Add GitHub Actions CI and release workflows

.Rbuildignore

@@ -6,3 +6,4 @@ README.md
 tests/*
 ^\.positai$
 ^\.claude$
+^\.github$

.github/workflows/R-CMD-check.yaml

@@ -0,0 +1,70 @@
+# Continuous integration: R CMD check on Linux, macOS and Windows.
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+  workflow_dispatch:
+
+name: R-CMD-check
+
+permissions: read-all
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  R-CMD-check:
+    runs-on: ${{ matrix.config.os }}
+
+    name: ${{ matrix.config.os }} (${{ matrix.config.r }})
+
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - {os: macos-latest,   r: 'release'}
+          - {os: windows-latest, r: 'release'}
+          - {os: ubuntu-latest,  r: 'devel', http-user-agent: 'release'}
+          - {os: ubuntu-latest,  r: 'release'}
+          - {os: ubuntu-latest,  r: 'oldrel-1'}
+
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+      R_KEEP_PKG_SOURCE: yes
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: r-lib/actions/setup-pandoc@v2
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          r-version: ${{ matrix.config.r }}
+          http-user-agent: ${{ matrix.config.http-user-agent }}
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::rcmdcheck
+          needs: check
+
+      - uses: r-lib/actions/check-r-package@v2
+        with:
+          upload-snapshots: true
+          build_args: 'c("--no-manual","--compact-vignettes=gs+qpdf")'
+
+      # tests/ is excluded from the source tarball via .Rbuildignore, so
+      # R CMD check skips them; run the testthat suite from the repo instead.
+      # Install first: the parallel tests start future workers that attach the
+      # installed package, so pkgload::load_all() is not enough.
+      - name: Run testthat suite
+        shell: Rscript {0}
+        env:
+          NOT_CRAN: 'true'
+        run: |
+          options(testthat.progress.max_fails = Inf)
+          install.packages(".", repos = NULL, type = "source")
+          testthat::test_dir("tests/testthat", package = "SCORPION", load_package = "installed",
+                             stop_on_failure = TRUE,
+                             reporter = testthat::ProgressReporter$new(show_praise = FALSE))

.github/workflows/release.yaml

@@ -0,0 +1,93 @@
+# Continuous delivery: on a version tag, build and check the source
+# tarball, then attach it to a GitHub release.
+on:
+  push:
+    tags: ['v*', '[0-9]*']
+  workflow_dispatch:
+
+name: release
+
+permissions: read-all
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: r-lib/actions/setup-pandoc@v2
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::rcmdcheck
+          needs: check
+
+      # Tags may be written as 1.2.3, v1.2.3 or v.1.2.3.
+      - name: Verify tag matches DESCRIPTION version
+        if: startsWith(github.ref, 'refs/tags/')
+        run: |
+          pkg_version=$(grep '^Version:' DESCRIPTION | sed 's/Version:[[:space:]]*//')
+          tag_version=${GITHUB_REF_NAME#v}
+          tag_version=${tag_version#.}
+          if [ "$tag_version" != "$pkg_version" ]; then
+            echo "::error::Tag $GITHUB_REF_NAME does not match DESCRIPTION version $pkg_version"
+            exit 1
+          fi
+
+      # tests/ is excluded from the source tarball via .Rbuildignore, so
+      # run the testthat suite from the checkout before releasing.
+      # Install first: the parallel tests start future workers that attach the
+      # installed package, so pkgload::load_all() is not enough.
+      - name: Run testthat suite
+        shell: Rscript {0}
+        env:
+          NOT_CRAN: 'true'
+        run: |
+          install.packages(".", repos = NULL, type = "source")
+          testthat::test_dir("tests/testthat", package = "SCORPION", load_package = "installed",
+                             stop_on_failure = TRUE,
+                             reporter = testthat::ProgressReporter$new(show_praise = FALSE))
+
+      - name: Build source tarball
+        run: R CMD build --no-manual .
+
+      - name: Check source tarball
+        shell: Rscript {0}
+        run: |
+          tarball <- Sys.glob("*.tar.gz")
+          stopifnot(length(tarball) == 1)
+          rcmdcheck::rcmdcheck(tarball, args = c("--no-manual", "--as-cran"),
+                               error_on = "warning", check_dir = "check")
+
+      - uses: actions/upload-artifact@v4
+        with:
+          name: source-tarball
+          path: '*.tar.gz'
+          if-no-files-found: error
+
+  publish:
+    needs: build
+    if: startsWith(github.ref, 'refs/tags/')
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: source-tarball
+
+      - name: Create GitHub release
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          gh release create "$GITHUB_REF_NAME" *.tar.gz \
+            --repo "$GITHUB_REPOSITORY" \
+            --title "$GITHUB_REF_NAME" --generate-notes

