diff --git a/packages/2023_VillaIslas_Science/2023_VillaIslas_Science.config b/packages/2023_VillaIslas_Science/2023_VillaIslas_Science.config new file mode 100644 index 0000000..ca10f8b --- /dev/null +++ b/packages/2023_VillaIslas_Science/2023_VillaIslas_Science.config @@ -0,0 +1,41 @@ +// Keep track of config versions +minotaur_release='0.3.0dev' // 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/2.4.6/parameters + + You can see the default values for parameters within poseidon-eager at: + https://github.com/poseidon-framework/poseidon-eager/blob/main/conf/Minotaur.config + */ +} diff --git a/packages/2023_VillaIslas_Science/2023_VillaIslas_Science.ssf b/packages/2023_VillaIslas_Science/2023_VillaIslas_Science.ssf new file mode 100644 index 0000000..3c4daf1 --- /dev/null +++ b/packages/2023_VillaIslas_Science/2023_VillaIslas_Science.ssf @@ -0,0 +1,40 @@ +poseidon_IDs udg library_built notes sample_accession study_accession run_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 +E2_Mich_b minus ds n/a SAMEA13300908 PRJEB51440 ERR9576879 E2_Mich_b ERS10903725 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA Whole-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/009/ERR9576879/ERR9576879.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/009/ERR9576879/ERR9576879.fastq.gz 46010068 fd0420483522106a21e6979e9b55342a 886820 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576879/E2_merged.realign.MD.uniq.pmd0.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576879/E2_merged.realign.MD.uniq.pmd0.bam.bai +11R_R_b minus ds n/a SAMEA13300897 PRJEB51440 ERR9576909 11R_R_b ERS10903714 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/009/ERR9576909/ERR9576909.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/009/ERR9576909/ERR9576909.fastq.gz 157704 50a6c1c38ee10b308f948579a00779e1 6258 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576909/11R_merged.realign.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576909/11R_merged.realign.rCRS.MD.bam.bai +2417C_TOL_a minus ds n/a SAMEA13300902 PRJEB51440 ERR9576910 2417C_TOL_a ERS10903719 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/000/ERR9576910/ERR9576910.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/000/ERR9576910/ERR9576910.fastq.gz 286443 1e75c61781c71214727bf64b8644f066 8526 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576910/2417C.RG.uniq.mt.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576910/2417C.RG.uniq.mt.realign.MD.bam.bai +333O_TOL_b minus ds n/a SAMEA13300896 PRJEB51440 ERR9576916 333O_TOL_b ERS10903713 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/006/ERR9576916/ERR9576916.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/006/ERR9576916/ERR9576916.fastq.gz 389947 c77b28fcdc823abf3db200caf23e45af 11784 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576916/333O.uniq.mt.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576916/333O.uniq.mt.realign.MD.bam.bai +333Q_TOL_b minus ds n/a SAMEA13300901 PRJEB51440 ERR9576917 333Q_TOL_b ERS10903718 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/007/ERR9576917/ERR9576917.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/007/ERR9576917/ERR9576917.fastq.gz 184387 b2e312da13fdd607741a9a31a755e0f0 5575 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576917/333Q.uniq.mt.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576917/333Q.uniq.mt.realign.MD.bam.bai +P_CCM_b minus ds n/a SAMEA13300894 PRJEB51440 ERR9576921 P_CCM_b ERS10903711 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/001/ERR9576921/ERR9576921.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/001/ERR9576921/ERR9576921.fastq.gz 300621 115e0448188d5397f01041049b394e1c 8930 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576921/Pepi.uniq.mt.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576921/Pepi.uniq.mt.realign.MD.bam.bai +E7_CdV_b minus ds n/a SAMEA13300914 PRJEB51440 ERR9576933 E7_CdV_b ERS10903731 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/003/ERR9576933/ERR9576933.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/003/ERR9576933/ERR9576933.fastq.gz 393258 2ba4bb7efe786ffd17271cb85af47e24 17153 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576933/E7CdV.merged.uniq.realign.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576933/E7CdV.merged.uniq.realign.rCRS.MD.bam.bai +E8_CdV_b minus ds n/a SAMEA13300915 PRJEB51440 ERR9576934 E8_CdV_b ERS10903732 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/004/ERR9576934/ERR9576934.