{"data":[{"id":"10.5061/dryad.z612jm6pj","type":"dois","attributes":{"doi":"10.5061/dryad.z612jm6pj","identifiers":[],"creators":[{"nameType":"Personal","affiliation":["University of Colorado Boulder"],"name":"Villanea, Fernando","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-6661-0368"}]},{"nameType":"Personal","affiliation":["Brown University"],"name":"Peede, David","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-4826-0464"}]},{"nameType":"Personal","affiliation":["University of Washington"],"name":"Kaufman, Eli","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0001-8553-210X"}]},{"nameType":"Personal","affiliation":["Brown University"],"name":"Añorve-Garibay, Valeria","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0009-0009-4238-902X"}]},{"nameType":"Personal","affiliation":["Brown University"],"name":"Chevy, Elizabeth","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0003-2279-6129"}]},{"nameType":"Personal","affiliation":["University of Copenhagen"],"name":"Villa-Islas, Viridiana","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0001-9218-561X"}]},{"nameType":"Personal","affiliation":["Clemson University"],"name":"Witt, Kelsey","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-3242-2123"}]},{"nameType":"Personal","affiliation":["University of Padova"],"name":"Zeloni, Roberta","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["University of Turin"],"name":"Marnetto, Davide","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0001-9573-0601"}]},{"nameType":"Personal","affiliation":["University of California, Berkeley"],"name":"Moorjani, Priya","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-0947-5673"}]},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Jay, Flora","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0001-5884-4730"}]},{"nameType":"Personal","affiliation":["University of Washington"],"name":"Valdmanis, Paul","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["Universidad Nacional Autónoma de México"],"name":"Ávila-Arcos, María","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0003-1691-1696"}]},{"nameType":"Personal","affiliation":["Brown University"],"name":"Huerta-Sánchez, Emilia","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-1506-5494"}]}],"titles":[{"title":"The MUC19 Gene: An Evolutionary History of Recurrent Introgression and Natural Selection"}],"publisher":"Dryad","container":{},"publicationYear":2025,"subjects":[{"schemeUri":"https://web-archive.oecd.org/2012-06-15/138575-38235147.pdf","subject":"FOS: Biological sciences","subjectScheme":"fos"},{"schemeUri":"https://github.com/PLOS/plos-thesaurus","subject":"Introgression","subjectScheme":"PLOS Subject Area Thesaurus"},{"schemeUri":"https://github.com/PLOS/plos-thesaurus","subject":"Archaic humans","subjectScheme":"PLOS Subject Area Thesaurus"},{"schemeUri":"https://github.com/PLOS/plos-thesaurus","subject":"Natural selection","subjectScheme":"PLOS Subject Area Thesaurus"}],"contributors":[{"nameType":"Personal","affiliation":["Brown University"],"name":"Huerta-Sánchez, Emilia","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-1506-5494"}],"contributorType":"ContactPerson"}],"dates":[{"date":"2025-05-08T12:57:20Z","dateType":"Created"},{"date":"2025-08-04T08:21:54Z","dateType":"Submitted"},{"date":"2025-08-21T00:00:00Z","dateType":"Issued"},{"date":"2025-08-21T00:00:00Z","dateType":"Available"}],"language":"en","types":{"schemaOrg":"Dataset","resourceTypeGeneral":"Dataset","citeproc":"dataset","bibtex":"misc","ris":"DATA","resourceType":"dataset"},"relatedIdentifiers":[{"relationType":"IsDerivedFrom","relatedIdentifier":"https://github.com/David-Peede/MUC19","relatedIdentifierType":"URL"},{"relationType":"IsCitedBy","relatedIdentifier":"10.1101/2023.09.25.559202","relatedIdentifierType":"DOI"},{"relationType":"IsCitedBy","relatedIdentifier":"10.1126/science.adl0882","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["145648852231 bytes"],"formats":[],"version":"8","rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/publicdomain/zero/1.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Zero v1.0 Universal","rightsIdentifier":"cc0-1.0"}],"descriptions":[{"descriptionType":"Abstract","description":"We study the gene MUC19, for which some modern humans carry a\n Denisovan-like haplotype. MUC19 is a mucin, a glycoprotein that forms gels\n with various biological functions. We find diagnostic variants for the\n Denisovan-like MUC19 haplotype at high frequencies in admixed Latin\n American individuals, and at highest frequency in 23 ancient Indigenous\n American individuals, all predating population admixture with Europeans\n and Africans. We find that the Denisovan-like MUC19 haplotype is under\n positive selection and carries a higher copy number of a 30 base-pair\n variable number tandem repeat, and that copy numbers of this repeat are\n exceedingly high in American populations. Finally, some Neanderthals carry\n the Denisovan-like MUC19 haplotype, and that it was likely introgressed\n into human populations through Neanderthal introgression rather than\n Denisovan introgression."},{"descriptionType":"Methods","description":"All code, meta information, and final results can be viewed on\n GitHub.\n These data are the intermediary files used to produce our final set of\n results."},{"descriptionType":"TechnicalInfo","description":"# Dryad Data **Citation:** Please cite [Villanea and Peede et al.\n 2025](https://doi.org/10.1126/science.adl0882)\n ([https://doi.org/10.1126/science.adl0882](https://doi.org/10.1126/science.adl0882)) when using this data. To use the data, you will first need to extract the individual data archives (`.tar.gz`). For example, run `tar -xf {data_archive}.tar.gz`. After extraction, you may need to edit the code on [GitHub](https://github.com/David-Peede/MUC19) so that the paths are appropriate for the computer on which the code is run. The paths provided in this README reflect my original project directory structure. Below is a quick reference of the naming conventions I used throughout the project. **Naming Conventions** * Archaic Individuals * `den`: Altai Denisovan * `alt`: Altai Neanderthal * `cha`: Chagyrskaya Neanderthal * This individual is considered a late Neanderthal. * `vin`: Vindija Neanderthal * This individual is considered a late Neanderthal. * Modern Human Datasets * `tgp`: 1000 Genomes Project * `sgdp`: Simon's Genome Diversity Project * 1000 Genomes Project Superpopulations \u0026amp; Populations * `afr`: Africans * Populations: `yri`, `lwk`, `gwd`, `msl`, `esn` * `amr`: Admixed Americans * Populations: `mxl`, `pel`, `clm`, `pur` * `sas`: South Asians * Populations: `beb`, `stu`, `itu`, `pjl`, `gih` * `eas`: East Asians * Populations: `chb`, `khv`, `chs`, `jpt`, `cdx` * `eur`: Europeans * Populations: `tsi`, `ceu`, `ibs`, `gbr`, `fin` ## Data Description **Note on Paths:** The file paths listed below correspond to the directory structure used in the original study. After extracting the archives, you may need to organize the files accordingly or adjust paths in the analysis scripts. ### `amr_lai` #### `72kb_amr_beds.tar.gz` \u0026amp; `short_read_repeat_amr_beds.tar.gz` Both `72kb_amr_beds.tar.gz` and `short_read_repeat_amr_beds.tar.gz` contain BED files, which are the output from the `bedtools` code found [here](https://github.com/David-Peede/MUC19/tree/main/amr_lai). **Paths** * `72kb_amr_beds.tar.gz` * `./muc19/amr_lai/region_beds/72kb/{amr_ind}_{A,B}.bed` * `short_read_repeat_amr_beds.tar.gz` * `./muc19/amr_lai/region_beds/short_read_repeat/{amr_ind}_{A,B}.bed` ##### `{amr_ind}_{A,B}.bed` Each admixed American individual (`{amr_ind}`) has two corresponding BED files, one per haplotype (`{A,B}`). Each BED file has the following columns: * Columns 1-6: Original columns from `RFmix`. * Columns 7-9: Coordinates for the intersecting region of interest. * The BED files for the intersecting region of interest can be found [here](https://github.com/David-Peede/MUC19/tree/main/amr_lai/region_beds). * Column 10: Number of base pairs of overlap with respect to the intersecting region of interest. ### `annotations` #### `annotations.tar.gz` `annotations.tar.gz` contains the output from `data_processing_v_revisions.ipynb` found [here](https://github.com/David-Peede/MUC19/blob/main/analyses_nbs/data_processing_v_revisions.ipynb) and the outputs from `tgp_single_archaic_gene_qc_v_revisions.py` and `consolidate_tgp_single_archaic_genes_v_revisions.py`, which can be found [here](https://github.com/David-Peede/MUC19/tree/main/annotations). **Paths** * `annotations.tar.gz` * `./muc19/annotations/hg19_genes/ncbi_refseq_genes_chr{1..22}.csv.gz` * `./muc19/annotations/hg19_genes/ncbi_refseq_transcripts.txt` * `./muc19/annotations/hg19_genes/ncbiRefSeqSelect.txt.gz` * `./muc19/annotations/rate_files/genetic_map_GRCh37_chr12.txt` * `./muc19/annotations/rate_files/subst_rate_autosome.bed.gz` * `./muc19/annotations/rate_files/subst_rate_autosome.bed.gz.tbi` * `./muc19/annotations/rate_files/{742,72}kb_region.bed` * `./muc19/annotations/rate_files/subst_rate_{742,72}kb.bed` * `./muc19/annotations/tgp_den_masked_no_aa/ncbi_refseq_genes_summary_chr{1..22}.csv.gz` * `./muc19/annotations/tgp_den_masked_no_aa/ncbi_refseq_{invariant,variant}_genes.csv.gz` ##### `ncbi_refseq_genes_chr{1..22}.csv.gz` One file per autosome (`{1..22}`) containing the NCBI RefSeq Select gene coordinates with the following columns: * `GENE_ID`: NCBI RefSeq Select gene ID. * `TRANSCRIPT_ID`: NCBI RefSeq Select transcript ID. * `START`: Start position (inclusive). * `STOP`: Stop position (inclusive). ##### `ncbi_refseq_transcripts.txt` One file with a single column listing all of the autosomal NCBI RefSeq Select transcript IDs used for the `SnpEff` annotations. ##### `ncbiRefSeqSelect.txt.gz` Original NCBI RefSeq Select gene coordinates in GTF format downloaded from UCSC Genome browser ([download link](https://hgdownload.cse.ucsc.edu/goldenpath/hg19/database/ncbiRefSeqSelect.txt.gz)), and the format of the file is described [here](https://genome.ucsc.edu/cgi-bin/hgTables?db=hg19\u0026amp;hgta_group=genes\u0026amp;hgta_track=refSeqComposite\u0026amp;hgta_table=refGene\u0026amp;hgta_doSchema=describe+table+schema). ##### `genetic_map_GRCh37_chr12.txt` HapMap genetic map for chromosome 12 build GRCh37/hg19, with the following columns: * `Chromosome`: Chromosome. * `Position(bp)` : Physical position. * `Rate(cM/Mb)`: Local recombination rate. * `Map(cM)`: The cumulative genetic map position with respect to the corresponding `Position(bp)` coordinate. ##### `subst_rate_autosome.bed.gz` and `subst_rate_autosome.bed.gz.tbi` `subst_rate_autosome.bed.gz` is a bgzipped BED file containing local mutation rates. This BED file was generated using [this script](https://github.com/StatisticalPopulationGenomics/ARGweaver/blob/master/helper_scripts/subst_rate.sh), with the following columns: * Column 1: Chromosome. * Column 2: Start position (inclusive). * Column 3: End position (exclusive). * Column 4: Local mutation rate. `subst_rate_autosome.bed.gz.tbi` is the corresponding binary index file using [`tabix`](https://www.htslib.org/doc/tabix.html), generated by running the following code: ```bash tabix -p bed subst_rate_autosome.bed.gz ``` ##### `{742,72}kb_region.bed` BED files with a single row per file for the focal 742kb and 72kb (`{742,72}kb`) *MUC19* regions, with the following columns: * Column 1: Chromosome. * Column 2: Start position (inclusive). * Column 3: End position (exclusive). ##### `subst_rate_{742,72}kb.bed` BED files containing the local mutation rates for the focal 742kb and 72kb (`{742,72}kb`) *MUC19* regions, generated by running the following [`bedtools`](https://bedtools.readthedocs.io/en/latest/) code: ```bash bedtools intersect -a subst_rate_autosome.bed.gz -b 72kb_region.bed -wo \u0026gt; subst_rate_72kb.bed bedtools intersect -a subst_rate_autosome.bed.gz -b 742kb_region.bed -wo \u0026gt; subst_rate_742kb.bed ``` with the following columns: * Columns 1-4: Original columns from `subst_rate_autosome.bed.gz` for the regions that intersect with the focal 742kb and 72kb (`{742,72}kb`) *MUC19* regions. * Columns 5-7: Original columns from 742kb and 72kb *MUC19* regions. * Column 8: Number of base pairs from `subst_rate_autosome.bed.gz` (i.e., columns 1-3 for a given row) that overlap with `{742,72}kb_region.bed` (i.e., columns 5-7 for a given row). ##### `ncbi_refseq_genes_summary_chr{1..22}.csv.gz` One file per autosome (`chr{1..22} ` ) where each row corresponds to the QC summary per NCBI RefSeq Select gene, with the following columns: * `IDX`: Gene index with respect to the `CHR` column. * `GENE_ID`: NCBI RefSeq Select gene ID. * `TRANSCRIPT_ID`: NCBI RefSeq Select transcript ID. * `START`: Start position (inclusive). * `STOP`: Stop position (inclusive). * `DEN`: Effective sequence length with respect to the Altai Denisovan. * `S`: Number of segregating sites. * `QC`: QC condition (numeric, e.g., 1 if true, 0 if false). ##### `ncbi_refseq_{invariant,variant}_genes.csv.gz` One file for invariant (`_invariant_`) and one for variant (`_variant_`) NCBI RefSeq Select genes, with the following columns: * `IDX`: Gene index with respect to the `CHR` column. * `GENE_ID`: NCBI RefSeq Select gene ID. * `TRANSCRIPT_ID`: NCBI RefSeq Select transcript ID. * `CHR`: Chromosome. * `START`: Start position (inclusive). * `STOP`: Stop position (inclusive). * `DEN`: Effective sequence length with respect to the Altai Denisovan. * `S`: Number of segregating sites. * `QC`: QC condition (numeric, e.g., 1 if true, 0 if false). **Note**: If only column headers are present in the invariant file (`_invariant_`), no invariant windows passed initial QC. ### `arc_snp_density` #### `classify_tgp_snps_chromosome.tar.gz` `classify_tgp_snps_chromosome.tar.gz` is the output from `classify_tgp_snps_chromosome_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/arc_snp_density). The original path is `./muc19/muc19_results/tgp_arcs_masked_no_aa/{non_afr_pop,tgp}_{snp_type}_chr{1..22}.txt.gz`. ##### ‌`{non_afr_pop,tgp}_{snp_type}_chr{1..22}.txt.gz` For each non-African population (`{non_afr_pop}`) and the entire 1000 Genomes Project (`{tgp}`), each file has one row listing the positions for the specified SNP classification (`{snp_type}`), stratified by autosome (`chr{1..22}`). #### `tgp_archaic_snp_denisty_windows.tar.gz` `tgp_archaic_snp_denisty_windows.tar.gz` is the output from `tgp_archaic_snp_denisty_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/arc_snp_density). The original path is `./muc19/muc19_results/tgp_arcs_masked_no_aa/{non_afr_pop}_arc_snp_denisty_chr{1..22}_{742,72}kb.txt.gz`. ##### `{non_afr_pop}_arc_snp_denisty_chr{1..22}_{742,72}kb.txt.gz` For each non-African population (`{non_afr_pop}`), each row contains archaic SNP partition counts for a non-overlapping 742kb or 72kb window (`{742,72}kb`), stratified by autosome (`chr{1..22}`), with the following columns: * Column 1: Denisovan-specific SNPs. * Column 2: Neanderthal-specific SNPs. * Column 3: Shared archaic SNPs. * Column 4: Archaic SNPs. ### `heterozygosity` #### `{den,alt,cha,vin}_heterozygosity_chromosome.tar.gz` `den_heterozygosity_chromosome.tar.gz`, `alt_heterozygosity_chromosome.tar.gz`, `cha_heterozygosity_chromosome.tar.gz`, and `vin_heterozygosity_chromosome.tar.gz` are the output from `archaic_heterozygosity_chromosome_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/heterozygosity). **Paths** * `den_heterozygosity_chromosome.tar.gz` * `./muc19/muc19_results/den_masked_no_aa/archaic_het_sites_heterozygosity_eff_seq_len_chr{1..22}.txt.gz` * `alt_heterozygosity_chromosome.tar.gz` * `./muc19/muc19_results/alt_masked_no_aa/archaic_het_sites_heterozygosity_eff_seq_len_chr{1..22}.txt.gz` * `cha_heterozygosity_chromosome.tar.gz` * `./muc19/muc19_results/cha_masked_no_aa/archaic_het_sites_heterozygosity_eff_seq_len_chr{1..22}.txt.gz` * `vin_heterozygosity_chromosome.tar.gz` * `./muc19/muc19_results/vin_masked_no_aa/archaic_het_sites_heterozygosity_eff_seq_len_chr{1..22}.txt.gz` ##### `archaic_het_sites_heterozygosity_eff_seq_len_chr{1..22}.txt.gz` For each archaic individual (`{den,alt,cha,vin}`), there is one corresponding file per autosome (`chr{1..22}`) with the following columns: * Column 1: Number of heterozygous sites. * Column 2: Gene diversity. * Column 3: Effective sequence length. #### `{den,alt,cha,vin}_heterozygosity_windows.tar.gz` `den_heterozygosity_windows.tar.gz`, `alt_heterozygosity_windows.tar.gz`, `cha_heterozygosity_windows.tar.gz`, and `vin_heterozygosity_windows.tar.gz` are the output from `archaic_heterozygosity_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/heterozygosity). **Paths** * `den_heterozygosity_windows.tar.gz` * `./muc19/muc19_results/den_masked_no_aa/archaic_het_sites_heterozygosity_chr{1..22}_72kb.txt.gz` * `alt_heterozygosity_windows.tar.gz` * `./muc19/muc19_results/alt_masked_no_aa/archaic_het_sites_heterozygosity_chr{1..22}_72kb.txt.gz` * `cha_heterozygosity_windows.tar.gz` * `./muc19/muc19_results/cha_masked_no_aa/archaic_het_sites_heterozygosity_chr{1..22}_72kb.txt.gz` * `vin_heterozygosity_windows.tar.gz` * `./muc19/muc19_results/vin_masked_no_aa/archaic_het_sites_heterozygosity_chr{1..22}_72kb.txt.gz` ##### `archaic_het_sites_heterozygosity_chr{1..22}_72kb.txt.gz` For each archaic individual (`{den,alt,cha,vin}`), there is one corresponding file per autosome (`chr{1..22}`). Each row corresponds to a non-overlapping 72kb window and has the following columns: * Column 1: Number of heterozygous sites. * Column 2: Gene diversity. #### `tgp_heterozygosity_chromosome.tar.gz` `tgp_heterozygosity_chromosome.tar.gz` is the output from `tgp_heterozygosity_chromosome_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/heterozygosity). **Paths** * `tgp_heterozygosity_chromosome.tar.gz` * `./muc19/muc19_results/tgp_mod_no_aa/tgp_het_sites_chr{1..22}.txt.gz` * `./muc19/muc19_results/tgp_mod_no_aa/afr_heterozygosity_eff_seq_len_chr{1..22}.txt.gz` ##### `tgp_het_sites_chr{1..22}.txt.gz` For each autosome (`chr{1..22}`), the columns correspond to a 1000 Genomes Project individual, in the same order as individuals appear in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data). Each entry is the number of heterozygous sites for that individual in that chromosome. ##### `afr_heterozygosity_eff_seq_len_chr{1..22}.txt.gz` For the African superpopulation (`afr`) in the 1000 Genomes Project, there is one corresponding file per autosome (`chr{1..22}`) with the following columns: * Column 1: Gene diversity. * Column 2: Effective sequence length. #### `tgp_heterozygosity_windows.tar.gz` `tgp_heterozygosity_windows.tar.gz` is the output from `tgp_heterozygosity_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/heterozygosity). The original path is `./muc19/muc19_results/tgp_mod_no_aa/{afr,het,hom}_het_sites_chr{1..22}_72kb.txt.gz`. ##### `{afr,het,hom}_het_sites_chr{1..22}_72kb.txt.gz` For each focal group (`{afr,het,hom}`), there is one corresponding file per autosome (`chr{1..22}`). Each row corresponds to a non-overlapping 72kb window, and the columns correspond to the number of heterozygous sites per 1000 Genomes Project individual. The order of individuals is as specified in the following metadata files: * `afr`: African individuals. * [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data) * `het`: Individuals with one introgressed haplotype at the 72kb