R/runSCORPION.R

@@ -262,15 +262,21 @@ runSCORPION <- function(gexMatrix,
 
   # Removing batch effect
   if (removeBatchEffect) {
-    if (showProgress) {
-      cli::cli_alert_success("Correcting for batch effects")
-    }
     if (is.null(batch)) {
       cli::cli_abort('batch is needed for batch effect correction')
     }
-    mean_expr <- apply(gexMatrix, 1, median)
-    gexMatrix <- remove_batch(X = gexMatrix, batch = batch)
-    gexMatrix <- gexMatrix + mean_expr
+    if (length(unique(batch[!is.na(batch)])) < 2) {
+      # A single batch leaves nothing to correct; skip so the per-gene median
+      # is not added to uncorrected data.
+      cli::cli_alert_warning("batch has fewer than two levels; skipping batch effect correction")
+    } else {
+      if (showProgress) {
+        cli::cli_alert_success("Correcting for batch effects")
+      }
+      mean_expr <- apply(gexMatrix, 1, median)
+      gexMatrix <- remove_batch(X = gexMatrix, batch = batch)
+      gexMatrix <- gexMatrix + mean_expr
+    }
   }
   rm(batch)
 

README.md

@@ -1,5 +1,7 @@
 # <img src="https://raw.githubusercontent.com/kuijjerlab/SCORPION/main/inst/logoSCORPION.png" width="30" title="SCORPION"> SCORPION
 
+[![R-CMD-check](https://github.com/kuijjerlab/SCORPION/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/kuijjerlab/SCORPION/actions/workflows/R-CMD-check.yaml)
+
 **SCORPION** (**S**ingle-**C**ell **O**riented **R**econstruction of **P**ANDA **I**ndividually **O**ptimized Gene Regulatory **N**etworks) is an R package for constructing gene regulatory networks from single-cell and single-nucleus RNA sequencing data. The package addresses the sparsity inherent in single-cell expression data through coarse-graining, which aggregates similar cells to improve correlation structure detection. Network reconstruction is performed using the PANDA (Passing Attributes between Networks for Data Assimilation) message-passing algorithm, integrating transcription factor motifs, protein-protein interactions, and gene expression data. By using consistent baseline priors across samples, SCORPION produces comparable, fully-connected, weighted regulatory networks suitable for population-level analyses.
 
 

tests/testthat/test_data_preprocessing.R

@@ -77,3 +77,29 @@ test_that("runSCORPION() batch effect correction works with valid batch", {
   expect_true(is.data.frame(result))
   expect_true(all(c("tf", "target") %in% colnames(result)))
 })
+
+test_that("runSCORPION() skips batch correction when batch has a single level", {
+  data(scorpionTest)
+
+  args <- list(
+    gexMatrix = scorpionTest$gex,
+    tfMotifs = scorpionTest$tf,
+    ppiNet = scorpionTest$ppi,
+    cellsMetadata = scorpionTest$metadata,
+    groupBy = "region",
+    showProgress = FALSE
+  )
+
+  set.seed(1)
+  uncorrected <- do.call(runSCORPION, args)
+  set.seed(1)
+  expect_message(
+    single_batch <- do.call(runSCORPION, c(args, list(
+      removeBatchEffect = TRUE,
+      batch = rep("b1", ncol(scorpionTest$gex))
+    ))),
+    "fewer than two levels"
+  )
+
+  expect_equal(single_batch, uncorrected)
+})