Add 2021_Carlhoff_Nature package

2021_CarlhoffNature/2021_CarlhoffNature.bib

@@ -0,0 +1,22 @@
+@article{CarlhoffNature2021,
+  title     = "Genome of a middle Holocene hunter-gatherer from Wallacea",
+  author    = "Carlhoff, Selina and Duli, Akin and N{\"a}gele, Kathrin and Nur,
+               Muhammad and Skov, Laurits and Sumantri, Iwan and Oktaviana,
+               Adhi Agus and Hakim, Budianto and Burhan, Basran and Syahdar,
+               Fardi Ali and McGahan, David P and Bulbeck, David and Perston,
+               Yinika L and Newman, Kim and Saiful, Andi Muhammad and
+               Ririmasse, Marlon and Chia, Stephen and {Hasanuddin} and
+               Pulubuhu, Dwia Aries Tina and {Suryatman} and {Supriadi} and
+               Jeong, Choongwon and Peter, Benjamin M and Pr{\"u}fer, Kay and
+               Powell, Adam and Krause, Johannes and Posth, Cosimo and Brumm,
+               Adam",
+  journal   = "Nature",
+  publisher = "Springer Science and Business Media LLC",
+  volume    =  596,
+  number    =  7873,
+  pages     = "543--547",
+  month     =  aug,
+  year      =  2021,
+  copyright = "https://creativecommons.org/licenses/by/4.0",
+  language  = "en"
+}

2021_CarlhoffNature/2021_CarlhoffNature.fam

@@ -0,0 +1,2 @@
+Leang_Panninge	GUP001_MNT	0	0	2	0
+Leang_Panninge	GUP001_ss_MNT	0	0	2	0

2021_CarlhoffNature/2021_CarlhoffNature.janno

@@ -0,0 +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
+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

