From 9278f3e09150194075ba70d6b9e704082b7fc2da Mon Sep 17 00:00:00 2001 From: "Thiseas C. Lamnidis" Date: Wed, 29 May 2024 14:28:21 +0200 Subject: [PATCH 1/3] rename Individual_ID to Main_ID for consistency --- 2021_CarlhoffNature/2021_CarlhoffNature.janno | 2 +- 2021_CarlhoffNature/CHANGELOG.md | 1 + 2021_CarlhoffNature/POSEIDON.yml | 6 +++--- 2021_Saag_EastEuropean/2021_Saag_EastEuropean.janno | 2 +- 2021_Saag_EastEuropean/CHANGELOG.md | 1 + 2021_Saag_EastEuropean/POSEIDON.yml | 6 +++--- 6 files changed, 10 insertions(+), 8 deletions(-) diff --git a/2021_CarlhoffNature/2021_CarlhoffNature.janno b/2021_CarlhoffNature/2021_CarlhoffNature.janno index 901b54d..05dc84e 100644 --- a/2021_CarlhoffNature/2021_CarlhoffNature.janno +++ b/2021_CarlhoffNature/2021_CarlhoffNature.janno @@ -1,3 +1,3 @@ -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 Nr_Libraries Library_Names Capture_Type UDG Library_Built Genotype_Ploidy Data_Preparation_Pipeline_URL Endogenous Nr_SNPs Coverage_on_Target_SNPs Damage Contamination Contamination_Err Contamination_Meas Contamination_Note Genetic_Source_Accession_IDs Primary_Contact Publication Note Keywords Eager_ID Individual_ID RateErrX RateErrY RateX RateY +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 Nr_Libraries Library_Names Capture_Type UDG Library_Built Genotype_Ploidy Data_Preparation_Pipeline_URL Endogenous Nr_SNPs Coverage_on_Target_SNPs Damage Contamination Contamination_Err Contamination_Meas Contamination_Note Genetic_Source_Accession_IDs Primary_Contact Publication Note Keywords Eager_ID Main_ID RateErrX RateErrY RateX RateY GUP001_MNT F Leang_Panninge n/a GUP001_ss_MNT identical same_as n/a 30 B. PANNINGE Skull block region 9 petrous Indonesia ID Southern Sulawesi Leang Panninge -4.7741 119.9396 C14 Wk-48639 6317 19 -5314 -5265 -5215 n/a M n/a bone_petrous 1 GUP001.A0101 1240K;Shotgun half ds haploid https://github.com/nf-core/eager/releases/tag/2.4.6 6.762222 272731 n/a 0.4636218846261551 0.11128 3.536035e-14 ANGSD[v0.935] Nr Snps (per library): 691. Estimate and error are weighted means of values per library. Libraries with fewer than 100 SNPs used in contamination estimation were excluded. PRJEB43715;ERS5956814;ERR5490520;ERR5490521;ERR5490522;ERR5490523;ERR5490524;ERR5490525;ERR5490526 Selina Carlhoff CarlhoffNature2021 C14 dates from charcoal and seeds associated with burial; damage for ds SG; mtcontam for ss with AuthentiCT n/a GUP001 GUP001 0.007582631999185001 0.001447150678242 0.8115348979428191 0.020098725775262002 GUP001_ss_MNT F Leang_Panninge n/a GUP001_MNT identical same_as n/a 30 B. PANNINGE Skull block region 9 petrous Indonesia ID Southern Sulawesi Leang Panninge -4.7741 119.9396 C14 Wk-48639 6317 19 -5314 -5265 -5215 n/a M n/a bone_petrous 1 GUP001.A0102 1240K;Shotgun minus ss haploid https://github.com/nf-core/eager/releases/tag/2.4.6 13.339985 134067 n/a 0.5877457008717157 0.097276 3.860919e-15 ANGSD[v0.935] Nr Snps (per library): 345. Estimate and error