Script to access data from the GSA

packages/2025_Liu_ShanDong/2025_Liu_ShanDong.config

@@ -0,0 +1,41 @@
+// Keep track of config versions
+minotaur_release='0.4.0dev' // The release tag of the poseidon-eager repository used for processing and config file retrieval
+config_template_version='0.3.0dev'
+package_config_version='0.3.0dev'
+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
+  */
+}

packages/2025_Liu_ShanDong/2025_Liu_ShanDong.tsv

@@ -0,0 +1,89 @@
+Sample_Name	Library_ID	Lane	Colour_Chemistry	SeqType	Organism	Strandedness	UDG_Treatment	R1	R2	BAM	R1_target_file	R2_target_file
+BQ4579	BQ4579_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4579_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4580_k	BQ4580_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4580_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4582	BQ4582_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4582_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4583_k	BQ4583_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4583_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4584	BQ4584_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4584_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4585	BQ4585_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4585_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4586_k	BQ4586_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4586_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4587	BQ4587_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4587_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4588	BQ4588_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4588_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4589_k	BQ4589_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4589_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4609	BQ4609_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4609_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4610_o	BQ4610_o_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4610_o_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4611_d_k	BQ4611_d_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4611_d_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4612_k	BQ4612_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4612_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4613	BQ4613_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4613_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4614	BQ4614_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4614_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4615	BQ4615_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4615_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4618	BQ4618_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4618_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4619_k	BQ4619_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4619_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4620_k	BQ4620_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4620_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4621_k	BQ4621_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4621_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4622_low_k	BQ4622_low_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4622_low_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4623	BQ4623_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4623_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4624	BQ4624_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4624_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4625_d_k	BQ4625_d_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4625_d_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4626	BQ4626_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4626_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4627	BQ4627_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4627_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4628_o	BQ4628_o_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4628_o_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4648_k	BQ4648_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4648_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+BQ4649_k	BQ4649_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/BQ4649_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+CZY4652	CZY4652_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/CZY4652_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+CZY4653	CZY4653_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/CZY4653_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+CZY4654	CZY4654_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/CZY4654_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+CZY4656	CZY4656_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/CZY4656_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+CZY4657	CZY4657_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/CZY4657_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+FJ4777	FJ4777_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/FJ4777_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+FJ4778	FJ4778_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/FJ4778_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+FJ4779	FJ4779_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/FJ4779_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+GS1689_k	GS1689_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/GS1689_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+GS1691	GS1691_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/GS1691_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+GS1693	GS1693_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/GS1693_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+HL4785	HL4785_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/HL4785_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+HL4786	HL4786_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/HL4786_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+HL4788_o	HL4788_o_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/HL4788_o_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4592	LJZ4592_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4592_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4593	LJZ4593_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4593_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4594	LJZ4594_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4594_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4595	LJZ4595_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4595_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4596	LJZ4596_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4596_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4597	LJZ4597_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4597_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4598	LJZ4598_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4598_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4599	LJZ4599_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4599_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4600_o	LJZ4600_o_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4600_o_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4601	LJZ4601_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4601_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4602	LJZ4602_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4602_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4605	LJZ4605_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4605_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4606	LJZ4606_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4606_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4607	LJZ4607_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4607_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+LJZ4608	LJZ4608_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/LJZ4608_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+TL4770	TL4770_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/TL4770_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+TL4772	TL4772_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/TL4772_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+TL4773_d_k	TL4773_d_k_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/TL4773_d_k_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+TL4774	TL4774_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/TL4774_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+TL4775	TL4775_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/TL4775_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+TL4776	TL4776_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/TL4776_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+TL5192	TL5192_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/TL5192_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+TL5193	TL5193_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/TL5193_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+XC1711	XC1711_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/XC1711_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+XC1715	XC1715_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/XC1715_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+XJS4345	XJS4345_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/XJS4345_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+XJS4353	XJS4353_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/XJS4353_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+XJS4354	XJS4354_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/XJS4354_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+XZ3467	XZ3467_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/XZ3467_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+XZ3468	XZ3468_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/XZ3468_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+XZ3469	XZ3469_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/XZ3469_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+XZ3471	XZ3471_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/XZ3471_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+XZ5197	XZ5197_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/XZ5197_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+YJC4337	YJC4337_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/YJC4337_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+YJC4338	YJC4338_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/YJC4338_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+YJC4339	YJC4339_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/YJC4339_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+YJC4340	YJC4340_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/YJC4340_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+YJC4341	YJC4341_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/YJC4341_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+YJC4659	YJC4659_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/YJC4659_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+YX4790_d	YX4790_d_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/YX4790_d_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+YX4793	YX4793_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/YX4793_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+YX5194	YX5194_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/YX5194_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+YX5195	YX5195_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/YX5195_n/a_L1_R1.fastq.gz	NA	NA	a	NA
+YX5196	YX5196_n/a	1		SE	Homo sapiens (modern human)	double	half	<PATH_TO_DATA>/YX5196_n/a_L1_R1.fastq.gz	NA	NA	a	NA

packages/2025_Liu_ShanDong/2025_Liu_ShanDong.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/2025_Liu_ShanDong/script_versions.txt

@@ -0,0 +1,2 @@
+create_eager_input.sh:	0.2.1dev
+source_me.sh for initial TSV:	0.2.3dev