2021_CarlhoffNature/2021_CarlhoffNature.ssf

@@ -0,0 +1,11 @@
+sample_accession	study_accession	run_accession	sample_alias	poseidon_IDs	udg	library_built	secondary_sample_accession	first_public	last_updated	instrument_model	library_layout	library_source	instrument_platform	library_name	library_strategy	fastq_aspera	fastq_bytes	fastq_md5	fastq_ftp	read_count	submitted_ftp
+SAMEA8270508	PRJEB43715	ERR5490520	GUP001	GUP001_MNT	half	ds	ERS5956814	2021-06-18	2021-06-18	Illumina HiSeq 4000	SINGLE	METAGENOMIC	ILLUMINA	GUP001.A0101	Targeted-Capture	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR549/000/ERR5490520/ERR5490520.fastq.gz	31485654	842ec55a3a0aff4979dea1b5dc529e7c	ftp.sra.ebi.ac.uk/vol1/fastq/ERR549/000/ERR5490520/ERR5490520.fastq.gz	945210	ftp.sra.ebi.ac.uk/vol1/run/ERR549/ERR5490520/GUP001.A0101.MT1.1.fastq.truncated.gz
+SAMEA8270508	PRJEB43715	ERR5490521	GUP001	GUP001_MNT	half	ds	ERS5956814	2021-06-18	2021-06-18	Illumina HiSeq 4000	SINGLE	METAGENOMIC	ILLUMINA	GUP001.A0101	Targeted-Capture	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR549/001/ERR5490521/ERR5490521.fastq.gz	32643939	e4c9ae3aed81094a383c2c2003dd961f	ftp.sra.ebi.ac.uk/vol1/fastq/ERR549/001/ERR5490521/ERR5490521.fastq.gz	1040533	ftp.sra.ebi.ac.uk/vol1/run/ERR549/ERR5490521/GUP001.A0101.MT1.2.fastq.truncated.gz
+SAMEA8270508	PRJEB43715	ERR5490522	GUP001	GUP001_MNT	half	ds	ERS5956814	2021-06-18	2021-06-18	Illumina HiSeq 4000	SINGLE	METAGENOMIC	ILLUMINA	GUP001.A0101	Targeted-Capture	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR549/002/ERR5490522/ERR5490522.fastq.gz	192243801	a4add9bc886418c913420eab0391297e	ftp.sra.ebi.ac.uk/vol1/fastq/ERR549/002/ERR5490522/ERR5490522.fastq.gz	6189559	ftp.sra.ebi.ac.uk/vol1/run/ERR549/ERR5490522/GUP001.A0101.MT1.3.fastq.truncated.gz
+SAMEA8270508	PRJEB43715	ERR5490523	GUP001	GUP001_MNT	half	ds	ERS5956814	2021-06-18	2021-06-18	Illumina HiSeq 4000	SINGLE	METAGENOMIC	ILLUMINA	GUP001.A0101	WGS	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR549/003/ERR5490523/ERR5490523.fastq.gz	95526960	29a36d22db98919f96d32af631a9422c	ftp.sra.ebi.ac.uk/vol1/fastq/ERR549/003/ERR5490523/ERR5490523.fastq.gz	2888875	ftp.sra.ebi.ac.uk/vol1/run/ERR549/ERR5490523/GUP001.A0101.SG1.1.fastq.truncated.gz
+SAMEA8270508	PRJEB43715	ERR5490524	GUP001	GUP001_MNT	half	ds	ERS5956814	2021-06-18	2021-06-18	Illumina HiSeq 4000	SINGLE	METAGENOMIC	ILLUMINA	GUP001.A0101	Targeted-Capture	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR549/004/ERR5490524/ERR5490524.fastq.gz	562634908	ee58126a3880e12ac25ff3c1adf97aec	ftp.sra.ebi.ac.uk/vol1/fastq/ERR549/004/ERR5490524/ERR5490524.fastq.gz	17847250	ftp.sra.ebi.ac.uk/vol1/run/ERR549/ERR5490524/GUP001.A0101.TF1.1.fastq.truncated.gz
+SAMEA8270508	PRJEB43715	ERR5490525	GUP001	GUP001_MNT	half	ds	ERS5956814	2021-06-18	2021-06-18	Illumina HiSeq 4000	SINGLE	METAGENOMIC	ILLUMINA	GUP001.A0101	Targeted-Capture	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR549/005/ERR5490525/ERR5490525.fastq.gz	1541567827	640a45bc4956b647f5578a66763813d0	ftp.sra.ebi.ac.uk/vol1/fastq/ERR549/005/ERR5490525/ERR5490525.fastq.gz	50108944	ftp.sra.ebi.ac.uk/vol1/run/ERR549/ERR5490525/GUP001.A0101.TF1.2.fastq.truncated.gz
+SAMEA8270508	PRJEB43715	ERR5490526	GUP001	GUP001_MNT	half	ds	ERS5956814	2021-06-18	2021-06-18	Illumina HiSeq 4000	SINGLE	METAGENOMIC	ILLUMINA	GUP001.A0101	Targeted-Capture	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR549/006/ERR5490526/ERR5490526.fastq.gz	674880719	e58345ddc808d879d255f8d68065050d	ftp.sra.ebi.ac.uk/vol1/fastq/ERR549/006/ERR5490526/ERR5490526.fastq.gz	23288459	ftp.sra.ebi.ac.uk/vol1/run/ERR549/ERR5490526/GUP001.A0101.TF1.3.fastq.truncated.gz
+SAMEA8270508	PRJEB43715	ERR5490527	GUP001	GUP001_ss_MNT	minus	ss	ERS5956814	2021-06-18	2021-06-18	Illumina HiSeq 4000	SINGLE	METAGENOMIC	ILLUMINA	GUP001.A0102	Targeted-Capture	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR549/007/ERR5490527/ERR5490527.fastq.gz	656969967	d16a8f18feef912878f0b56218581717	ftp.sra.ebi.ac.uk/vol1/fastq/ERR549/007/ERR5490527/ERR5490527.fastq.gz	21959304	ftp.sra.ebi.ac.uk/vol1/run/ERR549/ERR5490527/GUP001.A0102.AA1.1.fastq.truncated.gz
+SAMEA8270508	PRJEB43715	ERR5490528	GUP001	GUP001_ss_MNT	minus	ss	ERS5956814	2021-06-18	2021-06-18	Illumina HiSeq 4000	SINGLE	METAGENOMIC	ILLUMINA	GUP001.A0102	WGS	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR549/008/ERR5490528/ERR5490528.fastq.gz	145599926	e2be513bf56c01591ecdb7dfbe55c5cb	ftp.sra.ebi.ac.uk/vol1/fastq/ERR549/008/ERR5490528/ERR5490528.fastq.gz	5086983	ftp.sra.ebi.ac.uk/vol1/run/ERR549/ERR5490528/GUP001.A0102.SG1.1.fastq.truncated.gz
+SAMEA8270508	PRJEB43715	ERR5490529	GUP001	GUP001_ss_MNT	minus	ss	ERS5956814	2021-06-18	2021-06-18	Illumina HiSeq 4000	SINGLE	METAGENOMIC	ILLUMINA	GUP001.A0102	Targeted-Capture	fasp.sra.ebi.ac.uk:/vol1/fastq/ERR549/009/ERR5490529/ERR5490529.fastq.gz	674885210	189d55160fdfec278ddc8fba5296ad18	ftp.sra.ebi.ac.uk/vol1/fastq/ERR549/009/ERR5490529/ERR5490529.fastq.gz	23288459	ftp.sra.ebi.ac.uk/vol1/run/ERR549/ERR5490529/GUP001.A0102.TF1.1.fastq.truncated.gz