region. * [`./muc19/meta_data/tgp_het_den_like_ind_idx_72kb.txt.gz`](https://github.com/David-Peede/MUC19/tree/main/meta_data) * `hom`: Individuals with two introgressed haplotypes at the 72kb region. * [`./muc19/meta_data/tgp_hom_den_like_ind_idx_72kb.txt.gz`](https://github.com/David-Peede/MUC19/tree/main/meta_data) ### `iHS` #### `tgp_selscan_maps.tar.gz` \u0026amp; `tgp_selscan_vcfs.tar.gz` `tgp_selscan_maps.tar.gz` and `tgp_selscan_vcfs.tar.gz` are the outputs from `make_selscan_population_data_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/iHS). **Paths** * `tgp_selscan_maps.tar.gz` * `./muc19/iHS/maps/{pop}_selscan_chr{1..22}.map` * `tgp_selscan_vcfs.tar.gz` * `./muc19/iHS/selscan_vcfs/{pop}_selscan_chr{1..22}.vcf` ##### ‌‌`{pop}_selscan_chr{1..22}.map` For every population in the 1000 Genomes Project (`{pop}`), there is one corresponding map file per autosome (`chr{1..22}`) with the following columns: * Column 1: Chromosome. * Column 2: Locus ID. * Column 3: Genetic position. * Column 4: Physical position. ##### ‌‌`{pop}_selscan_chr{1..22}.vcf` For every population in the 1000 Genomes Project (`{pop}`), there is one corresponding `selscan` formatted VCF file per autosome (`chr{1..22}`) with the following columns: * Column 1: Chromosome. * Column 2: Physical position. * Column 3: Locus ID. * Column 4: Ancestral allele. * Column 5: Derived allele. * Column 6: Quality field. * Column 7: Filter field. * Column 8: Info field. * Column 9: Format field. * Subsequent columns contain genotype information for individuals in the same order as they appear in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data). #### `tgp_selscan_ihs_output.tar.gz` `tgp_selscan_ihs_output.tar.gz` is the output from the `selscan` code found [here](https://github.com/David-Peede/MUC19/tree/main/iHS). **Paths** * `tgp_selscan_ihs_output.tar.gz` * `./muc19/muc19_results/tgp_mod_aa/{pop}_chr{1..22}.ihs.out` * `./muc19/muc19_results/tgp_mod_aa/{pop}_chr{1..22}.ihs.out.100bins.norm` ##### `{pop}_chr{1..22}.ihs.out` \u0026amp; `{pop}_chr{1..22}.ihs.out.100bins.norm` For every population in the 1000 Genomes Project (`{pop}`), there is a corresponding unnormalized (`.ihs.out`) and normalized (`.ihs.out.100bins.norm`) *iHS* file per autosome (`chr{1..22}`). The columns are described in the `selscan` documentation, which you can find [here](https://github.com/szpiech/selscan). #### `tgp_ihs_tables.tar.gz` `tgp_ihs_tables.tar.gz` is the output from `compile_ihs_tables_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/iHS). **Paths** * `tgp_ihs_tables.tar.gz`: * `./muc19/muc19_results/tgp_mod_aa/{pop}_ihs_genome_wide.csv.gz` * `./muc19/muc19_results/tgp_mod_aa/{pop}_ihs_windows_{742,72}kb.csv.gz` ##### `{pop}_ihs_genome_wide.csv.gz` For every population in the 1000 Genomes Project (`{pop}`), this file contains genome-wide *iHS* data with the following columns: * `ID`: Locus ID. * `CHR`: Chromosome. * `POS`: Physical position. * `DAF`: Derived allele frequency. * `IHH1`: Integrated haplotype homozygosity for the derived allele. * `IHH0`: Integrated haplotype homozygosity for the ancestral allele. * `U_IHS`: Unnormalized integrated haplotype score. * `N_IHS`: Normalized integrated haplotype score. * `CRIT`: Is the absolute value of the normalized *iHS* greater than two? (numeric, e.g., 1 if true, 0 if false). * `DEN`: Is this a Denisovan-specific SNP? (boolean). * `NEA`: Is this a Neanderthal-specific SNP? (boolean). * `SHR`: Is this a shared archaic SNP? (boolean). * `ARC`: Is this an archaic SNP? (boolean). * `HOM`: Is this a shared Hominin SNP? (boolean). * `HUM`: Is this a human-specific SNP? (boolean). * `ALL_CRIT`: Is the absolute value of the normalized *iHS* greater than two? (boolean). * `DEN_CRIT`: Is this a Denisovan-specific SNP AND is the absolute value of the normalized *iHS* greater than two? (boolean). * `NEA_CRIT`: Is this a Neanderthal-specific SNP AND is the absolute value of the normalized *iHS* greater than two? (boolean). * `SHR_CRIT`: Is this a shared archaic SNP AND is the absolute value of the normalized *iHS* greater than two? (boolean). * `ARC_CRIT`: Is this an archaic SNP AND is the absolute value of the normalized *iHS* greater than two? (boolean). * `HOM_CRIT`: Is this a shared Hominin SNP AND is the absolute value of the normalized *iHS* greater than two? (boolean). * `HUM_CRIT`: Is this a human-specific SNP AND is the absolute value of the normalized *iHS* greater than two? (boolean). ##### `{pop}_ihs_windows_{742,72}kb.csv.gz` For every population in the 1000 Genomes Project (`{pop}`), this file contains windowed *iHS* data. Each row corresponds to a non-overlapping window (`{742,72}kb`) with the following columns: * `CHR`: Chromosome. * `START`: Start position (inclusive). * `STOP`: Stop position (exclusive). * `N_ALL_SNPS`: Number of SNPs. * `N_DEN_SNPS`: Number of Denisovan-specific SNPs. * `N_NEA_SNPS`: Number of Neanderthal-specific SNPs. * `N_SHR_SNPS`: Number of shared archaic SNPs. * `N_ARC_SNPS`: Number of archaic SNPs. * `N_HOM_SNPS`: Number of shared Hominin SNPs. * `N_HUM_SNPS`: Number of human-specific SNPs. * `N_ALL_CRIT`: Number of SNPs with an absolute value of the normalized *iHS* greater than two. * `PROP_ALL_CRIT`: Proportion of SNPs with an absolute value of the normalized *iHS* greater than two. * `N_DEN_CRIT`: Number of Denisovan-specific SNPs with an absolute value of the normalized *iHS* greater than two. * `PROP_DEN_CRIT`: Proportion of Denisovan-specific SNPs with an absolute value of the normalized *iHS* greater than two. * `N_NEA_CRIT`: Number of Neanderthal-specific SNPs with an absolute value of the normalized *iHS* greater than two. * `PROP_NEA_CRIT`: Proportion of Neanderthal-specific SNPs with an absolute value of the normalized *iHS* greater than two. * `N_SHR_CRIT`: Number of shared archaic SNPs with an absolute value of the normalized *iHS* greater than two. * `PROP_SHR_CRIT`: Proportion of shared archaic SNPs with an absolute value of the normalized *iHS* greater than two. * `N_ARC_CRIT`: Number of archaic SNPs with an absolute value of the normalized *iHS* greater than two. * `PROP_ARC_CRIT`: Proportion of archaic SNPs with an absolute value of the normalized *iHS* greater than two. * `N_HOM_CRIT`: Number of shared Hominin SNPs with an absolute value of the normalized *iHS* greater than two. * `PROP_HOM_CRIT`: Proportion of shared Hominin SNPs with an absolute value of the normalized *iHS* greater than two. * `N_HUM_CRIT`: Number