ncherric · ncherric · Jun 28, 2023 · Jun 28, 2023 · Jun 28, 2023 · Jun 28, 2023
diff --git a/.github/workflows/main.yaml b/.github/workflows/main.yaml
@@ -0,0 +1,52 @@
+name: Tests
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  formatting:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v1
+    - name: Checkout submodules
+      uses: textbook/[email protected]
+    - name: Formatting
+      uses: github/[email protected]
+      env:
+        VALIDATE_ALL_CODEBASE: false
+        DEFAULT_BRANCH: main
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        VALIDATE_SNAKEMAKE_SNAKEFMT: true
+
+  linting:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v1
+    - name: Checkout submodules
+      uses: textbook/[email protected]
+    - name: Linting
+      uses: snakemake/[email protected]
+      with:
+        directory: '.test'
+        snakefile: workflow/Snakefile
+        args: '--lint'
+
+  run-workflow:
+    runs-on: ubuntu-latest
+    needs:
+      - formatting
+      - linting
+    steps:
+    - uses: actions/checkout@v1
+    - name: Checkout submodules
+      uses: textbook/[email protected]
+
+    - name: snakemake
+      uses: snakemake/[email protected]
+      with:
+        directory: .test
+        snakefile: workflow/Snakefile
+        args: "--use-conda --show-failed-logs --cores 1 --conda-cleanup-pkgs cache"
diff --git a/.github/workflows/pylint.yml b/.github/workflows/pylint.yml
@@ -0,0 +1,23 @@
+name: Pylint
+
+on: [push]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.8", "3.9", "3.10"]
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v3
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install pylint
+    - name: Analysing the code with pylint
+      run: |
+        pylint $(git ls-files '*.py')
diff --git a/config/README.md b/config/README.md
@@ -59,7 +59,7 @@ Use an Excel sheet or CSV file with no header and the following two columns/fiel
 | --- | --- |
 | KPGP-00127 | ftp://ftp.kobic.re.kr/pub/KPGP/2020_release_candidate/WGS_SR/KPGP-00127/KPGP-00127_L1_R2.fq.gz |
 
-This exact template exists already in ``/Iliad/config/UserSampleTable.xlsx``. (The Excel Viewer extension on VS code is really handy for editing!)
+This exact template exists already in ``/Iliad/config/UserSampleTable.xlsx`` OR ``/Iliad/config/UserSampleTable.csv``. (The Excel Viewer extension on VS code is really handy for editing the .xlsx file if spreadsheets are your preference!)
 If you already have the sequence files and are not downloading open-source data, you have the option to place your data into the ``Iliad/data/fastq/`` directory.
 
 Whether you are automatically downloading via Iliad or you manually place data into ``Iliad/data/fastq/`` directory,

diff --git a/config/UserSampleTable.csv b/config/UserSampleTable.csv
@@ -0,0 +1,2 @@
+KPGP-00127  ftp://ftp.kobic.re.kr/pub/KPGP/2020_release_candidate/WGS_SR/KPGP-00127/KPGP-00127_L1_R1.fq.gz
+KPGP-00127  ftp://ftp.kobic.re.kr/pub/KPGP/2020_release_candidate/WGS_SR/KPGP-00127/KPGP-00127_L1_R2.fq.gz
diff --git a/config/config.yaml b/config/config.yaml
@@ -38,12 +38,12 @@ workdirPath: NEED PATH HERE
 
 # for downloading FastQ raw seq data make sure there is an Excel table or csv document with two columns and no header: Sample_Name,FTP_url
 # e.g KPGP-00127,ftp://ftp.kobic.re.kr/pub/KPGP/2020_release_candidate/WGS_SR/KPGP-00127/KPGP-00127_L1_R1.fq.gz
-samplesDict: config/UserSampleTable.xlsx
+samplesDict: config/UserSampleTable.csv
 # must include list of samples in one column with "sample" header, no matter if you use the download feature or if you re-direct ILIAD to FASTQ data path
 samples: config/samples.tsv
 
 # Same setup as above for if you are retrieving CRAM files from an FTP server
-cramSamplesDict: config/cramSampleTable.xlsx
+cramSamplesDict: config/cramSampleTable.csv
 cramSamples: config/cramSamples.tsv
 
 ###########################################################

diff --git a/config/cramSampleTable.csv b/config/cramSampleTable.csv
@@ -0,0 +1,2 @@
+NA12718 ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR323/ERR3239480/NA12718.final.cram
+NA12718 ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR323/ERR3239480/NA12718.final.cram.crai
diff --git a/docs/conf.py b/docs/conf.py
@@ -1,5 +1,6 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
+"""Module readthedocs configuration."""
 
 import sys
 import os
@@ -248,4 +249,4 @@
 
 
 def setup(app):
-    app.add_css_file("sphinx-argparse.css")
+    app.add_css_file("sphinx-argparse.css")
diff --git a/docs/getting_started/config.rst b/docs/getting_started/config.rst
@@ -54,12 +54,12 @@ The most important variables that a user can defined are also stated within each
 
     # for downloading FastQ raw seq data make sure there is an Excel table or csv document with two columns and no header: Sample_Name,FTP_url
     # e.g KPGP-00127,ftp://ftp.kobic.re.kr/pub/KPGP/2020_release_candidate/WGS_SR/KPGP-00127/KPGP-00127_L1_R1.fq.gz
-    samplesDict: config/UserSampleTable.xlsx
+    samplesDict: config/UserSampleTable.csv
     # must include list of samples in one column with "sample" header, no matter if you use the download feature or if you re-direct ILIAD to FASTQ data path
     samples: config/samples.tsv
 
