poseidon-framework · Tlkhi · Jul 19, 2025 · Jul 19, 2025
diff --git a/packages/2016_Broushaki_Science/2016_Broushaki_Science.config b/packages/2016_Broushaki_Science/2016_Broushaki_Science.config
@@ -0,0 +1,41 @@
+// Keep track of config versions
+minotaur_release='0.5.0' // The release tag of the poseidon-eager repository used for processing and config file retrieval
+config_template_version='0.5.0'
+package_config_version='0.5.0'
+minotaur_config_base="https://raw.githubusercontent.com/poseidon-framework/poseidon-eager/${minotaur_release}/conf"
+
+// This configuration file is designed to be a used with the nf-core/eager pipeline.
+//   Instead of having to specify all other configurations for the Minotaur pipeline
+//   on runtime, they are all contained in this file and loaded automatically upon
+//   specifying this config file during runtime. Additionally, any parameters that
+//   need to be altered from the defaults can be specified here.
+//
+// The intention is to make it easy for users to understand and reproduce the output
+//  from processing with the Minotaur workflow processing from the contents of a
+//  single file.
+
+// Load configuration profiles. They are loaded from the minotaur_config_base URL, main branch.
+includeConfig "${minotaur_config_base}/EVA_cluster.config" // Cluster-specific configurations for nf-core/eager execution at MPI-EVA
+includeConfig "${minotaur_config_base}/Minotaur.config"    // Default nf-core/eager parameters for Minotaur processing.
+
+// The following config file specifies BED files for on-target endogenous DNA calculation and mean coverage as well as pseudohaploid genotyping.
+// TODO: Select the appropriate config for the CaptureType of the package.
+includeConfig "${minotaur_config_base}/CaptureType_profiles/1240K.config"
+
+params {
+  // Keep track of config file versions used when processing
+  config_profile_description = "${config_profile_description}\n - config_template_version: ${config_template_version}\n - package_config_version: ${package_config_version}"
+  config_profile_contact     = "Thiseas C. Lamnidis (@TCLamnidis)"
+
+  /* 
+  TODO: If you need to change any of the default processing parameters for this package
+  you can specify these parameters below.
+  Any parameters not specified in any of the config files default to their nf-core/eager default values.
+
+  For information on all available parameters and their default values see: 
+    https://nf-co.re/eager/2.5.1/parameters
+
+  You can see the latest default values for parameters within poseidon-eager at:
+    https://github.com/poseidon-framework/poseidon-eager/blob/main/conf/Minotaur.config
+  */
+}
diff --git a/packages/2016_Broushaki_Science/2016_Broushaki_Science.ssf b/packages/2016_Broushaki_Science/2016_Broushaki_Science.ssf
@@ -0,0 +1,6 @@
+poseidon_IDs	udg	library_built	notes	run_accession	study_accession	sample_accession	sample_alias	secondary_sample_accession	first_public	last_updated	instrument_model	library_layout	library_source	instrument_platform	library_name	library_strategy	fastq_ftp	fastq_aspera	fastq_bytes	fastq_md5	read_count	submitted_ftp	submitted_md5
+AH1	minus	ds	n/a	ERR1427797	PRJEB14180	SAMEA4015206	AH1	ERS1186316	2016-07-15	2018-11-16	Illumina HiSeq 2500	SINGLE	METAGENOMIC	ILLUMINA	unspecified	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR142/007/ERR1427797/ERR1427797.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR142/007/ERR1427797/ERR1427797.fastq.gz	3206724794	a18da14f96ceb4f60c740d5608bdceb4	67506999	ftp.sra.ebi.ac.uk/vol1/run/ERR142/ERR1427797/AH1.all_lib.Mkdup.len.realg.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR142/ERR1427797/AH1.all_lib.Mkdup.len.realg.bam.bai	3458ae5f33f0d79e57b504d46b5d9e96;3e6a63bbbacb41d2c675ee3887ab3b8c
