Add package: 2024_Ellegaard_WellMan

packages/2024_Ellegaard_WellMan/2024_Ellegaard_WellMan.config

@@ -0,0 +1,41 @@
+// Keep track of config versions
+minotaur_release='1.0.0' // The release tag of the poseidon-eager repository used for processing and config file retrieval
+config_template_version='1.0.0'
+package_config_version='1.0.0'
+minotaur_config_base="https://raw.githubusercontent.com/poseidon-framework/poseidon-eager/${minotaur_release}/conf"
+
+// This configuration file is designed to be a used with the nf-core/eager pipeline.
+//   Instead of having to specify all other configurations for the Minotaur pipeline
+//   on runtime, they are all contained in this file and loaded automatically upon
+//   specifying this config file during runtime. Additionally, any parameters that
+//   need to be altered from the defaults can be specified here.
+//
+// The intention is to make it easy for users to understand and reproduce the output
+//  from processing with the Minotaur workflow processing from the contents of a
+//  single file.
+
+// Load configuration profiles. They are loaded from the minotaur_config_base URL, main branch.
+// The loaded config includes code that loads the institutional configs from https://github.com/poseidon-framework/minotaur-institutional-configs.
+includeConfig "${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
+  */
+}

packages/2024_Ellegaard_WellMan/2024_Ellegaard_WellMan.ssf

@@ -0,0 +1,15 @@
+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
+WM	minus	ss	n/a	ERR12268596	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTN1	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/096/ERR12268596/ERR12268596_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/096/ERR12268596/ERR12268596_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/096/ERR12268596/ERR12268596_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/096/ERR12268596/ERR12268596_2.fastq.gz	4603211674;5838732166	fcd11267f15f20d0f323f3818f0474fa;9e79316c6d79c46b7dc8e3a33685abab	288972166	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268596/WMTN1_FKDL210050469-1a-AK9315-AK3837_HVW7MDSXY_L1_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268596/WMTN1_FKDL210050469-1a-AK9315-AK3837_HVW7MDSXY_L1_2.fq.gz	20cee47d63b1f60c247932eacc906efc;5c8855ff45a77d73c850bd4c9341d306
+WM	minus	ss	n/a	ERR12268599	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTN1	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/099/ERR12268599/ERR12268599_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/099/ERR12268599/ERR12268599_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/099/ERR12268599/ERR12268599_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/099/ERR12268599/ERR12268599_2.fastq.gz	22287793880;21604123864	a3f3b3ef18e3911ae2ffc8a07cc2d628;bce19628dee897072f6987f0f925a8d0	1290721234	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268599/WMTN1_EKDL210002175-1a_H5T3NDSX2_L3_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268599/WMTN1_EKDL210002175-1a_H5T3NDSX2_L3_2.fq.gz	be02281fe3a017ce559decfabe8a5fc2;234c2a5f183ff4e6d775d1edf8220154
+WM	minus	ss	n/a	ERR12268600	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTN1	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/000/ERR12268600/ERR12268600_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/000/ERR12268600/ERR12268600_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/000/ERR12268600/ERR12268600_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/000/ERR12268600/ERR12268600_2.fastq.gz	13648262149;13959146528	95282b8d36348c46bb4594fdc2d9dfbf;3ce33e0b2b8281a0740534fe979c24a4	772351510	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268600/WMTN1_EKDL210002175-1a_H5T3NDSX2_L4_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268600/WMTN1_EKDL210002175-1a_H5T3NDSX2_L4_2.fq.gz	cb3f4b1de7460ce0167d80c9b4cb2dbc;49b865ab700f7c7d608aa940fe997df4