     # Same setup as above for if you are retrieving CRAM files from an FTP server
-    cramSamplesDict: config/cramSampleTable.xlsx
+    cramSamplesDict: config/cramSampleTable.csv
     cramSamples: config/cramSamples.tsv
 
     ###########################################################

diff --git a/docs/getting_started/demo.rst b/docs/getting_started/demo.rst
@@ -119,7 +119,7 @@ Cloning the GitHub Repo
 |
 |
 
-The table will have two columns - Column 1 you input the sample ID. It is ok to have multiple repeating Sample IDs for paired-end reads and multiplexed data. Here is the tutorial file already setup: ``./Iliad/config/UserSampleTable.xlsx``
+The table will have two columns - Column 1 you input the sample ID. It is ok to have multiple repeating Sample IDs for paired-end reads and multiplexed data. Here is the tutorial file already setup: ``./Iliad/config/UserSampleTable.csv``
 
 |
 |

diff --git a/docs/tutorial/raw_sequence.rst b/docs/tutorial/raw_sequence.rst
@@ -84,7 +84,7 @@ Example: **UserSampleTable.xlsx** or **UserSampleTable.csv** are found in the ``
    * - KPGP-00127
      - ftp://ftp.kobic.re.kr/pub/KPGP/2020_release_candidate/WGS_SR/KPGP-00127/KPGP-00127_L1_R2.fq.gz
 
-This exact template exists already in ``/Iliad/config/UserSampleTable.xlsx``. (The Excel Viewer extension on VS code is really handy for editing!)
+This exact template exists already in ``/Iliad/config/UserSampleTable.xlsx`` OR ``/Iliad/config/UserSampleTable.csv``. (The Excel Viewer extension on VS code is really handy for editing the .xlsx file if spreadsheets are your preference!)
 If you already have the sequence files and are not downloading open-source data, you have the option to place your data into the ``Iliad/data/fastq/`` directory.
 
 Whether you are automatically downloading via Iliad or you manually place data into ``Iliad/data/fastq/`` directory,

diff --git a/workflow/Lift-and-Merge_Snakefile b/workflow/Lift-and-Merge_Snakefile
@@ -1,6 +1,6 @@
 ##### Environment Dependencies #####
 
-singularity: "library://ncherric/iliad/igdp-container:latest"
+singularity: "library://ncherric/iliad/igdp-container:v1.16"
 include: "rules/common.smk"
 
 LiftoverTF=config["LiftoverTF"]

diff --git a/workflow/Snakefile b/workflow/Snakefile
@@ -1,4 +1,4 @@
-singularity: "library://ncherric/iliad/igdp-container:latest"
+singularity: "library://ncherric/iliad/igdp-container:v1.16"
 
 include: "rules/common.smk"
 splits=config['NYGC']['numberOfSplitRegionsFiles']

diff --git a/workflow/cram_Snakefile b/workflow/cram_Snakefile
@@ -1,4 +1,4 @@
-singularity: "library://ncherric/iliad/igdp-container"
+singularity: "library://ncherric/iliad/igdp-container:v1.16"
 
 include: "rules/common.smk"
 splits=config['NYGC']['numberOfSplitRegionsFiles']

diff --git a/workflow/liftoverTo37_Snakefile b/workflow/liftoverTo37_Snakefile
@@ -1,6 +1,6 @@
 ##### Environment Dependencies #####
 
-# singularity: "library://ncherric/iliad/igdp-container:latest"
+# singularity: "library://ncherric/iliad/igdp-container:v1.16"
 include: "rules/common.smk"
 
 ##### Target rules #####

diff --git a/workflow/liftoverTo38_Snakefile b/workflow/liftoverTo38_Snakefile
@@ -1,6 +1,6 @@
 ##### Environment Dependencies #####
 
-# singularity: "library://ncherric/iliad/igdp-container:latest"
+# singularity: "library://ncherric/iliad/igdp-container:v1.16"
 include: "rules/common.smk"
 
 ##### Target rules #####

diff --git a/workflow/scripts/concatenate-reference-set-overlap.py b/workflow/scripts/concatenate-reference-set-overlap.py
@@ -7,7 +7,7 @@
 log = snakemake.log_fmt_shell(stdout=False, stderr=True)
 
 shell(
-	"mkdir -p data/target_ref_merge/TempFiles/
+	"mkdir -p data/target_ref_merge/TempFiles/"
 )
 
 shell(

diff --git a/workflow/scripts/fixref.py b/workflow/scripts/fixref.py
@@ -19,7 +19,7 @@
 
 shell(
     "mkdir -p data/vcf_merge/{project}/{refAssemblyVersion}/step7-fixref/Temp/{vcf}/"
-
+)
 
 shell(
     "bcftools +fixref {snakemake.input.cleanDBSNPmyData}"

diff --git a/workflow/snpArray_Snakefile b/workflow/snpArray_Snakefile
@@ -1,6 +1,6 @@
 ##### Environment Dependencies #####
 
-singularity: "library://ncherric/iliad/igdp-container:latest"
+singularity: "library://ncherric/iliad/igdp-container:v1.16"
 
 ##### Target rules #####
 

diff --git a/workflow/targetRefMerge_Snakefile b/workflow/targetRefMerge_Snakefile
@@ -1,4 +1,4 @@
-singularity: "library://ncherric/iliad/igdp-container"
+singularity: "library://ncherric/iliad/igdp-container:v1.16"
 
 include: "rules/common.smk"