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/004/ERR9576934/ERR9576934.fastq.gz 422029 0f3fc288ff3725cf2ed3d06263d8bdb6 17467 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576934/E8CdV.merged.uniq.realign.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576934/E8CdV.merged.uniq.realign.rCRS.MD.bam.bai +E1A_Mich_b minus ds n/a SAMEA13300907 PRJEB51440 ERR9576945 E1A_Mich_b ERS10903724 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/005/ERR9576945/ERR9576945.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/005/ERR9576945/ERR9576945.fastq.gz 111888 dfa3ca001cc6969cb06d2ace7fe606ae 3496 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576945/E1A_Mich.uniq.mt.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576945/E1A_Mich.uniq.mt.realign.MD.bam.bai +M2_Mich_b minus ds n/a SAMEA13300911 PRJEB51440 ERR9576949 M2_Mich_b ERS10903728 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/009/ERR9576949/ERR9576949.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/009/ERR9576949/ERR9576949.fastq.gz 76676 e68e3201c4797823816d1673ab96e9e4 2585 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576949/M2_Mich.uniq.mt.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576949/M2_Mich.uniq.mt.realign.MD.bam.bai +MOM6_ST_a minus ds n/a SAMEA13300893 PRJEB51440 ERR9128942 MOM6_ST_a ERS10903710 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA Whole-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR912/002/ERR9128942/ERR9128942.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR912/002/ERR9128942/ERR9128942.fastq.gz 29414435 0bb5d0b81e2854ba41d9b0fa599b55da 0 ftp.sra.ebi.ac.uk/vol1/run/ERR912/ERR9128942/MOM6_merged.realing.MD.uniq.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR912/ERR9128942/MOM6_merged.realing.MD.uniq.bam.bai +11R_R_b minus ds n/a SAMEA13300897 PRJEB51440 ERR9169797 11R_R_b ERS10903714 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA Whole-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR916/007/ERR9169797/ERR9169797.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR916/007/ERR9169797/ERR9169797.fastq.gz 20407352 23bb20b0a3f0b1f071102b3afe5936bb 0 ftp.sra.ebi.ac.uk/vol1/run/ERR916/ERR9169797/11R_merged.realign.MD.uniq.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR916/ERR9169797/11R_merged.realign.MD.uniq.bam.bai +2417Q_TOL_b minus ds n/a SAMEA13300895 PRJEB51440 ERR9169798 2417Q_TOL_b ERS10903712 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA Whole-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR916/008/ERR9169798/ERR9169798.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR916/008/ERR9169798/ERR9169798.fastq.gz 5419036235 73397ed3955ae656a93d2200b1ee3d32 0 ftp.sra.ebi.ac.uk/vol1/run/ERR916/ERR9169798/2417Q.RG.uniq.nodups.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR916/ERR9169798/2417Q.RG.uniq.nodups.realign.MD.bam.bai +2417J_TOL_a minus ds n/a SAMEA13300903 PRJEB51440 ERR9169799 2417J_TOL_a ERS10903720 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA Whole-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR916/009/ERR9169799/ERR9169799.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR916/009/ERR9169799/ERR9169799.fastq.gz 1931820828 c5b1f9df3cdecec749a3efc6da1024de 0 ftp.sra.ebi.ac.uk/vol1/run/ERR916/ERR9169799/2417J.merged.uniq.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR916/ERR9169799/2417J.merged.uniq.realign.MD.bam.bai +E7_CdV_b minus ds n/a SAMEA13300914 PRJEB51440 ERR9576891 E7_CdV_b ERS10903731 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA Whole-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/001/ERR9576891/ERR9576891.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/001/ERR9576891/ERR9576891.fastq.gz 170863156 5999ee334ac8fac5cd30e01618038f35 4776517 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576891/E7CdV.merged.uniq.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576891/E7CdV.merged.uniq.realign.MD.bam.bai +E8_CdV_b minus ds n/a SAMEA13300915 PRJEB51440 ERR9576892 E8_CdV_b ERS10903732 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA Whole-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/002/ERR9576892/ERR9576892.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/002/ERR9576892/ERR9576892.fastq.gz 803265081 1d7f4bc3bad77f3ef0b6f3a0bca87b2b 18044845 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576892/E8CdV.merged.uniq.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576892/E8CdV.merged.uniq.realign.MD.bam.bai +F9_ST_a minus ds n/a SAMEA13300892 PRJEB51440 ERR9576902 F9_ST_a ERS10903709 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/002/ERR9576902/ERR9576902.