Add package: 2022_Tiesler_colonialCampeche

.github/workflows/add_pr_labels.yml

@@ -32,7 +32,7 @@ jobs:
         #   GITHUB_TOKEN: ${{ secrets.delphis_bot_org_token }}
 
       - name: Add label if .janno files exist
-        if: env.has_janno == 'true'
+        if: env.has_janno == 'true' && github.event.pull_request.head.repo.full_name == 'poseidon-framework/minotaur-recipes'
         uses: actions-ecosystem/action-add-labels@v1
         with:
           # github_token: ${{ secrets.delphis_bot_org_token }}

packages/2022_Tiesler_colonialCampeche/2022_Tiesler_colonialCampeche.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/2022_Tiesler_colonialCampeche/2022_Tiesler_colonialCampeche.janno

@@ -0,0 +1,11 @@
+Poseidon_ID	Genetic_Sex	Group_Name	Alternative_IDs	Relation_To	Relation_Degree	Relation_Type	Relation_Note	Collection_ID	Country	Country_ISO	Location	Site	Latitude	Longitude	Date_Type	Date_C14_Labnr	Date_C14_Uncal_BP	Date_C14_Uncal_BP_Err	Date_BC_AD_Start	Date_BC_AD_Median	Date_BC_AD_Stop	Date_Note	MT_Haplogroup	Y_Haplogroup	Source_Tissue
+I10859	F	Mexico_Colonial_	n/a	n/a	n/a	n/a	n/a	n/a	Mexico	MX	Campeche	Campeche	20.24	-90.46	contextual	n/a	n/a	n/a	1540	1610	1680	n/a	B2	Q1a2a1a1	bone_petrous
+I10860	F	Mexico_Colonial_African	n/a	n/a	n/a	n/a	n/a	n/a	Mexico	MX	Campeche	Campeche	20.24	-90.46	contextual	n/a	n/a	n/a	1540	1610	1680	n/a	L3e2b+152	n/a	bone_petrous
+I10861	M	Mexico_Colonial	n/a	n/a	n/a	n/a	n/a	n/a	Mexico	MX	Campeche	Campeche	20.24	-90.46	contextual	n/a	n/a	n/a	1540	1610	1680	n/a	B2+16278	Q1a2a1a1	bone_petrous
+I10862	M	Mexico_Colonial	n/a	n/a	n/a	n/a	n/a	n/a	Mexico	MX	Campeche	Campeche	20.24	-90.46	contextual	n/a	n/a	n/a	1540	1610	1680	n/a	A2	Q1a2a1a	bone_petrous
+I10863	F	Mexico_Colonial	n/a	n/a	n/a	n/a	n/a	n/a	Mexico	MX	Campeche	Campeche	20.24	-90.46	contextual	n/a	n/a	n/a	1540	1610	1680	n/a	A2m	n/a	bone_petrous
+I8558	M	Mexico_Colonial_o	n/a	n/a	n/a	n/a	n/a	n/a	Mexico	MX	Campeche	Campeche	20.24	-90.46	contextual	n/a	n/a	n/a	1540	1610	1680	n/a	X2d2	I2a2a1b	bone_petrous
+I8559	M	Mexico_Colonial	n/a	n/a	n/a	n/a	n/a	n/a	Mexico	MX	Campeche	Campeche	20.24	-90.46	C14	PSUAMS-4431	380	20	1446	1570	1624	n/a	R	n/a	bone_petrous
+I8555	F	Mexico_Colonial	n/a	n/a	n/a	n/a	n/a	n/a	Mexico	MX	Campeche	Campeche	20.24	-90.46	C14	PSUAMS-4430	335	20	1481	1615	1639	n/a	A2+(64)	n/a	bone_petrous
+I8556	F	Mexico_Colonial	n/a	n/a	n/a	n/a	n/a	n/a	Mexico	MX	Campeche	Campeche	20.24	-90.46	contextual	n/a	n/a	n/a	1540	1610	1680	n/a	A2r	n/a	bone_petrous
+I8557	F	Mexico_Colonial	n/a	n/a	n/a	n/a	n/a	n/a	Mexico	MX	Campeche	Campeche	20.24	-90.46	contextual	n/a	n/a	n/a	1540	1610	1680	n/a	A2+(64)	n/a	bone_petrous