+AH2	minus	ds	n/a	ERR1427798	PRJEB14180	SAMEA4015207	AH2	ERS1186317	2016-07-15	2018-11-16	Illumina HiSeq 2500	SINGLE	METAGENOMIC	ILLUMINA	unspecified	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR142/008/ERR1427798/ERR1427798.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR142/008/ERR1427798/ERR1427798.fastq.gz	1632005812	af98dcf94b55a1deffc34e8cb2ee719a	34394545	ftp.sra.ebi.ac.uk/vol1/run/ERR142/ERR1427798/AH2.all_lib.Mkdup.len.realg.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR142/ERR1427798/AH2.all_lib.Mkdup.len.realg.bam.bai	7ce1897d3f9deeeb4106dc23309951f9;2f1b18d63d2f0f334d5c4b15370219a2
+AH4	minus	ds	n/a	ERR1427799	PRJEB14180	SAMEA4015208	AH4	ERS1186318	2016-07-15	2018-11-16	Illumina HiSeq 2500	SINGLE	METAGENOMIC	ILLUMINA	unspecified	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR142/009/ERR1427799/ERR1427799.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR142/009/ERR1427799/ERR1427799.fastq.gz	2393087748	ea1ed117e1a5ff0b345b0920f3b999f2	50397195	ftp.sra.ebi.ac.uk/vol1/run/ERR142/ERR1427799/AH4.all_lib.Mkdup.len.realg.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR142/ERR1427799/AH4.all_lib.Mkdup.len.realg.bam.bai	7eed5cda5fa6cb0c7652b15093442354;4077b41d4b4530f447557f92a88917e9
+F38	minus	ds	n/a	ERR1427822	PRJEB14180	SAMEA4015209	F38	ERS1186319	2016-07-15	2018-11-16	Illumina HiSeq 2500	SINGLE	METAGENOMIC	ILLUMINA	unspecified	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR142/002/ERR1427822/ERR1427822.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR142/002/ERR1427822/ERR1427822.fastq.gz	3897149735	9b75054007eeca140aed003b1c524db5	68748753	ftp.sra.ebi.ac.uk/vol1/run/ERR142/ERR1427822/F38.all_realn.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR142/ERR1427822/F38.all_realn.bam.bai	159266dfea8bc6aaa4f9e5a76c9fc9f6;081b081ca9f9f8e52c5ddc616ad583bd
+WC1	minus	ds	n/a	ERR1427821	PRJEB14180	SAMEA4015210	WC1	ERS1186320	2016-07-15	2018-11-16	Illumina HiSeq 2500	SINGLE	METAGENOMIC	ILLUMINA	unspecified	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR142/001/ERR1427821/ERR1427821.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR142/001/ERR1427821/ERR1427821.fastq.gz	17945861342	0b8f4965bb9cb3893f83c21ed6f60e82	326262818	ftp.sra.ebi.ac.uk/vol1/run/ERR142/ERR1427821/WC1.all_SG_join.Mkdup.len.realg.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR142/ERR1427821/WC1.all_SG_join.Mkdup.len.realg.bam.bai	968c5f3b0272a8be133bf9c884afd5c2;736ddbd6cd69e0b74caae2602c90bbd7
diff --git a/packages/2016_Broushaki_Science/2016_Broushaki_Science.tsv b/packages/2016_Broushaki_Science/2016_Broushaki_Science.tsv
@@ -0,0 +1,6 @@
+Sample_Name	Library_ID	Lane	Colour_Chemistry	SeqType	Organism	Strandedness	UDG_Treatment	R1	R2	BAM	R1_target_file	R2_target_file	BAM_target
+AH1	AH1_unspecified	1	4	SE	Homo sapiens (modern human)	double	none	<PATH_TO_DATA>/AH1_unspecified_L1_R1.fastq.gz	NA	NA	ERR1427797.fastq.gz	NA	NA
+AH2	AH2_unspecified	1	4	SE	Homo sapiens (modern human)	double	none	<PATH_TO_DATA>/AH2_unspecified_L1_R1.fastq.gz	NA	NA	ERR1427798.fastq.gz	NA	NA
+AH4	AH4_unspecified	1	4	SE	Homo sapiens (modern human)	double	none	<PATH_TO_DATA>/AH4_unspecified_L1_R1.fastq.gz	NA	NA	ERR1427799.fastq.gz	NA	NA
+F38	F38_unspecified	1	4	SE	Homo sapiens (modern human)	double	none	<PATH_TO_DATA>/F38_unspecified_L1_R1.fastq.gz	NA	NA	ERR1427822.fastq.gz	NA	NA
+WC1	WC1_unspecified	1	4	SE	Homo sapiens (modern human)	double	none	<PATH_TO_DATA>/WC1_unspecified_L1_R1.fastq.gz	NA	NA	ERR1427821.fastq.gz	NA	NA
diff --git a/packages/2016_Broushaki_Science/2016_Broushaki_Science.tsv_patch.sh b/packages/2016_Broushaki_Science/2016_Broushaki_Science.tsv_patch.sh
@@ -0,0 +1,45 @@
+#!/usr/bin/env bash
+set -uo pipefail ## Pipefail, complain on new unassigned variables.
