Merge branch 'main' of github.com:poseidon-framework/poseidon-eager i…

…nto main

.gitattributes

@@ -0,0 +1,5 @@
+## All line endings should be linux file endings
+* text eol=lf
+## git lfs support for bed and pos files
+*.pos filter=lfs diff=lfs merge=lfs -text
+*.bed filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -5,4 +5,6 @@ eager/
 array_Logs/
 array_tempfiles/
 testing_assets/
-packages/
+packages/
+poseidon_packages/
+.tmp/

CHANGELOG.md

@@ -3,6 +3,26 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v0.2.1dev - 02/11/2023
+
+### `Added`
+
+- `scripts/minotaur_packager.sh`:        Script to create poseidon half-packages and fill in janno from eager results
+- `scripts/populate_janno.py`:           Script to fill in janno files with poseidon metadata from nf-core eager results.
+
+### `Fixed`
+
+- `scripts/validate_downloaded_data.sh`: Add helptext
+- `scripts/run_eager.sh`:                Now uses `big_data` profile
+- Updates to templates for packages and configs. These are now defunct as they are pulled from the minotaur-recipes repo, and will be removed in netx release.
+- `scripts/download_and_localise_package_files.sh` distinction between symlink dir and package_eager_dir.
+
+### `Dependencies`
+
+- nf-core/eager=2.4.6
+
+### `Deprecated`
+
 ## v0.2.0dev - 25/04/2023
 
 ### `Added`

assets/template.config

@@ -1,6 +1,6 @@
 // Keep track of config versions
-config_template_version='0.2.0dev'
-package_config_version='0.2.0dev'
+config_template_version='0.2.2dev'
+package_config_version='0.2.2dev'
 
 // This configuration file is designed to be a used with the nf-core/eager pipeline.
 //   Instead of having to specify all other configurations for the Minotaur pipeline
@@ -22,7 +22,7 @@ includeConfig '../../conf/CaptureType_profiles/1240K.config'
 
 params {
   // Keep track of config file versions used when processing
-  config_profile_description = "${config_profile_description}\nconfig_template_version: ${config_template_version}\npackage_config_version: ${package_config_version}"
+  config_profile_description = "${config_profile_description}, config_template_version: ${config_template_version}, package_config_version: ${package_config_version}"
   config_profile_contact     = "Thiseas C. Lamnidis (@TCLamnidis)"
 
   /* 

conf/CaptureType_profiles/1240K.config

@@ -1,12 +1,12 @@
 // Keep track of config versions
-capturetype_config_version='0.2.0dev'
+capturetype_config_version='0.2.2dev'
 
 //TODO Backup all bed/snp files in the repo somewhere and use from central location instead of hard-coding paths.
 // Profile specifying capture-specific parameters for packages of the '1240K' CaptureType.
 params{
     // Keep track of config file versions used when processing
     config_profile_name = "${config_profile_name}, on 1240K sites"
-    config_profile_description="${config_profile_description}\n1240K.config: ${capturetype_config_version}"
+    config_profile_description="${config_profile_description}\n - CaptureType.1240K.config: ${capturetype_config_version}"
 
     // Qualimap bedfile for on-target coverage calculation
     snpcapture_bed        = '/mnt/archgen/Reference_Genomes/Human/hs37d5/SNPCapBEDs/1240K.pos.list_hs37d5.0based.bed'

conf/Minotaur.config

@@ -1,30 +1,32 @@
 // Keep track of config versions
-minotaur_config_version='0.2.0dev'
+minotaur_config_version='0.2.1dev'
 
 // Default parameters for processing of data through Minotaur workflow.
 params{
     // Keep track of config file versions used when processing
     config_profile_name = "Minotaur pipeline config"
-    config_profile_description = "Minortaur.config: ${minotaur_config_version}"
+    config_profile_description = "Minotaur.config: ${minotaur_config_version}"
     config_profile_url = 'https://github.com/poseidon-framework/poseidon-eager'
 
+    // Skip steps
+    skip_preseq = true  // This data is published so won't be sequencing it more.
 
     // Mapping
     bwaalnn = 0.01
-    
+
     // BAM filtering
     run_bam_filtering = true            // Filter out unmapped reads, so barplots in MultiQC are not completely overtaken by unmapped reads.
     bam_unmapped_type = 'fastq'         // Keep unmapped reads as a separate fastq file. Preferred format for possible future pathogen screening.
     bam_mapping_quality_threshold = 30    // Keep MapQ 30+ (together with snpcapture_bed is needed for poseidon "coverage on target SNPs" field)
     // The above also means that reads that are mapped with MapQ below 30 are lost after filtering, not present in the fastq OR the filtered bam!
-    
+
     // mtDNA to nuclear ratio
     run_mtnucratio = true
     mtnucratio_header = "MT"
-    
+
     // Bam Trimming
     run_trim_bam = true
-    
+
     // Double-stranded library clipping parameters
     bamutils_clip_double_stranded_half_udg_left  = 2   // Trim 2 bp of either side for dsDNA half-UDG libraries.
     bamutils_clip_double_stranded_half_udg_right = 2   // Trim 2 bp of either side for dsDNA half-UDG libraries.

packages/2021_PattersonNature/2021_PattersonNature.config

@@ -34,6 +34,6 @@ params {
     https://nf-co.re/eager/2.4.6/parameters
 
   You can see the default values for parameters within poseidon-eager at: 
-    https://github.com/poseidon-framework/poseidon-eager/blob/main/conf/Poseidon.config
+    https://github.com/poseidon-framework/poseidon-eager/blob/main/conf/Minotaur.config
   */
 }