Skip to content

Commit

Permalink
Merge pull request #43 from friendsofstrandseq/dev
Browse files Browse the repository at this point in the history
Final results file to check if all outputs were produced, dump config…
  • Loading branch information
weber8thomas authored Dec 4, 2023
2 parents 7aadd43 + 202ad00 commit 33d8e87
Show file tree
Hide file tree
Showing 13 changed files with 884 additions and 190 deletions.
64 changes: 13 additions & 51 deletions .github/workflows/main.yaml → .github/workflows/main_test.yaml
Original file line number Diff line number Diff line change
@@ -1,23 +1,16 @@
name: ashleys-qc-pipeline workflow checks

on:
schedule:
# Run every Sunday at 00:00 UTC on the master branch
- cron: '0 0 * * 0'
# branches:
# - master
push:
branches:
- '*'
- '!master'

- "**"

jobs:
# WORK
Formatting:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3.3.0
- uses: actions/checkout@v4

- name: Formatting
uses: github/super-linter@v4
Expand All @@ -30,21 +23,17 @@ jobs:
Linting:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3.3.0
- uses: actions/checkout@v4
- name: Linting
uses: snakemake/snakemake-github-action@v1.24.0
with:
directory: .
snakefile: ./workflow/Snakefile
# stagein: "mamba env remove -n snakemake && mamba create -y -n snakemake -c conda-forge -c bioconda unzip snakemake pandas pysam tqdm imagemagick && source activate snakemake && ls -l && pwd"
args: "--lint --config ashleys_pipeline=True"
Testing_ashleys:
runs-on: ubuntu-latest
# needs:
# - Linting
# - Formatting
steps:
- uses: actions/checkout@v3.3.0
- uses: actions/checkout@v4
- name: Testing data
uses: snakemake/snakemake-github-action@v1.24.0
with:
Expand All @@ -61,11 +50,8 @@ jobs:

Testing_ashleys_fastqc_enabled:
runs-on: ubuntu-latest
# needs:
# - Linting
# - Formatting
steps:
- uses: actions/checkout@v3.3.0
- uses: actions/checkout@v4
- name: Testing data
uses: snakemake/snakemake-github-action@v1.24.0
with:
Expand All @@ -82,11 +68,8 @@ jobs:

Testing_ashleys_ms_norm_enabled:
runs-on: ubuntu-latest
# needs:
# - Linting
# - Formatting
steps:
- uses: actions/checkout@v3.3.0
- uses: actions/checkout@v4
- name: Testing data
uses: snakemake/snakemake-github-action@v1.24.0
with:
Expand All @@ -102,11 +85,8 @@ jobs:
args: "--cores 1 --use-conda --configfile .tests/config/simple_config.yaml --config multistep_normalisation=True --conda-frontend mamba --report report.zip"
Testing_ashleys_hg38:
runs-on: ubuntu-latest
# needs:
# - Linting
# - Formatting
steps:
- uses: actions/checkout@v3.3.0
- uses: actions/checkout@v4
- name: Testing data
uses: snakemake/snakemake-github-action@v1.24.0
with:
Expand All @@ -122,11 +102,8 @@ jobs:
args: "--cores 1 --use-conda --config reference=hg38 use_light_data=True chromosomes=[chr17] --conda-frontend mamba --report report.zip"
Testing_ashleys_hg19:
runs-on: ubuntu-latest
# needs:
# - Linting
# - Formatting
steps:
- uses: actions/checkout@v3.3.0
- uses: actions/checkout@v4
- name: Testing data
uses: snakemake/snakemake-github-action@v1.24.0
with:
Expand All @@ -142,11 +119,8 @@ jobs:
args: "--cores 1 --use-conda --config reference=hg19 use_light_data=True chromosomes=[chr17] --conda-frontend mamba --report report.zip"
Testing_ashleys_T2T:
runs-on: ubuntu-latest
# needs:
# - Linting
# - Formatting
steps:
- uses: actions/checkout@v3.3.0
- uses: actions/checkout@v4
- name: Testing data
uses: snakemake/snakemake-github-action@v1.24.0
with:
Expand All @@ -162,11 +136,8 @@ jobs:
args: "--cores 1 --use-conda --config reference=T2T use_light_data=True chromosomes=[chr17] --conda-frontend mamba --report report.zip"
Testing_ashleys_mm10:
runs-on: ubuntu-latest
# needs:
# - Linting
# - Formatting
steps:
- uses: actions/checkout@v3.3.0
- uses: actions/checkout@v4
- name: Testing data
uses: snakemake/snakemake-github-action@v1.24.0
with:
Expand All @@ -182,11 +153,8 @@ jobs:
args: "--cores 1 --use-conda --config reference=mm10 use_light_data=True chromosomes=[chr17] --conda-frontend mamba --report report.zip"
Testing_jub_nb:
runs-on: ubuntu-latest
# needs:
# - Linting
# - Formatting
steps:
- uses: actions/checkout@v3.3.0
- uses: actions/checkout@v4
- name: Testing data
uses: snakemake/snakemake-github-action@v1.24.0
with:
Expand All @@ -202,11 +170,8 @@ jobs:
args: "--cores 1 --use-conda --configfile .tests/config/simple_config.yaml --config hand_selection=True --conda-frontend mamba --report report.zip"
Testing_publishdir:
runs-on: ubuntu-latest
# needs:
# - Linting
# - Formatting
steps:
- uses: actions/checkout@v3.3.0
- uses: actions/checkout@v4
- name: Testing data
uses: snakemake/snakemake-github-action@v1.24.0
with:
Expand All @@ -222,11 +187,8 @@ jobs:
args: "--cores 1 --use-conda --configfile .tests/config/simple_config.yaml --config publishdir=.tests/data_chr17_publishdir --conda-frontend mamba --report report.zip"
Testing_list_commands:
runs-on: ubuntu-latest
# needs:
# - Linting
# - Formatting
steps:
- uses: actions/checkout@v3.3.0
- uses: actions/checkout@v4
- name: Testing data
uses: snakemake/snakemake-github-action@v1.24.0
with:
Expand Down
155 changes: 81 additions & 74 deletions .tests/config/simple_config.yaml
Original file line number Diff line number Diff line change
@@ -1,28 +1,36 @@
version: 2.2.2
# Option to display all potential options - listed in config_metadata.yaml
list_commands: False
## Data location - MUST BE AN ABSOULTE PATH (due to snakemake-symlink issues) - PLEASE MODIFY IT
# input_bam_location: ".tests/data_CHR17"
data_location: ".tests/data_CHR17"
# Reference genome used by BWA to map FASTQ files
# reference: sandbox.zenodo.org/record/1074721/files/GCA_000001405.15_GRCh38_no_alt_analysis_set.fna
# Enable / Disable download of external files (1000G SNV & Fasta ref genome)
dl_external_files: False
# Enable / Disable multistep normalisation
multistep_normalisation: False
# Ashleys-qc binary classification threshold
ashleys_threshold: 0.5
# Enable / Disable FastQC analysis
FastQC_analysis: False
# To be informed of pipeline status
# --------------------------------------------------------
# Ashleys-QC pipeline Configuration
# --------------------------------------------------------
version: 2.2.3