+WM	minus	ss	n/a	ERR12268597	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTN1	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/097/ERR12268597/ERR12268597_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/097/ERR12268597/ERR12268597_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/097/ERR12268597/ERR12268597_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/097/ERR12268597/ERR12268597_2.fastq.gz	28883583455;20548113806	64fedec31a4f72ac07319fa7d84dc913;6e8809388961d5c05b631fcbf4337a4f	1436445340	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268597/WMTN1_EKDL210002175-1a_H5CT2DSX2_L3_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268597/WMTN1_EKDL210002175-1a_H5CT2DSX2_L3_2.fq.gz	112dc43859788be38421b15bf68efd8f;b5cc95b328eed24c01899bf917139d16
+WM	minus	ss	n/a	ERR12268598	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTN1	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/098/ERR12268598/ERR12268598_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/098/ERR12268598/ERR12268598_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/098/ERR12268598/ERR12268598_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/098/ERR12268598/ERR12268598_2.fastq.gz	26405073967;27136104011	cd94b414c38f0a4f521828c4e8f1d2af;e6d76ddecac448e642103c3a7878d0af	1593754376	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268598/WMTN1_EKDL210002175-1a_H5T3NDSX2_L1_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268598/WMTN1_EKDL210002175-1a_H5T3NDSX2_L1_2.fq.gz	efc3d56d5cfbc06b48eb2d61814f6df9;7d5d781cd8b4f0e55f1b06fea5095ef5
+WM	minus	ss	n/a	ERR12268601	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTN2	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/001/ERR12268601/ERR12268601_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/001/ERR12268601/ERR12268601_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/001/ERR12268601/ERR12268601_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/001/ERR12268601/ERR12268601_2.fastq.gz	5694399192;7720149898	03dcc3869cd9843eb92812b01564fc8d;d573d2c9b1d66e0323011bd5108470dd	348239268	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268601/WMTN2_FKDL210050469-1a-AK36040-AK7764_HVW7MDSXY_L1_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268601/WMTN2_FKDL210050469-1a-AK36040-AK7764_HVW7MDSXY_L1_2.fq.gz	dd4318776b9011e8bf0aebd9e904fc14;00512a2c59c0ef50b1b8942580b1fcf3
+WM	minus	ss	n/a	ERR12268602	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTN3	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/002/ERR12268602/ERR12268602_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/002/ERR12268602/ERR12268602_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/002/ERR12268602/ERR12268602_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/002/ERR12268602/ERR12268602_2.fastq.gz	2582549581;3621271887	e10217a927a3c5b8557daab692f4c5af;b6e47295b34b49178b3ae156ea7bed69	161777748	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268602/WMTN3_FKDL210050469-1a-AK36041-AK10080_HVW7MDSXY_L1_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268602/WMTN3_FKDL210050469-1a-AK36041-AK10080_HVW7MDSXY_L1_2.fq.gz	cc4bb5cbf51869f5c8386d00be6be1d1;c961fba533e1e3059e75ae76a13a19ff
+WM	half	ss	USER-treated	ERR12268604	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTU1	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/004/ERR12268604/ERR12268604_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/004/ERR12268604/ERR12268604_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/004/ERR12268604/ERR12268604_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/004/ERR12268604/ERR12268604_2.fastq.gz	40763830128;30446711714	5c6b1dda83f17ef20821c7f2245eb76f;c4089bd3cb35f2726d9909aa7c452457	1778710978	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268604/WMTU1_EKDL210002174-1a_H5CT2DSX2_L3_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268604/WMTU1_EKDL210002174-1a_H5CT2DSX2_L3_2.fq.gz	9780045cdde32f07058fc3c4b8904d57;f041c272f4ec7db2a5a4855d74df5ea9
+WM	half	ss	USER-treated	ERR12268606	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTU1	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/006/ERR12268606/ERR12268606_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/006/ERR12268606/ERR12268606_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/006/ERR12268606/ERR12268606_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/006/ERR12268606/ERR12268606_2.fastq.gz	19100229136;19993694769	8c53accde08a66f6aca5f5e3f70c75aa;6bfd600ebcd7515328b57ae41b50365c	1005215506	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268606/WMTU1_EKDL210002174-1a_H7KWWDSX2_L3_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268606/WMTU1_EKDL210002174-1a_H7KWWDSX2_L3_2.fq.gz	6b727691490a1fd6f495a2d87f2f7338;79ba6ca50d783baa03130004dd68bc09