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/002/ERR9576902/ERR9576902.fastq.gz 6694230 b81f3940eb484f272b3c137b88cd949e 206216 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576902/F9_libs_nocont.sort.rmdup.realign.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576902/F9_libs_nocont.sort.rmdup.realign.rCRS.MD.bam.bai +MOM6_ST_a minus ds n/a SAMEA13300893 PRJEB51440 ERR9576903 MOM6_ST_a ERS10903710 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/003/ERR9576903/ERR9576903.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/003/ERR9576903/ERR9576903.fastq.gz 509644 c64cd4e4e9e2ef48233323d14a25304f 13626 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576903/MOM6_merged_realing.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576903/MOM6_merged_realing.rCRS.MD.bam.bai +2417J_TOL_a minus ds n/a SAMEA13300903 PRJEB51440 ERR9576911 2417J_TOL_a ERS10903720 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/001/ERR9576911/ERR9576911.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/001/ERR9576911/ERR9576911.fastq.gz 912401 b3d8571cc31a2d41a950f556a526c3a6 28230 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576911/2417J.RG.uniq.mt.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576911/2417J.RG.uniq.mt.realign.MD.bam.bai +37AI_R_b minus ds n/a SAMEA13300900 PRJEB51440 ERR9576918 37AI_R_b ERS10903717 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/008/ERR9576918/ERR9576918.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/008/ERR9576918/ERR9576918.fastq.gz 343372 a54a8679d1e51245a190aff21b48677f 10626 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576918/37AI.uniq.mt.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576918/37AI.uniq.mt.realign.MD.bam.bai +7A_R_b minus ds n/a SAMEA13300899 PRJEB51440 ERR9576920 7A_R_b ERS10903716 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/000/ERR9576920/ERR9576920.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/000/ERR9576920/ERR9576920.fastq.gz 244521 3839c9d78ceccb0f8a2d4472f051ffe1 7216 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576920/7A_merged.realign.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576920/7A_merged.realign.rCRS.MD.bam.bai +E19_CdV_b minus ds n/a SAMEA13300919 PRJEB51440 ERR9576930 E19_CdV_b ERS10903735 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/000/ERR9576930/ERR9576930.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/000/ERR9576930/ERR9576930.fastq.gz 717180 3380fcf8a5e478b68225b83e199bd7c8 30066 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576930/E19CdV.merged.uniq.realign.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576930/E19CdV.merged.uniq.realign.rCRS.MD.bam.bai +E2_Mich_b minus ds n/a SAMEA13300908 PRJEB51440 ERR9576946 E2_Mich_b ERS10903725 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/006/ERR9576946/ERR9576946.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/006/ERR9576946/ERR9576946.fastq.gz 891185 3127ddbe0315873fe661b101594338ed 28155 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576946/E2_Mich_merged.realign.MD.uniq.pmd0.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576946/E2_Mich_merged.realign.MD.uniq.pmd0.rCRS.MD.bam.bai +E4_Mich_b minus ds n/a SAMEA13300909 PRJEB51440 ERR9576947 E4_Mich_b ERS10903726 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/007/ERR9576947/ERR9576947.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/007/ERR9576947/ERR9576947.fastq.gz 953436 05132d1bb2dd71a1e2507127dc4899a8 27362 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576947/E4_Mich_merged.realign.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576947/E4_Mich_merged.realign.rCRS.MD.bam.bai +F9_ST_a minus ds n/a SAMEA13300892 PRJEB51440 ERR9128941 F9_ST_a ERS10903709 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA Whole-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR912/001/ERR9128941/ERR9128941.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR912/001/ERR9128941/ERR9128941.fastq.gz 2217480135 4daee34b5f82e00129c2c546d40d35cf 0 ftp.sra.ebi.ac.uk/vol1/run/ERR912/ERR9128941/F9_libs_nocont.sort.rmdup.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR912/ERR9128941/F9_libs_nocont.sort.rmdup.realign.MD.bam.bai +333B_TOL_a minus ds n/a SAMEA13300905 PRJEB51440 ERR9169800 333B_TOL_a ERS10903722 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA Whole-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR916/000/ERR9169800/ERR9169800.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR916/000/ERR9169800/ERR9169800.fastq.gz 3140499340 9b2e37eb52f4e1abf73785b10fc5de33 0 ftp.sra.ebi.ac.uk/vol1/run/ERR916/ERR9169800/333B_merged.realign.MD.uniq.