are weighted means of values per library. Libraries with fewer than 100 SNPs used in contamination estimation were excluded. PRJEB43715;ERS5956814;ERR5490527;ERR5490528;ERR5490529 Selina Carlhoff CarlhoffNature2021 C14 dates from charcoal and seeds associated with burial; damage for ds SG; mtcontam for ss with AuthentiCT n/a GUP001_ss GUP001 0.008514648295196001 0.0016382538785210002 0.7711635308594431 0.019378750752398 diff --git a/2021_CarlhoffNature/CHANGELOG.md b/2021_CarlhoffNature/CHANGELOG.md index 753a055..95c39fb 100644 --- a/2021_CarlhoffNature/CHANGELOG.md +++ b/2021_CarlhoffNature/CHANGELOG.md @@ -1,3 +1,4 @@ +- V 1.0.1: rename Individual_ID to Main_ID for consistency - V 1.0.0: Bump version for release - V 0.1.7: Update .bib - V 0.1.6: Add contributor and description diff --git a/2021_CarlhoffNature/POSEIDON.yml b/2021_CarlhoffNature/POSEIDON.yml index b019843..983fd71 100644 --- a/2021_CarlhoffNature/POSEIDON.yml +++ b/2021_CarlhoffNature/POSEIDON.yml @@ -5,8 +5,8 @@ contributor: - name: Thiseas C. Lamnidis email: thiseas_christos_lamnidis@eva.mpg.de orcid: 0000-0003-4485-8570 -packageVersion: 1.0.0 -lastModified: 2024-04-08 +packageVersion: 1.0.1 +lastModified: 2024-05-29 genotypeData: format: PLINK genoFile: 2021_CarlhoffNature.bed @@ -17,7 +17,7 @@ genotypeData: indFileChkSum: d5982f4cd410501dd26c0b2f2b95a83b snpSet: 1240K jannoFile: 2021_CarlhoffNature.janno -jannoFileChkSum: 9b1fc8f11211767fbb5868128327a6cd +jannoFileChkSum: 38b75f7f7bee6820b4f0a4b56cea064e sequencingSourceFile: 2021_CarlhoffNature.ssf sequencingSourceFileChkSum: ac4cec11100b5ab343548313c86c68b2 bibFile: 2021_CarlhoffNature.bib diff --git a/2021_Saag_EastEuropean/2021_Saag_EastEuropean.janno b/2021_Saag_EastEuropean/2021_Saag_EastEuropean.janno index 637c0b6..c41d077 100644 --- a/2021_Saag_EastEuropean/2021_Saag_EastEuropean.janno +++ b/2021_Saag_EastEuropean/2021_Saag_EastEuropean.janno @@ -1,4 +1,4 @@ -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 Nr_Libraries Library_Names Capture_Type UDG Library_Built Genotype_Ploidy Data_Preparation_Pipeline_URL Endogenous Nr_SNPs Coverage_on_Target_SNPs Damage Contamination Contamination_Err Contamination_Meas Contamination_Note Genetic_Source_Accession_IDs Primary_Contact Publication Note Keywords Eager_ID Individual_ID RateErrX RateErrY RateX RateY +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 Nr_Libraries Library_Names Capture_Type UDG Library_Built Genotype_Ploidy Data_Preparation_Pipeline_URL Endogenous Nr_SNPs Coverage_on_Target_SNPs Damage Contamination Contamination_Err Contamination_Meas Contamination_Note Genetic_Source_Accession_IDs Primary_Contact Publication Note Keywords Eager_ID Main_ID RateErrX RateErrY RateX RateY HAN003_MNT U Fatyanovo n/a n/a n/a n/a n/a n/a Russian Federation RU Moscow Khanevo 55.63639 35.89972 n/a n/a n/a n/a n/a n/a n/a n/a n/a n/a tooth 1 unspecified Shotgun minus ds haploid https://github.com/nf-core/eager/releases/tag/2.4.6 99.10002 896 n/a 