# Email for notifications about the pipeline's status
email: ""

############################################################################
# ADVANCED PARAMETERS
############################################################################
# List of samples to process if multiple are specified
samples_to_process: []

# Plate size
plate_size: 96

# --------------------------------------------------------
# Data location & I/O
# --------------------------------------------------------

# Absolute path to the data location (modify as needed)
data_location: ".tests/data_CHR17"

# Directory to publish important data (e.g., stats, plots, counts). Leave empty if not required.
publishdir: ""

# --------------------------------------------------------
# Reference Data Configuration
# --------------------------------------------------------

# Reference genome used by BWA to map FASTQ files
reference: "hg38"

# Reference genome files' location

references_data:
"hg38":
reference_fasta: ".tests/external_data/chr17.fa.gz"
Expand All @@ -31,70 +39,69 @@ references_data:
"T2T":
reference_fasta: "workflow/data/ref_genomes/T2T.fa"

# Boolean parameters
## Is the pipeline called used as a submodule in mosaicatcher-pipeline?
mosaicatcher_pipeline: False
## Enable/Disable hand selection through Jupyter Notebook
hand_selection: False
# List of chromosomes to process
chromosomes:
- chr17

# Window size used by mosaic binning algorithm
window: 200000
# Specify any chromosomes to exclude from processing
chromosomes_to_exclude: []

plottype_counts:
- "raw"
- "normalised"
# --------------------------------------------------------
# Quality Control Configuration
# --------------------------------------------------------

alfred_plots:
- "dist"
- "devi"
# Threshold for Ashleys-qc binary classification
ashleys_threshold: 0.5

plate_orientation: landscape
# Enable or disable FastQC analysis
MultiQC: False

# --------------------------------------------------------
# Counts Configuration
# --------------------------------------------------------

# Enable or disable multistep normalization analysis
multistep_normalisation: False

# Advanced parameters for multi-step normalisation
multistep_normalisation_options:
min_reads_bin: 5
n_subsample: 1000
min_reads_cell: 100000

# Window size used by the mosaic binning algorithm
window: 200000

# Enable or disable hand selection through the Jupyter Notebook
hand_selection: False

# --------------------------------------------------------
# GENECORE Configuration
# --------------------------------------------------------

# Chromosomes list to process
chromosomes:
- chr1
- chr2
- chr3
- chr4
- chr5
- chr6
- chr7
- chr8
- chr9
- chr10
- chr11
- chr12
- chr13
- chr14
- chr15
- chr16
- chr17
- chr18
- chr19
- chr20
- chr21
- chr22
- chrX
- chrY

# GENECORE
genecore: False
samples_to_process: []
genecore_date_folder: ""
genecore_prefix: "/g/korbel/shared/genecore"
genecore_prefix: "/g/korbel/STOCKS/Data/Assay/sequencing/2023"
genecore_regex_element: "PE20"

##### DEV only
# --------------------------------------------------------
# Internal Parameters
# --------------------------------------------------------

# Is the pipeline used as a submodule in mosaicatcher-pipeline?
mosaicatcher_pipeline: False

# Overwrite ASHLEYS PREDICTIONS for GitHub & smoke dataset purpose
use_light_data: True

# If specified, will copy important data (stats, plots, counts file) to a second place
publishdir: ""

# Multi-step normalisation advanced parameters
multistep_normalisation_options:
min_reads_bin: 5
n_subsample: 1000
min_reads_cell: 1000
# Others
# For snakemake linting
abs_path: "/"

# Type of plots for counts
plottype_counts:
- "raw"
- "normalised"

# Option to display all potential commands (as listed in config_metadata.yaml)
list_commands: False
# --------------------------------------------------------
5 changes: 4 additions & 1 deletion config/config.yaml
Original file line number Diff line number Diff line change
@@ -1,14 +1,17 @@
# --------------------------------------------------------
# Ashleys-QC pipeline Configuration
# --------------------------------------------------------
version: 2.2.2
version: 2.2.3

# Email for notifications about the pipeline's status
email: ""

# List of samples to process if multiple are specified
samples_to_process: []

# Plate size
plate_size: 96

# --------------------------------------------------------
# Data location & I/O
# --------------------------------------------------------
Expand Down
Loading

0 comments on commit 33d8e87

Please sign in to comment.