chore: fix actions versions

.github/workflows/conventional-prs.yml

@@ -11,7 +11,7 @@ jobs:
   title-format:
     runs-on: ubuntu-latest
     steps:
-      - uses: amannn/action-semantic-pull-request@v3.4.0
+      - uses: amannn/action-semantic-pull-request@v5.2.0
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:

.github/workflows/main.yml

@@ -1,8 +1,6 @@
 name: Tests
 
 on:
-  push:
-    branches: [ main ]
   pull_request:
     branches: [ main ]
 
@@ -11,9 +9,9 @@ jobs:
   Formatting:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Formatting
-        uses: github/super-linter@v4
+        uses: super-linter/super-linter@v5
         env:
           VALIDATE_ALL_CODEBASE: false
           DEFAULT_BRANCH: main
@@ -23,9 +21,9 @@ jobs:
   Linting:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
     - name: Lint workflow
-      uses: snakemake/snakemake-github-action@v1.24.0
+      uses: snakemake/snakemake-github-action@v1.25.1
       with:
         directory: .
         snakefile: workflow/Snakefile
@@ -37,17 +35,17 @@ jobs:
       - Linting
       - Formatting
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
 
     - name: Test workflow
-      uses: snakemake/snakemake-github-action@v1.24.0
+      uses: snakemake/snakemake-github-action@v1.25.1
       with:
         directory: .test
         snakefile: workflow/Snakefile
-        args: "--use-conda --show-failed-logs --cores 3 --conda-cleanup-pkgs cache --all-temp"
+        args: "--use-conda --show-failed-logs --cores 3 --conda-cleanup-pkgs cache --all-temp --configfile .test/config.yaml"
 
     - name: Test report
-      uses: snakemake/snakemake-github-action@v1.24.0
+      uses: snakemake/snakemake-github-action@v1.25.1
       with:
         directory: .test
         snakefile: workflow/Snakefile

.github/workflows/release-please.yml

@@ -10,7 +10,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
 
-      - uses: GoogleCloudPlatform/release-please-action@v2
+      - uses: GoogleCloudPlatform/release-please-action@v3
         id: release
         with:
           release-type: go # just keep a changelog, no version anywhere outside of git tags

.test/config.yaml

@@ -0,0 +1,33 @@
+###############################################################################
+###############                GENERAL PARAMETERS               ###############
+###############################################################################
+
+OUTPUT: results/
+METADATA: data/metadata.txt
+
+###############################################################################
+###############                     RAW DATA                    ###############
+###############################################################################
+
+# Path to folder containing gzipped raw fastq data
+RAW_DATA: data
+
+###############################################################################
+###############                CONDITIONAL RULES                ###############
+###############################################################################
+
+RUN_FASTQC: True
+RUN_STAR: True
+
+
+###############################################################################
+###############                    ALIGNMENT                    ###############
+###############################################################################
+
+# Paths to the folder of the parental genome assemblies
+
+GENOME_DIR_1: data/genome1/
+GENOME_DIR_2: data/genome2/
+
+GENOME_PARENT_1: g1.fa
+GENOME_PARENT_2: g2.fa

.test/data/metadata.txt

@@ -0,0 +1,2 @@
+name
+test_pe

config/config.yaml

@@ -2,15 +2,15 @@
 ###############                GENERAL PARAMETERS               ###############
 ###############################################################################
 
-OUTPUT: output/
-METADATA: test/metadata.txt
+OUTPUT: results/
+METADATA: .test/data/metadata.txt
 
 ###############################################################################
 ###############                     RAW DATA                    ###############
 ###############################################################################
 
 # Path to folder containing gzipped raw fastq data
-RAW_DATA: test
+RAW_DATA: .test/data
 
 ###############################################################################
 ###############                CONDITIONAL RULES                ###############
@@ -26,8 +26,8 @@ RUN_STAR: True
 
 # Paths to the folder of the parental genome assemblies
 
-GENOME_DIR_1: test/genome1/
-GENOME_DIR_2: test/genome2/
+GENOME_DIR_1: .test/data/genome1/
+GENOME_DIR_2: .test/data/genome2/
 
-GENOME_PARENT_1: Ahal_ref.fa
-GENOME_PARENT_2: Alyr_ref.fa
+GENOME_PARENT_1: g1.fa
+GENOME_PARENT_2: g2.fa

workflow/Snakefile

@@ -14,7 +14,6 @@ if len(config) == 0:
 
         configfile: "config/config.yaml"
 
-
     else:
         sys.exit(
             f"Make sure there is a config.yaml file in {os.getcwd()} or specify one with the --configfile commandline parameter."
@@ -28,20 +27,23 @@ samples = pd.read_csv(config["METADATA"], sep="\t")
 
 ## Parse config file
 
-RAW_DATA_DIR = os.path.normpath(config["RAW_DATA"]) 
+RAW_DATA_DIR = os.path.normpath(config["RAW_DATA"])
 OUTPUT_DIR = os.path.normpath(config["OUTPUT"])
 GENOME_DIR_1 = os.path.normpath(config["GENOME_DIR_1"])
 GENOME_DIR_2 = os.path.normpath(config["GENOME_DIR_2"])
 GENOME_PARENT_1 = os.path.splitext(config["GENOME_PARENT_1"])[0]
 GENOME_PARENT_2 = os.path.splitext(config["GENOME_PARENT_2"])[0]
 
+
 ## Run all analyses
 rule all:
     input:
-        f"{OUTPUT_DIR}/MultiQC/multiqc_report.html"
+        f"{OUTPUT_DIR}/MultiQC/multiqc_report.html",
+
 