0.17801590044936053 n/a n/a n/a Nr Snps (per library): 0. Estimate and error are weighted means of values per library. Libraries with fewer than 100 SNPs used in contamination estimation were excluded. PRJEB40698;ERS5500809;ERR5032514 n/a SaagScienceAdvances2021 n/a n/a HAN003 HAN003 0.11039409610091401 0.13464525869124802 0.45079846344425406 0.44378068581963204 TIM001_MNT M Fatyanovo n/a n/a n/a n/a n/a n/a Russian Federation RU Ivanovo Timofeyevka 57.13447 39.97571 n/a n/a n/a n/a n/a n/a n/a n/a K1b1a1+199 R1a tooth 1 unspecified Shotgun minus ds haploid https://github.com/nf-core/eager/releases/tag/2.4.6 99.571303 16564 n/a 9.598967562986363e-2 n/a n/a n/a Nr Snps (per library): 0. Estimate and error are weighted means of values per library. Libraries with fewer than 100 SNPs used in contamination estimation were excluded. PRJEB40698;ERS5500830;ERR5032535 n/a SaagScienceAdvances2021 n/a n/a TIM001 TIM001 0.025895105282729 0.028701492605426003 0.46082793745530903 0.375512663170518 TIM011_MNT F Fatyanovo n/a n/a n/a n/a n/a n/a Russian Federation RU Ivanovo Timofeyevka 57.13447 39.97571 n/a n/a n/a n/a n/a n/a n/a n/a U5b2a1a+16311 n/a tooth 1 unspecified Shotgun minus ds haploid https://github.com/nf-core/eager/releases/tag/2.4.6 99.647917 5462 n/a 0.10822709163346614 n/a n/a n/a Nr Snps (per library): 1. Estimate and error are weighted means of values per library. Libraries with fewer than 100 SNPs used in contamination estimation were excluded. PRJEB40698;ERS5500838;ERR5032543 n/a SaagScienceAdvances2021 n/a n/a TIM011 TIM011 0.061573573867055004 0.009419188399547 0.836002448923796 0.013318226120096002 diff --git a/2021_Saag_EastEuropean/CHANGELOG.md b/2021_Saag_EastEuropean/CHANGELOG.md index 91c2c45..592d19c 100644 --- a/2021_Saag_EastEuropean/CHANGELOG.md +++ b/2021_Saag_EastEuropean/CHANGELOG.md @@ -1,3 +1,4 @@ +- V 1.0.1: rename Individual_ID to Main_ID for consistency - V 1.0.0: Bump version for release - V 0.1.4: Add Country_ISO information - V 0.1.3: Fill-in metadata from community-archive: 2021_Saag_EastEuropean-3.2.0 diff --git a/2021_Saag_EastEuropean/POSEIDON.yml b/2021_Saag_EastEuropean/POSEIDON.yml index 4911ede..8a026e9 100644 --- a/2021_Saag_EastEuropean/POSEIDON.yml +++ b/2021_Saag_EastEuropean/POSEIDON.yml @@ -6,8 +6,8 @@ contributor: - name: Thiseas C. Lamnidis email: thiseas_christos_lamnidis@eva.mpg.de orcid: 0000-0003-4485-8570 -packageVersion: 1.0.0 -lastModified: 2024-04-08 +packageVersion: 1.0.1 +lastModified: 2024-05-29 genotypeData: format: PLINK genoFile: 2021_Saag_EastEuropean.bed @@ -18,7 +18,7 @@ genotypeData: indFileChkSum: 319d167cf360277e6a0d0c2ebdfa4ccc snpSet: 1240K jannoFile: 2021_Saag_EastEuropean.janno -jannoFileChkSum: b2903911f5ad62108d738d84e006b256 +jannoFileChkSum: 28056a3463bb1d7899b1afa88929ca14 sequencingSourceFile: 2021_Saag_EastEuropean.ssf sequencingSourceFileChkSum: ede192f2a129e62c78ea8f48c17b50c8 bibFile: 2021_Saag_EastEuropean.bib From 533dbec4f9b62926dc7b57adc28799d05053b3ad