packages/2022_Tiesler_colonialCampeche/2022_Tiesler_colonialCampeche.ssf

@@ -0,0 +1,21 @@
+poseidon_IDs	udg	library_built	notes	run_accession	sample_accession	study_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
+I10859	half	ds	n/a	ERR10024820	SAMEA110460290	PRJEB50901	I10859_auto	ERS12558320	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558320	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/020/ERR10024820/ERR10024820.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/020/ERR10024820/ERR10024820.fastq.gz	299547010	b52e33953172c9cc125c0004717e36cc	10500049	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024820/I10859_auto.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024820/I10859_auto.bam.bai	6d8218d59d2b359a9eda9056fb2cd070;9033be2c8f161b8b8dff468bd2d7a788
+I10860	half	ds	n/a	ERR10024822	SAMEA110460292	PRJEB50901	I10860_auto	ERS12558322	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558322	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/022/ERR10024822/ERR10024822.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/022/ERR10024822/ERR10024822.fastq.gz	173605539	ecd6e523cc8879911603c6b8233a5e8d	5845153	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024822/I10860_auto.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024822/I10860_auto.bam.bai	2f9e63dded86c72c9f0d058788deda81;e1252775805908d320e7130d8d9116d7
+I10860	half	ds	n/a	ERR10024823	SAMEA110460293	PRJEB50901	I10860_mt	ERS12558323	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558323	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/023/ERR10024823/ERR10024823.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/023/ERR10024823/ERR10024823.fastq.gz	1710042	3a5c1f02190b55f7335c1396899b3dd8	97318	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024823/I10860_mt.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024823/I10860_mt.bam.bai	e294ec10218d8a714df665a17a912c03;8b08fe6051a428d1d63b7c669c0bfa3b
+I10861	half	ds	n/a	ERR10024824	SAMEA110460294	PRJEB50901	I10861_auto	ERS12558324	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558324	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/024/ERR10024824/ERR10024824.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/024/ERR10024824/ERR10024824.fastq.gz	202652666	96a037f98e7b9be878aef98b9ddbe9b9	6608872	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024824/I10861_auto.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024824/I10861_auto.bam.bai	efb6758fade0da4bef5effd1393ae132;4455ebc52988f33eb380bfe8095f1b58
+I10861	half	ds	n/a	ERR10024825	SAMEA110460295	PRJEB50901	I10861_mt	ERS12558325	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558325	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/025/ERR10024825/ERR10024825.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/025/ERR10024825/ERR10024825.fastq.gz	1591243	f0cf33874043b27ad23f53606b134d74	88092	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024825/I10861_mt.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024825/I10861_mt.bam.bai	35de16aa41f23efb3a973bd7b5d8f8f1;2ea76d6f28015939372f21465d8f64fb
+I10862	half	ds	n/a	ERR10024826	SAMEA110460296	PRJEB50901	I10862_auto	ERS12558326	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558326	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/026/ERR10024826/ERR10024826.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/026/ERR10024826/ERR10024826.fastq.gz	172569326	ed36dbd332430655c97450986befd877	5911868	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024826/I10862_auto.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024826/I10862_auto.bam.bai	c7ea6a786dcc8fa7660af56108f11a76;e8314f9614fe7a0cce4748228dd76535
+I10863	half	ds	n/a	ERR10024828	SAMEA110460298	PRJEB50901	I10863_auto	ERS12558328	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558328	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/028/ERR10024828/ERR10024828.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/028/ERR10024828/ERR10024828.fastq.gz	399969993	3db35b7d6cc684c2811ac21b87d886ba	13805187	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024828/I10863_auto.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024828/I10863_auto.bam.bai	31ee33f822086e23d6ac1a3935cabaf2;afab3f2556b6992edcb2c0afef8fd8b8
+I8558	half	ds	n/a	ERR10024836	SAMEA110460306	PRJEB50901	I8558_auto	ERS12558336	2022-08-07	2022-08-07	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558336	OTHER					0	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024836/I8558_auto.bam	dbc563d88e769f01b640fb88fceac28b
+I8558	half	ds	n/a	ERR10024837	SAMEA110460307	PRJEB50901	I8558_mt	ERS12558337	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558337	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/037/ERR10024837/ERR10024837.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/037/ERR10024837/ERR10024837.fastq.gz	443549	6ebac4d22bae77c80d4e807212872e61	20021	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024837/I8558_mt.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024837/I8558_mt.bam.bai	42691afc59127a2bb097faf4fec0a442;186e3ef209e7585078971ee770ace5f8