2021_CarlhoffNature/CHANGELOG.md

@@ -0,0 +1,6 @@
+- V 0.1.6: Add contributor and description
+- V 0.1.5: Remove abstract from .bib file
+- V 0.1.4: Add Country_ISO info
+- V 0.1.3: Fill-in metadata from community-archive: 2021_CarlhoffNature-2.2.0
+- V 0.1.2: Add bibtex. Update Genetic_Sex. Add identical individual to Relation_* columns.
+- V 0.1.1: Automatic update of janno file from Minotaur processing.

2021_CarlhoffNature/POSEIDON.yml

@@ -0,0 +1,26 @@
+poseidonVersion: 2.7.1
+title: 2021_CarlhoffNature
+description: Genome of a Middle Holocene hunter-gatherer from Wallacea
+contributor:
+- name: Thiseas C. Lamnidis
+  email: [email protected]
+  orcid: 0000-0003-4485-8570
+packageVersion: 0.1.6
+lastModified: 2024-04-04
+genotypeData:
+  format: PLINK
+  genoFile: 2021_CarlhoffNature.bed
+  genoFileChkSum: 079d15ad25a6db3f7e3d1da9e105abc3
+  snpFile: 2021_CarlhoffNature.bim
+  snpFileChkSum: 433fa85a23f3123bade02348e4628b75
+  indFile: 2021_CarlhoffNature.fam
+  indFileChkSum: d5982f4cd410501dd26c0b2f2b95a83b
+  snpSet: 1240K
+jannoFile: 2021_CarlhoffNature.janno
+jannoFileChkSum: 9b1fc8f11211767fbb5868128327a6cd
+sequencingSourceFile: 2021_CarlhoffNature.ssf
+sequencingSourceFileChkSum: ac4cec11100b5ab343548313c86c68b2
+bibFile: 2021_CarlhoffNature.bib
+bibFileChkSum: 6a742a8973cab71d1676cef91071395c
+readmeFile: README.md
+changelogFile: CHANGELOG.md

2021_CarlhoffNature/README.md

@@ -0,0 +1,53 @@
+# 2021_CarlhoffNature
+
+This package was created on 2024-04-03 and was processed using the following versions:
+
+- nf-core/eager version: 2.4.6
+- Minotaur config version: 0.2.1dev
+- CaptureType profile: 1240K
+- CaptureType config version: 0.2.2dev
+- Config template version: 0.3.0dev
+- Package config version: 0.3.0dev
+- Minotaur-packager version: 0.3.0dev
+- populate_janno.py version: 0.3.2dev
+
+## Fill relevant columns from the community archive package.
+
+```bash
+## First fill-in missing metadata from relevant columns (no processing-based info).
+trident jannocoalesce \
+  -s ../../archives/community-archive/2021_CarlhoffNature-2.2.0/2021_CarlhoffNature.janno \
+  -t 2021_CarlhoffNature/2021_CarlhoffNature.janno \
+  --stripIdRegex "(_ss_MNT$)|(_MNT$)" \
+  --includeColumns 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,Primary_Contact,Note,Keywords
+
+## Then fill in Group_Name and Genetic_Sex
+trident jannocoalesce \
+  -s ../../archives/community-archive/2021_CarlhoffNature-2.2.0/2021_CarlhoffNature.janno \
+  -t 2021_CarlhoffNature/2021_CarlhoffNature.janno \
+  --stripIdRegex "(_ss_MNT$)|(_MNT$)" \
+  --includeColumns Genetic_Sex,Group_Name \
+  --force
+
+## Mirror Sex and Group name info to the fam file.
+paste -d "\t" 2021_CarlhoffNature/2021_CarlhoffNature.fam <(cut -f 1-3 2021_CarlhoffNature/2021_CarlhoffNature.janno |tail -n +2) | \
+  awk '
+  BEGIN{
+    OFS=IFS="\t"
+  }
+  {
+    $1=$9
+    if ($8 == "M") {
+      $5=1
+    } else if ($8 == "F") {
+      $5=2
+    }
+    print $1,$2,$3,$4,$5,$6
+  }
+  ' > tmp.fam
+  ## Cannot overwrite in the same command that reads in the file, so an extra mv is needed.
+  mv tmp.fam 2021_CarlhoffNature/2021_CarlhoffNature.fam
+
+  ## trident version: 1.4.1.0
+  trident rectify --packageVersion Patch --logText "Fill-in metadata from community-archive: 2021_CarlhoffNature-2.2.0" --checksumAll -d .
+```