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR916/ERR9169800/333B_merged.realign.MD.uniq.bam.bai +E4_Mich_b minus ds n/a SAMEA13300909 PRJEB51440 ERR9576880 E4_Mich_b ERS10903726 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA Whole-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/000/ERR9576880/ERR9576880.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/000/ERR9576880/ERR9576880.fastq.gz 72636673 b11adc159afe347c3952d7608a3b783c 1323390 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576880/E4_merged.realign.MD.uniq.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576880/E4_merged.realign.MD.uniq.bam.bai +E4_CdV_b minus ds n/a SAMEA13300912 PRJEB51440 ERR9576890 E4_CdV_b ERS10903729 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA Whole-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/000/ERR9576890/ERR9576890.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/000/ERR9576890/ERR9576890.fastq.gz 39490934 1406d3f8aed4c841e6c1a11a672d60ac 1119802 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576890/E4CdV.merged.uniq.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576890/E4CdV.merged.uniq.realign.MD.bam.bai +E19_CdV_b minus ds n/a SAMEA13300919 PRJEB51440 ERR9576893 E19_CdV_b ERS10903735 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA Whole-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/003/ERR9576893/ERR9576893.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/003/ERR9576893/ERR9576893.fastq.gz 190588676 ca719b290567248b06e7cf08a834ac4e 4987519 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576893/E19CdV.merged.uniq.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576893/E19CdV.merged.uniq.realign.MD.bam.bai +2417Q_TOL_b minus ds n/a SAMEA13300895 PRJEB51440 ERR9576912 2417Q_TOL_b ERS10903712 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/002/ERR9576912/ERR9576912.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/002/ERR9576912/ERR9576912.fastq.gz 961922 84593ea7638a0ae222228db114c4e299 33166 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576912/2417Q.RG.uniq.mt.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576912/2417Q.RG.uniq.mt.realign.MD.bam.bai +333A_TOL_a minus ds n/a SAMEA13300904 PRJEB51440 ERR9576913 333A_TOL_a ERS10903721 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/003/ERR9576913/ERR9576913.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/003/ERR9576913/ERR9576913.fastq.gz 51230 0772647552436b6c9456c02761e0e1b9 1344 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576913/333A.uniq.mt.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576913/333A.uniq.mt.realign.MD.bam.bai +333B_TOL_a minus ds n/a SAMEA13300905 PRJEB51440 ERR9576914 333B_TOL_a ERS10903722 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/004/ERR9576914/ERR9576914.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/004/ERR9576914/ERR9576914.fastq.gz 2631580 0b3a3a00dd6c7005df952ea424d56c39 72204 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576914/333B_merged.realign.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576914/333B_merged.realign.rCRS.MD.bam.bai +333C_TOL_a minus ds n/a SAMEA13300906 PRJEB51440 ERR9576915 333C_TOL_a ERS10903723 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/005/ERR9576915/ERR9576915.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/005/ERR9576915/ERR9576915.fastq.gz 684961 25908d2ef30af9bbda6679ac21153938 21310 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576915/333C_merged.realign.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576915/333C_merged.realign.rCRS.MD.bam.bai +6428A_TOL_b minus ds n/a SAMEA13300898 PRJEB51440 ERR9576919 6428A_TOL_b ERS10903715 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/009/ERR9576919/ERR9576919.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/009/ERR9576919/ERR9576919.fastq.gz 617816 fb8bf066cd9db27bc3ad4aa740154f8d 16659 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576919/6428A.uniq.mt.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576919/6428A.uniq.mt.realign.MD.bam.bai +E10_CdV_b minus ds n/a SAMEA13300916 PRJEB51440 ERR9576928 E10_CdV_b ERS10903733 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/008/ERR9576928/ERR9576928.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/008/ERR9576928/ERR9576928.fastq.gz 241152 105a00be33324c6731394da5f907f13e 8593 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576928/E10CdV.merged.uniq.realign.