+
+## Track the version of the TSV_patch template used
+VERSION='0.2.1dev'
+
+## This script is applied to the eager input TSV file locally to edit the dummy
+##    path to the fastQ files added by `create_eager_input.sh` to a real local
+##    path provided as a positional argument. Any further local tweaks to the
+##    TSV before running eager should be added below that in the form of bash
+##    commands to aid in reproducibility.
+
+## usage tsv_patch.sh <local_data_dir> <input_tsv> <path/to/source_me.sh>
+
+local_data_dir="$(readlink -f ${1})"
+input_tsv="$(readlink -f ${2})"
+output_tsv="$(dirname ${local_data_dir})/$(basename -s ".tsv" ${input_tsv}).finalised.tsv"
+columns_to_keep=("Sample_Name" "Library_ID" "Lane" "Colour_Chemistry" "SeqType" "Organism" "Strandedness" "UDG_Treatment" "R1" "R2" "BAM")
+source $(readlink -f ${3}) ## Path to helper function script should be provided as 3rd argument. https://github.com/poseidon-framework/poseidon-eager/blob/main/scripts/source_me.sh
+
+## Index non-proliferated columns and exclude them from the finalised TSV
+cut_selector=''
+tsv_header=($(head -n1 ${input_tsv}))
+for col_name in ${columns_to_keep[@]}; do
+  let idx=$(get_index_of ${col_name} "${columns_to_keep[@]}")+1 ## awk uses 1-based indexing
+  if [[ ! ${idx} -eq -1 ]]; then
+    cut_selector+="${idx},"
+  fi
+done
+
+## Remove added columns, and put columns in right order
+cut -f ${cut_selector%,} ${input_tsv} > ${output_tsv}
+sed -i -e "s|<PATH_TO_DATA>|${local_data_dir}|g" ${output_tsv}
+
+## Any further commands to edit the file before finalisation should be added below as shown
+# sed -ie 's/replace_this/with_this/g' ${output_tsv}
+
+## Keep track of versions
+version_file="$(dirname ${input_tsv})/script_versions.txt"
+##    Remove versions from older run if there
+grep -v -F -e "$(basename ${0})" -e "source_me.sh for final TSV" ${version_file} >${version_file}.new
+##    Then add new versions
+echo -e "$(basename ${0}):\t${VERSION}" >> ${version_file}.new
+echo -e "source_me.sh for final TSV:\t${HELPER_FUNCTION_VERSION}" >>${version_file}.new
+mv ${version_file}.new ${version_file}
diff --git a/packages/2016_Broushaki_Science/script_versions.txt b/packages/2016_Broushaki_Science/script_versions.txt
@@ -0,0 +1,2 @@
+create_eager_input.sh:	0.5.1
+source_me.sh for initial TSV:	0.5.2
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		create_eager_input.sh: 0.5.1
		source_me.sh for initial TSV: 0.5.2