+WM	half	ss	USER-treated	ERR12268607	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTU1	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/007/ERR12268607/ERR12268607_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/007/ERR12268607/ERR12268607_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/007/ERR12268607/ERR12268607_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/007/ERR12268607/ERR12268607_2.fastq.gz	20795445093;19548273640	4aa0022d5513555ebf8f39078d62b553;2797712bfe11a6be4f1407a6f4d42597	1057346922	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268607/WMTU1_EKDL210002174-1a_H7KWWDSX2_L4_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268607/WMTU1_EKDL210002174-1a_H7KWWDSX2_L4_2.fq.gz	f3ba33bea23baab44c4a09f6914f8d4d;8d0716cee204243cda5205d9360f0428
+WM	half	ss	USER-treated	ERR12268603	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTU1	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/003/ERR12268603/ERR12268603_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/003/ERR12268603/ERR12268603_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/003/ERR12268603/ERR12268603_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/003/ERR12268603/ERR12268603_2.fastq.gz	5942208653;7150046877	ee9343774c025724f84b29b2ba5d5f2e;43fa6aba09a089c71db58d33f2764189	333411234	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268603/WMTU1_FKDL210050469-1a-AK3384-AK17268_HVW7MDSXY_L1_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268603/WMTU1_FKDL210050469-1a-AK3384-AK17268_HVW7MDSXY_L1_2.fq.gz	14b2b9e7e92e1856709d3d9fd0584010;5c9d7b2f4e580380a20f8db55b3b7963
+WM	half	ss	USER-treated	ERR12268605	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTU1	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/005/ERR12268605/ERR12268605_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/005/ERR12268605/ERR12268605_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/005/ERR12268605/ERR12268605_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/005/ERR12268605/ERR12268605_2.fastq.gz	20386620160;19258562017	6b14403d7dbac24458c8eb4e94db330b;9134168063dfd64ef14addd28969b2b5	1034445802	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268605/WMTU1_EKDL210002174-1a_H7KWWDSX2_L2_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268605/WMTU1_EKDL210002174-1a_H7KWWDSX2_L2_2.fq.gz	fba6c258357d304132f3ec547d644ea7;2ba33c9590d9a40cb16671e0c0befc9d
+WM	half	ss	USER-treated	ERR12268608	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTU2	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/008/ERR12268608/ERR12268608_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/008/ERR12268608/ERR12268608_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/008/ERR12268608/ERR12268608_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/008/ERR12268608/ERR12268608_2.fastq.gz	4791897606;3812260643	29f2aa9820c2d6386326b8557bc71da2;7492c37e64c82e7a518b841b3a55b7ce	224513544	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268608/WMTU2_FKDL210050469-1a-AK3825-AK17270_HVW7MDSXY_L1_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268608/WMTU2_FKDL210050469-1a-AK3825-AK17270_HVW7MDSXY_L1_2.fq.gz	48c076a78401b738550ecd7e7c3ab944;641b1a8373da861490b2048c45a575e4
+WM	half	ss	USER-treated	ERR12268609	PRJEB69227	SAMEA114606680	WM	ERS16898600	2024-09-17	2024-09-17	Illumina NovaSeq 6000	PAIRED	GENOMIC	ILLUMINA	WMTU3	WGS	ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/009/ERR12268609/ERR12268609_1.fastq.gz;ftp.sra.ebi.ac.uk/vol1/fastq/ERR122/009/ERR12268609/ERR12268609_2.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/009/ERR12268609/ERR12268609_1.fastq.gz;fasp.sra.ebi.ac.uk:/vol1/fastq/ERR122/009/ERR12268609/ERR12268609_2.fastq.gz	9021696524;9617280497	e2a8f741b6e693c05ec039c4e43b78a3;c82b4c45831fee7cc1a23639a3c44e5c	394387606	ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268609/WMTU3_FKDL210050469-1a-AK2790-AK6045_HVW7MDSXY_L1_1.fq.gz;ftp.sra.ebi.ac.uk/vol1/run/ERR122/ERR12268609/WMTU3_FKDL210050469-1a-AK2790-AK6045_HVW7MDSXY_L1_2.fq.gz	53fe5b76c5689f00ca66e88c3d857440;fe86b548d1ad5fc46910a7fd05ca0732