of human-specific SNPs with an absolute value of the normalized *iHS* greater than two. * `PROP_HUM_CRIT`: Proportion of human-specific SNPs with an absolute value of the normalized *iHS* greater than two. ### `introgression` #### `archaic_site_patterns_windows.tar.gz` `archaic_site_patterns_windows.tar.gz` is the output from `archaic_site_patterns_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/introgression). **Paths** * `archaic_site_patterns_windows.tar.gz` * `./muc19/muc19_results/arcs_masked_aa/alt_{cha,vin}_den_chr{1..22}_72kb.txt.gz` ##### `alt_{cha,vin}_den_chr{1..22}_72kb.txt.gz` For each late Neanderthal (`{cha,vin}`), there is one corresponding file per autosome (`chr{1..22}`). Each row corresponds to a non-overlapping 72kb window with the following columns: * Column 1: Number of ABBA sites. * Column 2: Number of BABA sites. * Column 3: Number of BBAA sites. * Column 4: Number of BAAA sites. * Column 5: Number of ABAA sites. * Column 6: Number of AABA sites. #### `yri_na19664_archaic_site_patterns_windows.tar.gz` `yri_na19664_archaic_site_patterns_windows.tar.gz` is the output from `mxl_archaic_site_patterns_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/introgression). **Paths** * `yri_na19664_archaic_site_patterns_windows.tar.gz`: * `./muc19/muc19_results/tgp_den_masked_aa/yri_na19664_den_chr{1..22}_{742,72}kb.txt.gz` * `./muc19/muc19_results/tgp_alt_masked_aa/yri_na19664_alt_chr{1..22}_{742,72}kb.txt.gz` * `./muc19/muc19_results/tgp_cha_masked_aa/yri_na19664_cha_chr{1..22}_{742,72}kb.txt.gz` * `./muc19/muc19_results/tgp_vin_masked_aa/yri_na19664_vin_chr{1..22}_{742,72}kb.txt.gz` ##### `yri_na19664_{den,alt,cha,vin}_chr{1..22}_{742,72}kb.txt.gz` For each archaic individual (`{den,alt,cha,vin}`), there is one corresponding file per autosome (`chr{1..22}`). Each row corresponds to a non-overlapping window (`{742,72}kb`) with the following columns: * Column 1: Number of ABBA sites. * Column 2: Number of BABA sites. * Column 3: Number of BBAA sites. * Column 4: Number of BAAA sites. * Column 5: Number of ABAA sites. * Column 6: Number of AABA sites. #### `tgp_q95_u30_afr_b_den_windows.tar.gz` `tgp_q95_u30_afr_b_den_windows.tar.gz` is the output from `tgp_q95_u30_afr_b_den_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/introgression). **Paths** * `tgp_q95_u30_afr_b_den_windows.tar.gz` * `./muc19/muc19_results/tgp_den_masked_no_aa/q95_u20_u30_afr_{non_afr_pop}_den_chr{1..22}_{742,72}kb.txt.gz` ##### `q95_u20_u30_afr_{non_afr_pop}_den_chr{1..22}_{742,72}kb.txt.gz` For each non-African population (`{non_afr_pop}`), there is one corresponding file per autosome (`chr{1..22}`). Each row corresponds to a non-overlapping window (`{742,72}kb`) with the following columns: * Column 1: The *Q95* value. * Column 2: The *U20* value. * Column 3: The *U30* value. #### `tgp_u30_afr_b_den_windows.tar.gz` `tgp_u30_afr_b_den_windows.tar.gz` is the output from `tgp_u30_afr_b_den_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/introgression). **Paths** * `tgp_u30_afr_b_den_windows.tar.gz` * `./muc19/muc19_results/tgp_den_masked_no_aa/u30_afr_b_den_chr{1..22}_{742,72}kb.txt.gz` ##### `u30_afr_b_den_chr{1..22}_{742,72}kb.txt.gz` For each autosome (`chr{1..22}`), there is one corresponding file. Each row corresponds to a non-overlapping window (`{742,72}kb`), and the columns correspond to the non-African population used to compute *U30* in the following order: MXL, PEL, CLM, PUR, BEB, STU, ITU, PJL, GIH, CHB, KHV, CHS, JPT, CDX, TSI, CEU, IBS, GBR, FIN. #### `tgp_u30_afr_b_den_genes.tar.gz` `tgp_u30_afr_b_den_genes.tar.gz` is the output from `tgp_u30_afr_b_den_genes_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/introgression). **Paths** * `tgp_u30_afr_b_den_genes.tar.gz` * `./muc19/muc19_results/tgp_den_masked_no_aa/u30_afr_b_den_per_gene_chr{1..22}.txt.gz` ##### `u30_afr_b_den_per_gene_chr{1..22}.txt.gz` For each autosome (`chr{1..22}`), there is one corresponding file. Each row corresponds to an NCBI RefSeq Select gene, and the columns correspond to the non-African population used to compute *U30* in the following order: MXL, PEL, CLM, PUR, BEB, STU, ITU, PJL, GIH, CHB, KHV, CHS, JPT, CDX, TSI, CEU, IBS, GBR, FIN. ### `pbs` #### `amr_asn_eur_pbs_windows.tar.gz` `amr_asn_eur_pbs_windows.tar.gz` is the output from `amr_asn_eur_pbs_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/pbs). **Paths** * `amr_asn_eur_pbs_windows.tar.gz` * `./muc19/muc19_results/tgp_mod_no_aa/{amr_pop}_{asn_pop}_{eur_pop}_chr{1..22}_{742,72}kb.txt.gz` ##### `{amr_pop}_{asn_pop}_{eur_pop}_chr{1..22}_{742,72}kb.txt.gz` *PBS(A, B, C)* values for all unique combinations of *A* = AMR population (`{amr_pop}`), *B* = EAS/SAS population (`{asn_pop}`), and *C* = EUR population (`{eur_pop}`). There is one corresponding file per autosome (`chr{1..22}`). Each file contains a single row, where each column in that row represents the *PBS(A,B,C)* value for a non-overlapping window (`{742,72}kb`). #### `mxl_chb_ceu_pbs_chromsome.tar.gz` `mxl_chb_ceu_pbs_chromsome.tar.gz` is the output from `mxl_chb_ceu_pbs_chromsome_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/pbs). **Paths** * `mxl_chb_ceu_pbs_chromsome.tar.gz` * `./muc19/muc19_results/tgp_mod_no_aa/mxl_chb_ceu_pbs_partitions_chr{1..22}.txt.gz` ##### `mxl_chb_ceu_pbs_partitions_chr{1..22}.txt.gz` For each autosome (`chr{1..22}`), there is one corresponding file. Each row corresponds to a genomic position and has the following columns: * Column 1: *PBS* using all MXL individuals. * Column 2: *PBS* using only MXL individuals with more than 50% Indigenous American ancestry. * Column 3: *PBS* using only MXL individuals with less than 50% Indigenous American ancestry. #### `mxl_chb_ceu_pbs_windows.tar.gz` `mxl_chb_ceu_pbs_windows.tar.gz` is the output from `mxl_chb_ceu_pbs_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/pbs). **Paths** * `mxl_chb_ceu_pbs_windows.tar.gz` * `./muc19/muc19_results/tgp_mod_no_aa/mxl_chb_ceu_pbs_partitions_chr{1..22}_{742,72}kb.txt.gz` ##### `mxl_chb_ceu_pbs_partitions_chr{1..22}_{742,72}kb.txt.gz` For each autosome (`chr{1..22}`), there is one corresponding file. Each row corresponds to a non-overlapping window (`{742,72}kb`) with the following columns: * Column 1: *PBS* using all MXL individuals. * Column 2: *PBS* using only MXL individuals with more than 50% Indigenous American ancestry. * Column 3: *PBS* using only MXL individuals with less than 50% Indigenous American