From 06cb10cbc16371dd8fda39e8544155e27ea8577e Mon Sep 17 00:00:00 2001
From: Chananchida Sang-aram VSCODE <sai.chananchida@gmail.com>
Date: Thu, 3 Oct 2024 09:00:33 +0200
Subject: [PATCH] split up c2l; skip test for dstg due to stochasticity

---
 .../test_run_dataset_cell2location.yml        | 69 +++++++++++++++++++
 .github/workflows/test_run_dataset_python.yml |  4 +-
 unit-test/test_run_dataset.R                  | 29 ++++----
 3 files changed, 87 insertions(+), 15 deletions(-)
 create mode 100644 .github/workflows/test_run_dataset_cell2location.yml

diff --git a/.github/workflows/test_run_dataset_cell2location.yml b/.github/workflows/test_run_dataset_cell2location.yml
new file mode 100644
index 0000000..df6708a
--- /dev/null
+++ b/.github/workflows/test_run_dataset_cell2location.yml
@@ -0,0 +1,69 @@
+name: test run_dataset mode for Python tools
+# This workflow runs the pipeline with the minimal test dataset to check that it completes without any syntax errors
+on: [ pull_request, workflow_dispatch ]
+
+jobs:
+  run_dataset:
+    name: Run workflow with run_dataset mode
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        # Nextflow versions: check pipeline minimum and latest edge version
+        nxf_ver: 
+          - 'NXF_VER=21.04.3'
+    steps:
+      - name: Check out pipeline code
+        uses: actions/checkout@v3
+        # with
+        #   lfs: true
+
+      - name: Download test dataset
+        run: |
+          wget https://zenodo.org/record/5763377/files/test_data.tar.gz?download=1 -O test_data.tar.gz
+          tar -xzvf test_data.tar.gz
+          echo $(ls)
+
+  #     - name: Checkout LFS objects
+  #       run: git lfs checkout
+
+      - name: Install Nextflow
+        run: |
+          wget -qO- get.nextflow.io | bash
+          sudo mv nextflow /usr/local/bin/
+          export ${{ matrix.nxf_ver }}
+          nextflow self-update
+
+      - name: Run pipeline with test data
+        run: |
+          nextflow run main.nf -profile test,docker --mode run_dataset \
+          --methods cell2location
+
+      - name: Upload proportions and metrics
+        uses: actions/upload-artifact@v3
+        with:
+          name: deconv-proportions-and-metrics
+          path: |
+            deconv_proportions/*
+            results/*
+            trace.txt
+
+  test_output_run_dataset:
+    name: Tests outputs of the pipeline
+    needs: run_dataset
+    runs-on: ubuntu-latest
+    container: rocker/tidyverse:3.6.3
+    steps:
+      - name: Check out pipeline code
+        uses: actions/checkout@v3
+
+      - name: Download proportions from test run
+        uses: actions/download-artifact@v3
+        with:
+          name: deconv-proportions-and-metrics
+
+      - name: Check proportions and metrics with testthat
+        shell: bash
+        run: |
+          echo $(ls)
+          Rscript unit-test/test_run_dataset.R \
+          cell2location
\ No newline at end of file
diff --git a/.github/workflows/test_run_dataset_python.yml b/.github/workflows/test_run_dataset_python.yml
index 7e26597..31e8514 100644
--- a/.github/workflows/test_run_dataset_python.yml
+++ b/.github/workflows/test_run_dataset_python.yml
@@ -36,7 +36,7 @@ jobs:
       - name: Run pipeline with test data
         run: |
           nextflow run main.nf -profile test,docker --mode run_dataset \
-          --methods cell2location,stereoscope,destvi,tangram,stride
+          --methods stereoscope,destvi,tangram,stride
 
       - name: Upload proportions and metrics
         uses: actions/upload-artifact@v3
@@ -66,4 +66,4 @@ jobs:
         run: |
           echo $(ls)
           Rscript unit-test/test_run_dataset.R \
-          cell2location,stereoscope,destvi,tangram,stride
\ No newline at end of file
+          stereoscope,destvi,tangram,stride
\ No newline at end of file
diff --git a/unit-test/test_run_dataset.R b/unit-test/test_run_dataset.R
index 5657165..d5f8e4f 100644
--- a/unit-test/test_run_dataset.R
+++ b/unit-test/test_run_dataset.R
@@ -26,15 +26,16 @@ for (method in methods){
   expect_equal(colnames(output_props), celltypenames)
   
   # Check 2
-  cat(">>> Checking whether proportions are correct...\n")
-  expected_props <- read.table(paste0("unit-test/test_run_dataset/",
-                                      "proportions_", method, "_test_sp_data"),
-                               sep="\t", header=TRUE)
-  expect_equal(rowSums(output_props), rep(1, 16), tolerance=1e-6)
-  expect_equal(sum(output_props$L23IT), sum(expected_props$L23IT), tolerance=1e-3)
-  expect_equal(output_props[15,1:10], expected_props[15,1:10], tolerance=1e-3)
+  if (method != "dstg"){
+    cat(">>> Checking whether proportions are correct...\n")
+    expected_props <- read.table(paste0("unit-test/test_run_dataset/",
+                                        "proportions_", method, "_test_sp_data"),
+                                sep="\t", header=TRUE)
+    expect_equal(rowSums(output_props), rep(1, 16), tolerance=1e-6)
+    expect_equal(sum(output_props$L23IT), sum(expected_props$L23IT), tolerance=1e-3)
+    expect_equal(output_props[15,1:10], expected_props[15,1:10], tolerance=1e-3)
+  }
 
-  
   # Check 3
   cat(">>> Checking whether metrics file is formatted correctly...\n")
   output_metrics <- read.table(paste0("results/test_sp_data/metrics_", method, "_test_sp_data"),
@@ -47,12 +48,14 @@ for (method in methods){
   expect_equal(colnames(output_metrics), metric_names)
   
   # Check 4
-  cat(">>> Checking whether metrics are correct...\n")
-  expected_metrics <- read.table(paste0("unit-test/test_run_dataset/",
-                                        "metrics_", method, "_test_sp_data"),
-                                 sep=" ", header=TRUE)
+  if (method != "dstg"){
+    cat(">>> Checking whether metrics are correct...\n")
+    expected_metrics <- read.table(paste0("unit-test/test_run_dataset/",
+                                          "metrics_", method, "_test_sp_data"),
+                                  sep=" ", header=TRUE)
 
-  expect_equal(output_metrics, expected_metrics, tolerance=1e-3) 
+    expect_equal(output_metrics, expected_metrics, tolerance=1e-3) 
+  }
 
 }