 ######################### Main rules of REAP #############################
 
+
 include: "rules/input_functions.smk"
 include: "rules/quality_check.smk"
 include: "rules/alignment.smk"

workflow/rules/alignment.smk

@@ -1,6 +1,7 @@
 #### Indexing reference rule ####
 
-# Index genome 1 
+
+# Index genome 1
 rule star_index_genome_1:
     input:
         fasta=f"{GENOME_DIR_1}/{GENOME_PARENT_1}.fa",
@@ -16,7 +17,8 @@ rule star_index_genome_1:
     wrapper:
         "v2.3.0/bio/star/index"
 
-# Index genome 2 
+
+# Index genome 2
 rule star_index_genome_2:
     input:
         fasta=f"{GENOME_DIR_2}/{GENOME_PARENT_2}.fa",
@@ -33,14 +35,14 @@ rule star_index_genome_2:
         "v2.3.0/bio/star/index"
 
 
-
 #### Alignment rule ####
 
+
 rule star_pe_multi_1:
     input:
-        fq1=f"test/{{sample}}_R1.fastq.gz",
+        fq1=f"{RAW_DATA_DIR}/{{sample}}_R1.fastq.gz",
         # paired end reads needs to be ordered so each item in the two lists match
-        fq2=f"test/{{sample}}_R2.fastq.gz",  #optional
+        fq2=f"{RAW_DATA_DIR}/{{sample}}_R2.fastq.gz",  #optional
         # path to STAR reference genome index
         idx=f"{GENOME_DIR_1}",
     output:
@@ -61,9 +63,9 @@ rule star_pe_multi_1:
 
 rule star_pe_multi_2:
     input:
-        fq1=f"test/{{sample}}_R1.fastq.gz",
+        fq1=f"{RAW_DATA_DIR}/{{sample}}_R1.fastq.gz",
         # paired end reads needs to be ordered so each item in the two lists match
-        fq2=f"test/{{sample}}_R2.fastq.gz",  #optional
+        fq2=f"{RAW_DATA_DIR}/{{sample}}_R2.fastq.gz",  #optional
         # path to STAR reference genome index
         idx=f"{GENOME_DIR_2}",
     output:

workflow/rules/input_functions.smk

@@ -1,32 +1,29 @@
 # This file includes all functions to define inputs to other rules
 
+
 def multiqc_input(wildcards):
-
     input = []
-
     if config["RUN_FASTQC"]:
         input.extend(
             expand(
                 f"{OUTPUT_DIR}/fastqc/{{sample}}_{{extension}}_fastqc.zip",
-                sample=samples.name.values.tolist(),extension=['R1','R2'],
+                sample=samples.name.values.tolist(),
+                extension=["R1", "R2"],
             )
         )
     if config["RUN_STAR"]:
         input.extend(
-                    expand(
-                        f"{OUTPUT_DIR}/qualimap/{{sample}}/aligned_1",
-                        sample=samples.name.values.tolist(),
-                    )
-                )
+            expand(
+                f"{OUTPUT_DIR}/qualimap/{{sample}}/aligned_1",
+                sample=samples.name.values.tolist(),
+            )
+        )
 
         input.extend(
-                    expand(
-                        f"{OUTPUT_DIR}/qualimap/{{sample}}/aligned_2",
-                        sample=samples.name.values.tolist(),
-                    )
-                )
+            expand(
+                f"{OUTPUT_DIR}/qualimap/{{sample}}/aligned_2",
+                sample=samples.name.values.tolist(),
+            )
+        )
 
     return input
-
-
-

workflow/rules/quality_check.smk

@@ -4,19 +4,20 @@
 
 # Quality check for the raw data
 
+
 rule fastqc:
     input:
         fastq=f"{RAW_DATA_DIR}/{{sample}}_{{extension}}.fastq.gz",
     output:
         html=f"{OUTPUT_DIR}/fastqc/{{sample}}_{{extension}}.html",
-        zip=f"{OUTPUT_DIR}/fastqc/{{sample}}_{{extension}}_fastqc.zip" # the suffix _fastqc.zip is necessary for multiqc to find the file. If not using multiqc, you are free to choose an arbitrary filename
+        zip=f"{OUTPUT_DIR}/fastqc/{{sample}}_{{extension}}_fastqc.zip",  # the suffix _fastqc.zip is necessary for multiqc to find the file. If not using multiqc, you are free to choose an arbitrary filename
     params:
-        extra = "--quiet"
+        extra="--quiet",
     log:
-        f"logs/fastqc/{{sample}}_{{extension}}.log"
+        f"logs/fastqc/{{sample}}_{{extension}}.log",
     threads: 1
     resources:
-        mem_mb = 1024
+        mem_mb=1024,
     wrapper:
         "v2.3.0/bio/fastqc"
 
@@ -27,6 +28,7 @@ rule fastqc:
 
 # Quality check for the alignment with STAR
 
+
 rule qualimap_1:
     input:
         # BAM aligned, splicing-aware, to reference genome
@@ -63,21 +65,21 @@ rule qualimap_2:
         "v2.3.0/bio/qualimap/bamqc"
 
 
-
 ###################
 #### Multi QC #####
 ###################
 
 # Multi QC report
 
+
 rule multiqc_dir:
     input:
         multiqc_input,
     output:
-        out=f"{OUTPUT_DIR}/MultiQC/multiqc_report.html"
+        out=f"{OUTPUT_DIR}/MultiQC/multiqc_report.html",
     params:
-        extra=""  # Optional: extra parameters for multiqc.
+        extra="",  # Optional: extra parameters for multiqc.
     log:
-        "logs/multiqc.log"
+        "logs/multiqc.log",
     wrapper:
-        "v2.3.0/bio/multiqc"
+        "v2.3.0/bio/multiqc"