ancestry. #### `sprime_sites_mxl_chb_ceu_pbs_windows.tar.gz` `sprime_sites_mxl_chb_ceu_pbs_windows.tar.gz` is the output from `sprime_sites_mxl_chb_ceu_pbs_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/pbs). **Paths** * `sprime_sites_mxl_chb_ceu_pbs_windows.tar.gz` * `./muc19/muc19_results/tgp_mod_no_aa/mxl_chb_ceu_pbs_sprime_all_arc_chr{1..22}_{742,72}kb.txt.gz` ##### `mxl_chb_ceu_pbs_sprime_all_arc_chr{1..22}_{742,72}kb.txt.gz` For each autosome (`chr{1..22}`), there is one corresponding file. Each row corresponds to a non-overlapping window (`{742,72}kb`) with the following columns: * Column 1: *PBS* for `SPrime` sites in MXL that match with either the Altai Denisovan or Altai Neanderthal. * Column 2: Number of `SPrime` sites in MXL that match with either the Altai Denisovan or Altai Neanderthal. ### `pbs_sims` #### `{neutral,negative,positive_neutral_s1,positive_neutral_s01,positive_neutral_s0015}_recomb_map_slimulated_vcfs.tar.gz` These archives (listed below) contain the VCF files from the SLiMulations. The `SLiM` scripts can be found [here](https://github.com/David-Peede/MUC19/tree/main/pbs_sims). * `neutral_recomb_map_slimulated_vcfs.tar.gz` is output from `sim_sneutral_rmap.slim`. * `negative_recomb_map_slimulated_vcfs.tar.gz` is output from `sim_snegative_rmap.slim`. * `positive_neutral_s1_recomb_map_slimulated_vcfs.tar.gz` is output from `sim_spositive_neutral_1_rmap.slim`. * `positive_neutral_s01_recomb_map_slimulated_vcfs.tar.gz` is output from `sim_spositive_neutral_01_rmap.slim`. * `positive_neutral_s0015_recomb_map_slimulated_vcfs.tar.gz` is output from `sim_spositive_neutral_0015_rmap.slim`. **Paths** * `neutral_recomb_map_slimulated_vcfs.tar.gz` * `./muc19/pbs_sims/smodel/neutral/recomb_map/VCF_sneutral_{sim_id}_{rep_id}.txt.gz` * `negative_recomb_map_slimulated_vcfs.tar.gz` * `./muc19/pbs_sims/smodel/negative/recomb_map/VCF_snegative_{sim_id}_{rep_id}.txt.gz` * `positive_neutral_s1_recomb_map_slimulated_vcfs.tar.gz` * `./muc19/pbs_sims/smodel/positive_neutral_1/VCF_spositive_neutral_{sim_id}_{rep_id}.txt` * `positive_neutral_s01_recomb_map_slimulated_vcfs.tar.gz` * `./muc19/pbs_sims/smodel/positive_neutral_01/VCF_spositive_neutral_{sim_id}_{rep_id}.txt` * `positive_neutral_s0015_recomb_map_slimulated_vcfs.tar.gz` * `./muc19/pbs_sims/smodel/positive_neutral_0015/VCF_spositive_neutral_{sim_id}_{rep_id}.txt` ##### `VCF_{sneutral,snegative,spositive_neutral}_{sim_id}_{rep_id}.{txt,txt.gz}` There are 10,000 simulated replicates (`{sim_id}_{rep_id}`), each as a bgzipped VCF file (`.txt.gz`), for the neutral (`{sneutral}`) and heterosis (`{snegative}`) SLiMulations. There are 1,000 simulated replicates, each as a VCF file (`.txt`), for the positive selection (`{spositive_neutral}`) SLiMulations. In each VCF file, the first 99 samples are simulated European individuals, the next 103 samples are simulated East Asian individuals, and the last 64 samples are simulated Mexican individuals. The VCF format specification can be found [here](https://samtools.github.io/hts-specs/VCFv4.2.pdf). #### `mxl_slimulations.tar.gz` `mxl_slimulations.tar.gz` is the output from `extract_neutral_negative_recomb_map_slimulated_results.py` and `extract_positive_slimulations_info.py` found [here](https://github.com/David-Peede/MUC19/tree/main/pbs_sims). **Paths** * `mxl_slimulations.tar.gz` * `./muc19/muc19_results/mxl_slimulations/{neutral,negative}_per_10k_replicates.csv.gz` * `./muc19/muc19_results/mxl_slimulations/{neutral,negative}_{all,arc}_snp_freqs_{742,72}kb_per_snp.txt.gz` * `./muc19/muc19_results/mxl_slimulations/{neutral,negative}_pbs_{all,arc}_snps_{742,72}kb_per_snp.txt.gz` * `./muc19/muc19_results/mxl_slimulations/positive_s{s1,s01,s0015}_per_1k_replicates.csv.gz` ##### `{neutral,negative}_per_10k_replicates.csv.gz` For each selection scenario (`{neutral,negative}`), there is one corresponding file. Each row corresponds to one simulated replicate, with the following columns: * `geq_all_snps_742kb`: Number of SNPs in MXL segregating at a frequency greater than or equal to 0.3 in the 742kb region. * `pbs_all_snps_742kb`: *PBS(A=MXL,B=EAS,C=EUR)* value for the 742kb region using all SNPs. * `prop_out_pbs_all_snps_742kb`: Proportion of per-SNP *PBS(A=MXL,B=EAS,C=EUR)* values greater than the empirical 99.95th percentile for the 742kb region. * `geq_arc_snps_742kb`: Number of archaic SNPs in MXL segregating at a frequency greater than or equal to 0.3 in the 742kb region. * `pbs_arc_snps_742kb`: *PBS(A=MXL,B=EAS,C=EUR)* value for the 742kb region using archaic SNPs. * `prop_out_pbs_arc_snps_742kb`: Proportion of per-archaic SNP *PBS(A=MXL,B=EAS,C=EUR)* values greater than the empirical 99.95th percentile for the 742kb region. * `geq_all_snps_72kb`: Number of SNPs in MXL segregating at a frequency greater than or equal to 0.3 in the 72kb region. * `pbs_all_snps_72kb`: *PBS(A=MXL,B=EAS,C=EUR)* value for the 72kb region using all SNPs. * `prop_out_pbs_all_snps_72kb`: Proportion of per-SNP *PBS(A=MXL,B=EAS,C=EUR)* values greater than the empirical 99.95th percentile for the 72kb region. * `geq_arc_snps_72kb`: Number of archaic SNPs in MXL segregating at a frequency greater than or equal to 0.3 in the 72kb region. * `pbs_arc_snps_72kb`: *PBS(A=MXL,B=EAS,C=EUR)* value for the 72kb region using archaic SNPs. * `prop_out_pbs_arc_snps_72kb`: Proportion of per-archaic SNP *PBS(A=MXL,B=EAS,C=EUR)* values greater than the empirical 99.95th percentile for the 72kb region. ##### `{neutral,negative}_{all,arc}_snp_freqs_{742,72}kb_per_snp.txt.gz` For each selection scenario (`{neutral,negative}`), there is one corresponding file for all (`{all}`) and archaic (`{arc}`) SNPs per focal region (`{742,72}kb`). Each file has one row, where the values represent the allele frequency for sites segregating in MXL across all 10,000 simulated replicates. ##### `{neutral,negative}_pbs_{all,arc}_snps_{742,72}kb_per_snp.txt.gz` For each selection scenario (`{neutral,negative}`), there is one corresponding file for all (`{all}`) and archaic (`{arc}`) SNPs per focal region (`{742,72}kb`). Each file has one row, where the values represent the per-SNP *PBS(A=MXL,B=EAS,C=EUR)* values across all 10,000 simulated replicates. ##### `positive_s{s1,s01,s0015}_per_1k_replicates.csv.gz` For each selection coefficient (`{s1,s01,s0015}`), there is one corresponding file. Each row corresponds to one simulated replicate, with the following columns: * `vcf_file`: Corresponding VCF file. * `rng_seed`: Corresponding SLiM rng seed. * `org_rep_id`: Arbitrary replicate ID. * `n_den_742kb`: Number of Denisovan SNPs in the 742kb region. * `n_nea_742kb`: Number of Neanderthal SNPs in the 742kb region. * `n_arc_742kb`: Number of archaic SNPs in the 742kb region. * `n_den_72kb`: Number of Denisovan SNPs in the 72kb region. * `n_nea_72kb`: Number of Neanderthal SNPs in the 72kb region. * `n_arc_72kb`: Number of archaic SNPs in the 72kb region. * `sel_pos`: Position of the selected mutation. * `sel_origin`: Population origin of the selected mutation. * `sel_mxl_daf`: Frequency of the selected allele in the sampled MXL individuals. * `sel_eas_daf`: Frequency of the selected allele in the sampled EAS individuals. * `sel_eur_daf`: Frequency of the selected allele in the sampled EUR individuals. * `MXB_before`: Frequency of the mutation in the MXB population before positive selection. * `EAS_before`: Frequency of the mutation in the EAS population before positive selection. * `EUR_before`: Frequency of the mutation in the EUR population before positive selection. * `MXB_after`: Frequency of the selected allele in the MXB population at the end of the SLiMulation. * `MXL_after`: Frequency of the selected allele in the MXL population at the end of the SLiMulation. * `EAS_after`: Frequency of the selected allele in the EAS population at the end of the SLiMulation. * `EUR_after`: Frequency of the selected allele in the EUR population at the end of the SLiMulation. * `n_seg_all_snps_742kb`: Number of segregating sites in the 742kb region. * `pbs_all_snps_742kb`: *PBS(A=MXL,B=EAS,C=EUR)* value for the 742kb region using all SNPs. * `fst_mxl_eas_all_snps_742kb`: *Fst(MXL,EAS)* value for the 742kb region using all SNPs. * `fst_mxl_eur_all_snps_742kb`: *Fst(MXL,EUR)* value for the 742kb region using all SNPs. * `fst_eas_eur_all_snps_742kb`: *Fst(EAS,EUR)* value for the 742kb region using all SNPs. * `n_seg_arc_snps_742kb`: Number of archaic SNPs segregating in the 742kb region. * `pbs_arc_snps_742kb`: *PBS(A=MXL,B=EAS,C=EUR)* value for the 742kb region using archaic SNPs. * `fst_mxl_eas_arc_snps_742kb`: *Fst(MXL,EAS)* value for the 742kb region using archaic SNPs. * `fst_mxl_eur_arc_snps_742kb`: *Fst(MXL,EUR)* value for the 742kb region using archaic SNPs. * `fst_eas_eur_arc_snps_742kb`: *Fst(EAS,EUR)* value for the 742kb region using archaic SNPs. * `n_seg_all_snps_72kb`: Number of segregating sites in the 722kb region. * `pbs_all_snps_72kb`: *PBS(A=MXL,B=EAS,C=EUR)* value for the 72kb region using all SNPs. * `fst_mxl_eas_all_snps_72kb`: *Fst(MXL,EAS)* value for the 72kb region using all SNPs. * `fst_mxl_eur_all_snps_72kb`: *Fst(MXL,EUR)* value for the 72kb region using all SNPs. * `fst_eas_eur_all_snps_72kb`: *Fst(EAS,EUR)* value for the 72kb region using all SNPs. * `n_seg_arc_snps_72kb`: Number of archaic SNPs segregating in the 72kb region. * `pbs_arc_snps_72kb`: *PBS(A=MXL,B=EAS,C=EUR)* value for the 72kb region using archaic SNPs. * `fst_mxl_eas_arc_snps_72kb`: *Fst(MXL,EAS)* value for the 72kb region using archaic SNPs. * `fst_mxl_eur_arc_snps_72kb`: *Fst(MXL,EUR)* value for the 72kb region using archaic SNPs. * `fst_eas_eur_arc_snps_72kb`: *Fst(EAS,EUR)* value for the 72kb region using archaic SNPs. ### `psuedo_ancestry_painting` #### `archaic_psuedo_ancestry_painting_windows.tar.gz` `archaic_psuedo_ancestry_painting_windows.tar.gz` is the output from `archaic_psuedo_ancestry_painting_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/psuedo_ancestry_painting). **Paths** * `archaic_psuedo_ancestry_painting_windows.tar.gz` * `./muc19/muc19_results/arcs_masked_no_aa/{cha,vin}_den_alt_pap_counts_chr{1..22}_72kb.txt.gz` ##### `{cha,vin}_den_alt_pap_counts_chr{1..22}_72kb.txt.gz` For each late Neanderthal (`{cha,vin}`), there is one corresponding file per autosome (`chr{1..22}`). Each row corresponds to a non-overlapping 72kb window with the following columns: * Column 1: Number of *PAP* sites. * Column 2: Number of heterozygous sites. #### `tgp_archaic_psuedo_ancestry_painting_windows.tar.gz` `tgp_archaic_psuedo_ancestry_painting_windows.tar.gz` is the output from `tgp_archaic_psuedo_ancestry_painting_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/psuedo_ancestry_painting). **Paths** * `tgp_archaic_psuedo_ancestry_painting_windows.tar.gz` * `./muc19/muc19_results/tgp_arcs_masked_no_aa/{den,alt,cha,vin}_mxl_yri_pap_counts_chr{1..22}_72kb.txt.gz` ##### `{cha,vin}_den_alt_pap_counts_chr{1..22}_72kb.txt.gz` For each archaic individual (`{den,alt,cha,vin}`), there is one corresponding file per autosome (`chr{1..22}`). Each row corresponds to a non-overlapping 72kb window with the following columns: * Column 1: Number of *PAP* sites. * Column 2: Number of heterozygous sites. ### `sequence_divergence` #### `den_v_alt_divergence_windows.tar.gz` `den_v_alt_divergence_windows.tar.gz` is the output from `arc_dip_v_arc_dip_divergence_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/sequence_divergence). **Paths** * `den_v_alt_divergence_windows.tar.gz` * `./muc19/muc19_results/arcs_masked_no_aa/den_v_alt_pw_diffs_chr{1..22}_72kb.txt.gz` ##### `den_v_alt_pw_diffs_chr{1..22}_72kb.txt.gz` For each autosome (`chr{1..22}`), there is one corresponding file. This file contains a single row, where each column in that row corresponds to the average number of pairwise differences between the Altai Denisovan's and Altai Neanderthal's two chromosomes per non-overlapping 72kb window. #### `sgdp_denisovan_sequence_divergence_at_denisovan_intro_tracts_in_papuans.tar.gz` `sgdp_denisovan_sequence_divergence_at_denisovan_intro_tracts_in_papuans.tar.gz` is the output from `sgdp_denisovan_sequence_divergence_at_denisovan_intro_tracts_in_papuans_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/sequence_divergence). **Paths** * `sgdp_denisovan_sequence_divergence_at_denisovan_intro_tracts_in_papuans.tar.gz` * `./muc19/muc19_results/sgdp_den_masked_no_aa/{pap_ind}_hap{1,2}_den_pw_diffs_seq_div_at_den_intro_tracts_chr{1..22}.txt.gz` ##### `{pap_ind}_hap{1,2}_den_pw_diffs_seq_div_at_den_intro_tracts_chr{1..22}.txt.gz` For each Papuan individual (`{pap_ind}`), there is one corresponding file per autosome (`chr{1..22}`) for each haploid genome (`hap{1,2}`). Each row corresponds to a Denisovan introgressed tract for the corresponding haploid genome (`hap{1,2}`) in the respective Papuan individual (`{pap_ind}`) with the following columns: * Column 1: The average number of pairwise differences between the Papuan individual's haplotype and the Altai Denisovan's