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576928/E10CdV.merged.uniq.realign.rCRS.MD.bam.bai +E11_CdV_b minus ds n/a SAMEA13300917 PRJEB51440 ERR9576929 E11_CdV_b ERS10903734 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/009/ERR9576929/ERR9576929.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/009/ERR9576929/ERR9576929.fastq.gz 31599 585c7728c9a935a78f8cfed146fa6f66 1110 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576929/E11CdV.merged.uniq.realign.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576929/E11CdV.merged.uniq.realign.rCRS.MD.bam.bai +E4_CdV_b minus ds n/a SAMEA13300912 PRJEB51440 ERR9576931 E4_CdV_b ERS10903729 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/001/ERR9576931/ERR9576931.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/001/ERR9576931/ERR9576931.fastq.gz 55840 67bfb19edfd765749b2852449c325ef8 1523 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576931/E4CdV.merged.uniq.realign.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576931/E4CdV.merged.uniq.realign.rCRS.MD.bam.bai +E6_CdV_b minus ds n/a SAMEA13300913 PRJEB51440 ERR9576932 E6_CdV_b ERS10903730 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/002/ERR9576932/ERR9576932.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/002/ERR9576932/ERR9576932.fastq.gz 20264 cfd7577573279e34c97af56d1235fce6 632 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576932/E6CdV.merged.uniq.realign.rCRS.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576932/E6CdV.merged.uniq.realign.rCRS.MD.bam.bai +M1_Mich minus ds n/a SAMEA13300910 PRJEB51440 ERR9576948 M1_Mich ERS10903727 2022-07-23 2022-07-23 NextSeq 550 SINGLE GENOMIC ILLUMINA mtDNA-genome WGS ftp.sra.ebi.ac.uk/vol1/fastq/ERR957/008/ERR9576948/ERR9576948.fastq.gz fasp.sra.ebi.ac.uk:/vol1/fastq/ERR957/008/ERR9576948/ERR9576948.fastq.gz 217648 72e169d3eb8cc460980c6554cad3896c 8151 ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576948/M1_Mich.uniq.mt.realign.MD.bam;ftp.sra.ebi.ac.uk/vol1/run/ERR957/ERR9576948/M1_Mich.uniq.mt.realign.MD.bam.bai diff --git a/packages/2023_VillaIslas_Science/2023_VillaIslas_Science.tsv b/packages/2023_VillaIslas_Science/2023_VillaIslas_Science.tsv new file mode 100644 index 0000000..0d7c5ae --- /dev/null +++ b/packages/2023_VillaIslas_Science/2023_VillaIslas_Science.tsv @@ -0,0 +1,40 @@ +Sample_Name Library_ID Lane Colour_Chemistry SeqType Organism Strandedness UDG_Treatment R1 R2 BAM R1_target_file R2_target_file +E2_Mich_b E2_Mich_b_Whole-genome 1 4 SE Homo sapiens (modern human) double none /E2_Mich_b_Whole-genome_L1_R1.fastq.gz NA NA ERR9576879.fastq.gz NA +11R_R_b 11R_R_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /11R_R_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576909.fastq.gz NA +2417C_TOL_a 2417C_TOL_a_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /2417C_TOL_a_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576910.fastq.gz NA +333O_TOL_b 333O_TOL_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /333O_TOL_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576916.fastq.gz NA +333Q_TOL_b 333Q_TOL_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /333Q_TOL_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576917.fastq.gz NA +P_CCM_b P_CCM_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /P_CCM_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576921.fastq.gz NA +E7_CdV_b E7_CdV_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /E7_CdV_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576933.fastq.gz NA +E8_CdV_b E8_CdV_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /E8_CdV_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576934.fastq.gz NA +E1A_Mich_b E1A_Mich_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /E1A_Mich_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576945.fastq.gz NA +M2_Mich_b M2_Mich_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /M2_Mich_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576949.fastq.gz NA +MOM6_ST_a MOM6_ST_a_Whole-genome 1 4 SE Homo sapiens (modern human) double none /MOM6_ST_a_Whole-genome_L1_R1.fastq.gz NA NA ERR9128942.fastq.gz NA +11R_R_b 11R_R_b_Whole-genome 1 4 SE Homo sapiens (modern human) double none /11R_R_b_Whole-genome_L1_R1.fastq.gz NA NA ERR9169797.fastq.gz NA +2417Q_TOL_b 2417Q_TOL_b_Whole-genome 1 4 SE Homo sapiens (modern human) double none /2417Q_TOL_b_Whole-genome_L1_R1.fastq.gz NA NA ERR9169798.fastq.gz NA +2417J_TOL_a 2417J_TOL_a_Whole-genome 1 4 SE Homo sapiens (modern human) double none /2417J_TOL_a_Whole-genome_L1_R1.fastq.gz NA NA ERR9169799.fastq.gz