Mon Sep 17 00:00:00 2001 From: TCLamnidis Date: Wed, 29 May 2024 15:21:18 +0000 Subject: [PATCH 2/3] Update of chronicle file --- archive.chron | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/archive.chron b/archive.chron index a1ea146..c4aded4 100644 --- a/archive.chron +++ b/archive.chron @@ -1,6 +1,6 @@ title: Poseidon minotaur-archive chronicle -chronicleVersion: 1.3.0 -lastModified: 2024-04-30 +chronicleVersion: 1.4.0 +lastModified: 2024-05-29 packages: - title: 2020_Margaryan_Viking version: 1.0.0 @@ -10,10 +10,18 @@ packages: version: 1.0.0 commit: fa09bafe346791c1cba137b8afc905f9fdbb6a17 path: 2021_CarlhoffNature +- title: 2021_CarlhoffNature + version: 1.0.1 + commit: 7b598465b8637841f554b84cd1fc43af84a329b1 + path: 2021_CarlhoffNature - title: 2021_Saag_EastEuropean version: 1.0.0 commit: fa09bafe346791c1cba137b8afc905f9fdbb6a17 path: 2021_Saag_EastEuropean +- title: 2021_Saag_EastEuropean + version: 1.0.1 + commit: 7b598465b8637841f554b84cd1fc43af84a329b1 + path: 2021_Saag_EastEuropean - title: 2023_OlaldeCarrion_Roman version: 1.0.0 commit: 3a8c6d97bf581e45b183671ac0171b37045ed805 From b5bb1acb3290a1598116453b3b1bba162697de21 Mon Sep 17 00:00:00 2001 From: Clemens Schmid Date: Mon, 10 Jun 2024 11:07:41 +0200 Subject: [PATCH 3/3] added the quotes check also here, @TCLamnidis --- .github/workflows/validation.yml | 8 ++++++-- checkQuotes.sh | 28 ++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+), 2 deletions(-) create mode 100755 checkQuotes.sh diff --git a/.github/workflows/validation.yml b/.github/workflows/validation.yml index 7e3e9b8..fb375dd 100644 --- a/.github/workflows/validation.yml +++ b/.github/workflows/validation.yml @@ -11,12 +11,12 @@ jobs: name: validate packages runs-on: ubuntu-latest steps: - + - name: Install trident run: | wget https://github.com/poseidon-framework/poseidon-hs/releases/latest/download/trident-Linux chmod +x trident-Linux - + - name: Clone data repo uses: actions/checkout@v3 with: @@ -36,3 +36,7 @@ jobs: - name: Check if all files have UTF-8 encoding and Unix line endings run: ./checkFileEncoding.sh working-directory: ./data + + - name: Check if any .janno and .ssf files start with a single or double-quote character + run: ./checkQuotes.sh + working-directory: ./data diff --git a/checkQuotes.sh b/checkQuotes.sh new file mode 100755 index 0000000..f420d60 --- /dev/null +++ b/checkQuotes.sh @@ -0,0 +1,28 @@ +#!/bin/bash + +# function to check if a file starts with a double-quote +starts_with_quote() { + if grep -q ^[\"\'] "${1}"; then + return 0 + else + return 1 + fi +} + +# file extensions to search for +extensions=("janno" "ssf") + +# initialize exit code +exit_code=0 + +# recursive search for files and check them +for ext in "${extensions[@]}"; do + while IFS= read -r -d '' file; do + if starts_with_quote "${file}"; then + echo "FAIL: ${file}" + exit_code=1 + fi + done < <(find . -type f -name "*.${ext}" -not -path "./.git*" -print0) +done + +exit ${exit_code}