packages/2024_Ellegaard_WellMan/2024_Ellegaard_WellMan.tsv

@@ -0,0 +1,15 @@
+Sample_Name	Library_ID	Lane	Colour_Chemistry	SeqType	Organism	Strandedness	UDG_Treatment	R1	R2	BAM	R1_target_file	R2_target_file	BAM_target
+WM_ss	WM_ss_WMTN1_ss	1	4	PE	Homo sapiens (modern human)	single	none	<PATH_TO_DATA>/WM_ss_WMTN1_ss_L1_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTN1_ss_L1_R2.fastq.gz	NA	ERR12268596_1.fastq.gz	ERR12268596_2.fastq.gz	NA
+WM_ss	WM_ss_WMTN1_ss	2	4	PE	Homo sapiens (modern human)	single	none	<PATH_TO_DATA>/WM_ss_WMTN1_ss_L2_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTN1_ss_L2_R2.fastq.gz	NA	ERR12268599_1.fastq.gz	ERR12268599_2.fastq.gz	NA
+WM_ss	WM_ss_WMTN1_ss	3	4	PE	Homo sapiens (modern human)	single	none	<PATH_TO_DATA>/WM_ss_WMTN1_ss_L3_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTN1_ss_L3_R2.fastq.gz	NA	ERR12268600_1.fastq.gz	ERR12268600_2.fastq.gz	NA
+WM_ss	WM_ss_WMTN1_ss	4	4	PE	Homo sapiens (modern human)	single	none	<PATH_TO_DATA>/WM_ss_WMTN1_ss_L4_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTN1_ss_L4_R2.fastq.gz	NA	ERR12268597_1.fastq.gz	ERR12268597_2.fastq.gz	NA
+WM_ss	WM_ss_WMTN1_ss	5	4	PE	Homo sapiens (modern human)	single	none	<PATH_TO_DATA>/WM_ss_WMTN1_ss_L5_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTN1_ss_L5_R2.fastq.gz	NA	ERR12268598_1.fastq.gz	ERR12268598_2.fastq.gz	NA
+WM_ss	WM_ss_WMTN2_ss	1	4	PE	Homo sapiens (modern human)	single	none	<PATH_TO_DATA>/WM_ss_WMTN2_ss_L1_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTN2_ss_L1_R2.fastq.gz	NA	ERR12268601_1.fastq.gz	ERR12268601_2.fastq.gz	NA
+WM_ss	WM_ss_WMTN3_ss	1	4	PE	Homo sapiens (modern human)	single	none	<PATH_TO_DATA>/WM_ss_WMTN3_ss_L1_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTN3_ss_L1_R2.fastq.gz	NA	ERR12268602_1.fastq.gz	ERR12268602_2.fastq.gz	NA
+WM_ss	WM_ss_WMTU1_ss	1	4	PE	Homo sapiens (modern human)	single	half	<PATH_TO_DATA>/WM_ss_WMTU1_ss_L1_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTU1_ss_L1_R2.fastq.gz	NA	ERR12268604_1.fastq.gz	ERR12268604_2.fastq.gz	NA
+WM_ss	WM_ss_WMTU1_ss	2	4	PE	Homo sapiens (modern human)	single	half	<PATH_TO_DATA>/WM_ss_WMTU1_ss_L2_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTU1_ss_L2_R2.fastq.gz	NA	ERR12268606_1.fastq.gz	ERR12268606_2.fastq.gz	NA
+WM_ss	WM_ss_WMTU1_ss	3	4	PE	Homo sapiens (modern human)	single	half	<PATH_TO_DATA>/WM_ss_WMTU1_ss_L3_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTU1_ss_L3_R2.fastq.gz	NA	ERR12268607_1.fastq.gz	ERR12268607_2.fastq.gz	NA
+WM_ss	WM_ss_WMTU1_ss	4	4	PE	Homo sapiens (modern human)	single	half	<PATH_TO_DATA>/WM_ss_WMTU1_ss_L4_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTU1_ss_L4_R2.fastq.gz	NA	ERR12268603_1.fastq.gz	ERR12268603_2.fastq.gz	NA
+WM_ss	WM_ss_WMTU1_ss	5	4	PE	Homo sapiens (modern human)	single	half	<PATH_TO_DATA>/WM_ss_WMTU1_ss_L5_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTU1_ss_L5_R2.fastq.gz	NA	ERR12268605_1.fastq.gz	ERR12268605_2.fastq.gz	NA
+WM_ss	WM_ss_WMTU2_ss	1	4	PE	Homo sapiens (modern human)	single	half	<PATH_TO_DATA>/WM_ss_WMTU2_ss_L1_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTU2_ss_L1_R2.fastq.gz	NA	ERR12268608_1.fastq.gz	ERR12268608_2.fastq.gz	NA
+WM_ss	WM_ss_WMTU3_ss	1	4	PE	Homo sapiens (modern human)	single	half	<PATH_TO_DATA>/WM_ss_WMTU3_ss_L1_R1.fastq.gz	<PATH_TO_DATA>/WM_ss_WMTU3_ss_L1_R2.fastq.gz	NA	ERR12268609_1.fastq.gz	ERR12268609_2.fastq.gz	NA

packages/2024_Ellegaard_WellMan/2024_Ellegaard_WellMan.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}

packages/2024_Ellegaard_WellMan/script_versions.txt

@@ -0,0 +1,2 @@
+create_eager_input.sh:	0.5.1
+source_me.sh for initial TSV:	0.5.2