+I8559	half	ds	n/a	ERR10024839	SAMEA110460309	PRJEB50901	I8559_mt	ERS12558339	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558339	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/039/ERR10024839/ERR10024839.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/039/ERR10024839/ERR10024839.fastq.gz	395981	a71e771484127cedae344949313f6d8b	17877	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024839/I8559_mt.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024839/I8559_mt.bam.bai	ff622b7c39714f925802522f3d6ca72b;39fd548c8780a30e1f93cb6e783791ae
+I10859	half	ds	n/a	ERR10024821	SAMEA110460291	PRJEB50901	I10859_mt	ERS12558321	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558321	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/021/ERR10024821/ERR10024821.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/021/ERR10024821/ERR10024821.fastq.gz	4784965	f29196418c329647e4400087740b0b60	263041	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024821/I10859_mt.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024821/I10859_mt.bam.bai	361b1cb823c9c9cf0831e142520a6439;930782ca7105775f37811ff3b477321b
+I10862	half	ds	n/a	ERR10024827	SAMEA110460297	PRJEB50901	I10862_mt	ERS12558327	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558327	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/027/ERR10024827/ERR10024827.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/027/ERR10024827/ERR10024827.fastq.gz	1378040	f88ecdca84065186eea8c26487f89abb	78650	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024827/I10862_mt.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024827/I10862_mt.bam.bai	ff36e70b76c92effc97943e88d74abf3;d1b5172cbc0e2f2d4c59adfa0ef54393
+I10863	half	ds	n/a	ERR10024829	SAMEA110460299	PRJEB50901	I10863_mt	ERS12558329	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558329	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/029/ERR10024829/ERR10024829.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/029/ERR10024829/ERR10024829.fastq.gz	4258100	79a3b2e29a82da51060777b5bc9372ac	226286	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024829/I10863_mt.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024829/I10863_mt.bam.bai	8298a549f5af819c38167a9074487772;9351a683caf3995e424caeb793d935b1
+I8555	half	ds	n/a	ERR10024830	SAMEA110460300	PRJEB50901	I8555_auto	ERS12558330	2022-08-07	2022-08-07	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558330	OTHER					0	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024830/I8555_auto.bam	9a050bc3bf289482878d8d2a050b1c40
+I8556	half	ds	n/a	ERR10024832	SAMEA110460302	PRJEB50901	I8556_auto	ERS12558332	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558332	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/032/ERR10024832/ERR10024832.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/032/ERR10024832/ERR10024832.fastq.gz	10069607	fc5eaef693aa8781b72a74838801f2d9	373844	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024832/I8556_auto.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024832/I8556_auto.bam.bai	4b070f9fd03730cf6f5a698658dba143;65517a967ff15291d5937c827c25286c
+I8555	half	ds	n/a	ERR10024831	SAMEA110460301	PRJEB50901	I8555_mt	ERS12558331	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558331	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/031/ERR10024831/ERR10024831.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/031/ERR10024831/ERR10024831.fastq.gz	261250	67e3316bc126ae6c288e21221e086b69	11338	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024831/I8555_mt.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024831/I8555_mt.bam.bai	c4929a7c4a9499e395673b79f47a3df4;8fe761372b7d4c33601665636b38054f
+I8556	half	ds	n/a	ERR10024833	SAMEA110460303	PRJEB50901	I8556_mt	ERS12558333	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558333	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/033/ERR10024833/ERR10024833.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/033/ERR10024833/ERR10024833.fastq.gz	111468	3bf94c8ac5dbf5cedbcb72b00eb44c3f	5006	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024833/I8556_mt.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024833/I8556_mt.bam.bai	0db8191b86f143f72cb6c41ebc059236;dc3ac28aefd3964eb04058a83d6d4dc8
+I8557	half	ds	n/a	ERR10024834	SAMEA110460304	PRJEB50901	I8557_auto	ERS12558334	2022-08-07	2022-08-07	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558334	OTHER					0	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024834/I8557_auto.bam	c960aba6eed82c7da8ea69445d7d88d9
+I8557	half	ds	n/a	ERR10024835	SAMEA110460305	PRJEB50901	I8557_mt	ERS12558335	2022-08-07	2022-08-08	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558335	OTHER	ftp.sra.ebi.ac.uk/vol1/fastq/ERR100/035/ERR10024835/ERR10024835.fastq.gz	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR100/035/ERR10024835/ERR10024835.fastq.gz	315440	b9be6056bf59344ed4a03c96f490fc7e	14220	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024835/I8557_mt.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024835/I8557_mt.bam.bai	de7d94f822891b6fc5f146e653e78c62;dba1653f35a2e9d526373a5228e1a7a9
+I8559	half	ds	n/a	ERR10024838	SAMEA110460308	PRJEB50901	I8559_auto	ERS12558338	2022-08-07	2022-08-07	Illumina HiSeq X	SINGLE	GENOMIC	ILLUMINA	ERS12558338	OTHER					0	ftp.sra.ebi.ac.uk/vol1/run/ERR100/ERR10024838/I8559_auto.bam	3ce524a5460c0c903fbf3892c4dfcf28

