioconductor/r-ver:3.19
+
+# Labels following the Open Containers Initiative (OCI) recommendations
+# For more information, see https://specs.opencontainers.org/image-spec/annotations/?v=v1.0.1
+LABEL org.opencontainers.image.authors="OpenScPCA [email protected]"
+LABEL org.opencontainers.image.source="https://github.com/AlexsLemonade/OpenScPCA-analysis/tree/main/analyses/seurat-conversion"
+
+# Set an environment variable to allow checking if we are in an OpenScPCA container
+ENV OPENSCPCA_DOCKER=TRUE
+
+# Install renv to enable later package installation
+RUN Rscript -e "install.packages('renv')"
+
+# Disable the renv cache to install packages directly into the R library
+ENV RENV_CONFIG_CACHE_ENABLED=FALSE
+
+# Copy the renv.lock file from the host environment to the image
+COPY renv.lock renv.lock
+
+# restore from renv.lock file and clean up to reduce image size
+RUN Rscript -e 'renv::restore()' && \
+  rm -rf ~/.cache/R/renv && \
+  rm -rf /tmp/downloaded_packages && \
+  rm -rf /tmp/Rtmp*

analyses/seurat-conversion/README.md

@@ -0,0 +1,33 @@
+# Seurat conversion
+
+This analysis module is used to convert the SingleCellExperiment objects from the ScPCA Portal to Seurat objects.
+
+## Description
+
+Please provide a description of your module, including:
+
+- What type of analysis is included?
+- What methods or tools are used?
+
+If there are multiple steps in the module, please include an outline of the analysis steps and scripts used.
+
+## Usage
+
+TBD
+
+## Input files
+
+Input modules will be a SingleCellExperiment objects (as `.rds` files) from the ScPCA Portal.
+
+
+## Output files
+
+Seurat object files (as `.rds` files) will be generated as output, organized by project.
+
+## Software requirements
+
+The code for the project will be in R, so all software dependencies will be managed by `renv`.
+
+## Computational resources
+
+The only computational requirements should be sufficient RAM to load the SingleCellExperiment objects and resulting Seurat objects into memory.

analyses/seurat-conversion/components/dependencies.R

@@ -0,0 +1,2 @@
+# R dependencies not captured by `renv`
+# library("missing_package")

analyses/seurat-conversion/renv.lock

@@ -0,0 +1,46 @@
+{
+  "R": {
+    "Version": "4.4.0",
+    "Repositories": [
+      {
+        "Name": "BioCsoft",
+        "URL": "https://bioconductor.org/packages/3.19/bioc"
+      },
+      {
+        "Name": "BioCann",
+        "URL": "https://bioconductor.org/packages/3.19/data/annotation"
+      },
+      {
+        "Name": "BioCexp",
+        "URL": "https://bioconductor.org/packages/3.19/data/experiment"
+      },
+      {
+        "Name": "BioCworkflows",
+        "URL": "https://bioconductor.org/packages/3.19/workflows"
+      },
+      {
+        "Name": "BioCbooks",
+        "URL": "https://bioconductor.org/packages/3.19/books"
+      },
+      {
+        "Name": "CRAN",
+        "URL": "https://p3m.dev/cran/latest"
+      }
+    ]
+  },
+  "Bioconductor": {
+    "Version": "3.19"
+  },
+  "Packages": {
+    "renv": {
+      "Package": "renv",
+      "Version": "1.0.11",
+      "Source": "Repository",
+      "Repository": "CRAN",
+      "Requirements": [
+        "utils"
+      ],
+      "Hash": "47623f66b4e80b3b0587bc5d7b309888"
+    }
+  }
+}

analyses/seurat-conversion/renv/.gitignore

@@ -0,0 +1,7 @@
+library/
+local/
+cellar/
+lock/
+python/
+sandbox/
+staging/