NA +E7_CdV_b E7_CdV_b_Whole-genome 1 4 SE Homo sapiens (modern human) double none /E7_CdV_b_Whole-genome_L1_R1.fastq.gz NA NA ERR9576891.fastq.gz NA +E8_CdV_b E8_CdV_b_Whole-genome 1 4 SE Homo sapiens (modern human) double none /E8_CdV_b_Whole-genome_L1_R1.fastq.gz NA NA ERR9576892.fastq.gz NA +F9_ST_a F9_ST_a_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /F9_ST_a_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576902.fastq.gz NA +MOM6_ST_a MOM6_ST_a_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /MOM6_ST_a_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576903.fastq.gz NA +2417J_TOL_a 2417J_TOL_a_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /2417J_TOL_a_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576911.fastq.gz NA +37AI_R_b 37AI_R_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /37AI_R_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576918.fastq.gz NA +7A_R_b 7A_R_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /7A_R_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576920.fastq.gz NA +E19_CdV_b E19_CdV_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /E19_CdV_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576930.fastq.gz NA +E2_Mich_b E2_Mich_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /E2_Mich_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576946.fastq.gz NA +E4_Mich_b E4_Mich_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /E4_Mich_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576947.fastq.gz NA +F9_ST_a F9_ST_a_Whole-genome 1 4 SE Homo sapiens (modern human) double none /F9_ST_a_Whole-genome_L1_R1.fastq.gz NA NA ERR9128941.fastq.gz NA +333B_TOL_a 333B_TOL_a_Whole-genome 1 4 SE Homo sapiens (modern human) double none /333B_TOL_a_Whole-genome_L1_R1.fastq.gz NA NA ERR9169800.fastq.gz NA +E4_Mich_b E4_Mich_b_Whole-genome 1 4 SE Homo sapiens (modern human) double none /E4_Mich_b_Whole-genome_L1_R1.fastq.gz NA NA ERR9576880.fastq.gz NA +E4_CdV_b E4_CdV_b_Whole-genome 1 4 SE Homo sapiens (modern human) double none /E4_CdV_b_Whole-genome_L1_R1.fastq.gz NA NA ERR9576890.fastq.gz NA +E19_CdV_b E19_CdV_b_Whole-genome 1 4 SE Homo sapiens (modern human) double none /E19_CdV_b_Whole-genome_L1_R1.fastq.gz NA NA ERR9576893.fastq.gz NA +2417Q_TOL_b 2417Q_TOL_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /2417Q_TOL_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576912.fastq.gz NA +333A_TOL_a 333A_TOL_a_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /333A_TOL_a_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576913.fastq.gz NA +333B_TOL_a 333B_TOL_a_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /333B_TOL_a_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576914.fastq.gz NA +333C_TOL_a 333C_TOL_a_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /333C_TOL_a_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576915.fastq.gz NA +6428A_TOL_b 6428A_TOL_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /6428A_TOL_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576919.fastq.gz NA +E10_CdV_b E10_CdV_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /E10_CdV_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576928.fastq.gz NA +E11_CdV_b E11_CdV_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /E11_CdV_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576929.fastq.gz NA +E4_CdV_b E4_CdV_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /E4_CdV_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576931.fastq.gz NA +E6_CdV_b E6_CdV_b_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /E6_CdV_b_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576932.fastq.gz NA +M1_Mich M1_Mich_mtDNA-genome 1 4 SE Homo sapiens (modern human) double none /M1_Mich_mtDNA-genome_L1_R1.fastq.gz NA NA ERR9576948.fastq.gz NA diff --git a/packages/2023_VillaIslas_Science/2023_VillaIslas_Science.tsv_patch.sh b/packages/2023_VillaIslas_Science/2023_VillaIslas_Science.tsv_patch.sh new file mode 100755 index 0000000..a73f9af --- /dev/null +++ b/packages/2023_VillaIslas_Science/2023_VillaIslas_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="$(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} > ${output_tsv} +sed -i -e "s||${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/2023_VillaIslas_Science/script_versions.txt b/packages/2023_VillaIslas_Science/script_versions.txt new file mode 100644 index 0000000..be6857b --- /dev/null +++ b/packages/2023_VillaIslas_Science/script_versions.txt @@ -0,0 +1,2 @@ +create_eager_input.sh: 0.2.1dev +source_me.sh for initial TSV: 0.2.1dev