packages/2022_Tiesler_colonialCampeche/2022_Tiesler_colonialCampeche.tsv

@@ -0,0 +1,21 @@
+Sample_Name	Library_ID	Lane	Colour_Chemistry	SeqType	Organism	Strandedness	UDG_Treatment	R1	R2	BAM	R1_target_file	R2_target_file	BAM_target
+I10859	I10859_ERS12558320	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I10859_ERS12558320_L1_R1.fastq.gz	NA	NA	ERR10024820.fastq.gz	NA	NA
+I10860	I10860_ERS12558322	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I10860_ERS12558322_L1_R1.fastq.gz	NA	NA	ERR10024822.fastq.gz	NA	NA
+I10860	I10860_ERS12558323	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I10860_ERS12558323_L1_R1.fastq.gz	NA	NA	ERR10024823.fastq.gz	NA	NA
+I10861	I10861_ERS12558324	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I10861_ERS12558324_L1_R1.fastq.gz	NA	NA	ERR10024824.fastq.gz	NA	NA
+I10861	I10861_ERS12558325	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I10861_ERS12558325_L1_R1.fastq.gz	NA	NA	ERR10024825.fastq.gz	NA	NA
+I10862	I10862_ERS12558326	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I10862_ERS12558326_L1_R1.fastq.gz	NA	NA	ERR10024826.fastq.gz	NA	NA
+I10863	I10863_ERS12558328	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I10863_ERS12558328_L1_R1.fastq.gz	NA	NA	ERR10024828.fastq.gz	NA	NA
+I8558	I8558_ERS12558336	1	4	SE	Homo sapiens (modern human)	double	half	NA	NA	<PATH_TO_DATA>/I8558_ERS12558336_L1.bam	NA	NA	I8558_auto.bam
+I8558	I8558_ERS12558337	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I8558_ERS12558337_L1_R1.fastq.gz	NA	NA	ERR10024837.fastq.gz	NA	NA
+I8559	I8559_ERS12558339	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I8559_ERS12558339_L1_R1.fastq.gz	NA	NA	ERR10024839.fastq.gz	NA	NA
+I10859	I10859_ERS12558321	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I10859_ERS12558321_L1_R1.fastq.gz	NA	NA	ERR10024821.fastq.gz	NA	NA
+I10862	I10862_ERS12558327	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I10862_ERS12558327_L1_R1.fastq.gz	NA	NA	ERR10024827.fastq.gz	NA	NA
+I10863	I10863_ERS12558329	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I10863_ERS12558329_L1_R1.fastq.gz	NA	NA	ERR10024829.fastq.gz	NA	NA
+I8555	I8555_ERS12558330	1	4	SE	Homo sapiens (modern human)	double	half	NA	NA	<PATH_TO_DATA>/I8555_ERS12558330_L1.bam	NA	NA	I8555_auto.bam
+I8556	I8556_ERS12558332	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I8556_ERS12558332_L1_R1.fastq.gz	NA	NA	ERR10024832.fastq.gz	NA	NA
+I8555	I8555_ERS12558331	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I8555_ERS12558331_L1_R1.fastq.gz	NA	NA	ERR10024831.fastq.gz	NA	NA
+I8556	I8556_ERS12558333	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I8556_ERS12558333_L1_R1.fastq.gz	NA	NA	ERR10024833.fastq.gz	NA	NA
+I8557	I8557_ERS12558334	1	4	SE	Homo sapiens (modern human)	double	half	NA	NA	<PATH_TO_DATA>/I8557_ERS12558334_L1.bam	NA	NA	I8557_auto.bam
+I8557	I8557_ERS12558335	1	4	SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/I8557_ERS12558335_L1_R1.fastq.gz	NA	NA	ERR10024835.fastq.gz	NA	NA
+I8559	I8559_ERS12558338	1	4	SE	Homo sapiens (modern human)	double	half	NA	NA	<PATH_TO_DATA>/I8559_ERS12558338_L1.bam	NA	NA	I8559_auto.bam

packages/2022_Tiesler_colonialCampeche/2022_Tiesler_colonialCampeche.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}