two chromosomes. * Column 2: The corresponding sequence divergence. #### `tgp_hap_v_arc_dip_divergence_windows.tar.gz` `tgp_hap_v_arc_dip_divergence_windows.tar.gz` is the output from `tgp_hap_v_arc_dip_divergence_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/sequence_divergence). **Paths** * `tgp_hap_v_arc_dip_divergence_windows.tar.gz` * `./muc19/muc19_results/tgp_den_masked_no_aa/den_hap_{1,2}_pw_diffs_chr{1..22}_{742,72}kb.txt.gz` * `./muc19/muc19_results/tgp_alt_masked_no_aa/alt_hap_{1,2}_pw_diffs_chr{1..22}_{742,72}kb.txt.gz` * `./muc19/muc19_results/tgp_cha_masked_no_aa/cha_hap_{1,2}_pw_diffs_chr{1..22}_{742,72}kb.txt.gz` * `./muc19/muc19_results/tgp_vin_masked_no_aa/vin_hap_{1,2}_pw_diffs_chr{1..22}_{742,72}kb.txt.gz` ##### `{den,alt,cha,vin}_hap_{1,2}_pw_diffs_chr{1..22}_{742,72}kb.txt.gz` For each archaic individual (`{den,alt,cha,vin}`), there is one corresponding file per autosome (`chr{1..22}`) for each haploid genome (`hap_{1,2}`). Each row corresponds to a non-overlapping window (`{742,72}kb`). The columns correspond to the average number of pairwise differences between a 1000 Genomes Project individual's haplotype (`hap_{1,2}`) and the archaic individual's (`{den,alt,cha,vin}`) two chromosomes, in the same order as individuals appear in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data). #### `tgp_hap_v_arc_dip_divergence_windows.tar.gz` `tgp_hap_v_arc_dip_divergence_windows.tar.gz` is the output from `tgp_hap_v_arc_psuedo_hap_divergence_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/sequence_divergence). **Paths** * `tgp_hap_v_arc_psuedo_hap_divergence_windows.tar.gz` * `./muc19/muc19_results/tgp_cha_masked_no_aa/cha_hap_{1,2}_psuedo_hap_diffs_chr{1..22}_72kb.txt.gz` * `./muc19/muc19_results/tgp_vin_masked_no_aa/vin_hap_{1,2}_psuedo_hap_diffs_chr{1..22}_72kb.txt.gz` ##### `{cha,vin}_hap_{1,2}_psuedo_hap_diffs_chr{1..22}_72kb.txt.gz` For each late Neanderthal (`{cha,vin}`), there is one corresponding file per autosome (`chr{1..22}`) for each haploid genome (`hap_{1,2}`). Each row corresponds to a non-overlapping 72kb window. The columns correspond to the average number of pairwise differences between a 1000 Genomes Project individual's haplotype (`hap_{1,2}`) and the late Neanderthal's (`{cha,vin}`) pseudo-haplotype, in the same order as individuals appear in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data). #### `afr_v_den_divergence_windows.tar.gz` `afr_v_den_divergence_windows.tar.gz` is the output from `tgp_spop_v_arc_dip_divergence_windows_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/sequence_divergence). **Paths** * `afr_v_den_divergence_windows.tar.gz` * `./muc19/muc19_results/tgp_den_masked_no_aa/afr_den_avg_pw_diffs_chr{1..22}_72kb.txt.gz` ##### `afr_den_avg_pw_diffs_chr{1..22}_72kb.txt.gz` For each autosome (`chr{1..22}`), there is one corresponding file. This file contains one row, where each column corresponds to the average number of pairwise differences between all African chromosomes in the 1000 Genomes Project and the Altai Denisovan's two chromosomes per non-overlapping 72kb window. ### `vcf_data` Since ALL of the VCF files and bookkeeping information are well over 3TB, we provide the converted Zarr arrays, which are the output of `vcf_to_zarr_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/vcf_data), as 99.99% of analyses are performed using these data. Additionally, in the following `windowing` subsubsection, we provide the corresponding bookkeeping files used in our analyses and include the raw bookkeeping files for the sake of completeness, which are located in `bookkeeping.tar.gz`. Note that all VCF files are formatted in accordance with the [VCF specification](https://samtools.github.io/hts-specs/VCFv4.2.pdf), and the format of the raw bookkeeping files is described in the VCF processing scripts found [here](https://github.com/David-Peede/MUC19/tree/main/vcf_data). The `{prefix}.tar.gz` files are named by the dataset (`{prefix}`) and, unless otherwise noted, contain the corresponding Zarr arrays for all autosomes (`chr{1..22}`). **Datasets \u0026amp; Paths** * `arcs_masked_no_aa.tar.gz` * All archaic individuals without ancestral allele calls. Individuals are in the following order: Altai Neanderthal, Chagyrskaya Neanderthal, Vindija Neanderthal, Altai Denisovan. * `./muc19/zarr_data/arcs_masked_no_aa_chr{1..22}.zarr` * `arcs_masked_aa.tar.gz` * All archaic individuals with ancestral allele calls. Individuals are in the following order: Altai Neanderthal, Chagyrskaya Neanderthal, Vindija Neanderthal, Altai Denisovan, and a placeholder individual \"Ancestor\" who is always homozygous for the ancestral allele. * `./muc19/zarr_data/arcs_masked_no_aa_chr{1..22}.zarr` * `{den,alt,cha,vin}_masked_no_aa.tar.gz` * `den_masked_no_aa.tar.gz`: Altai Denisovan without ancestral allele calls. * `./muc19/zarr_data/den_masked_no_aa_chr{1..22}.zarr` * `alt_masked_no_aa.tar.gz`: Altai Denisovan without ancestral allele calls. * `./muc19/zarr_data/alt_masked_no_aa_chr{1..22}.zarr` * `cha_masked_no_aa.tar.gz`: Chagyrskaya Neanderthal without ancestral allele calls. * `./muc19/zarr_data/cha_masked_no_aa_chr{1..22}.zarr` * `vin_masked_no_aa.tar.gz`: Vindija Neanderthal without ancestral allele calls. * `./muc19/zarr_data/vin_masked_no_aa_chr{1..22}.zarr` * `tgp_arcs_masked_no_aa.tar.gz` * 1000 Genomes Project and all archaic individuals without ancestral allele calls. Individuals are in the following order: 1000 Genomes Project individuals (order as in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)), Altai Neanderthal, Chagyrskaya Neanderthal, Vindija Neanderthal, Altai Denisovan. * `./muc19/zarr_data/tgp_arcs_masked_no_aa_chr{1..22}.zarr` * `tgp_{den,alt,cha,vin}_masked_no_aa.tar.gz` * `tgp_den_masked_no_aa.tar.gz`: 1000 Genomes Project (order as in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)) and the Altai Denisovan, without ancestral allele calls. * `./muc19/zarr_data/tgp_den_masked_no_aa_chr{1..22}.zarr` * `tgp_alt_masked_no_aa.tar.gz`: 1000 Genomes Project (order as in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)) and the Altai Neanderthal, without ancestral allele calls. * `./muc19/zarr_data/tgp_alt_masked_no_aa_chr{1..22}.zarr` * `tgp_cha_masked_no_aa.tar.gz`: 1000 Genomes Project (order as in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)) and the Chagyrskaya Neanderthal, without ancestral allele calls. * `./muc19/zarr_data/tgp_cha_masked_no_aa_chr{1..22}.zarr` * `tgp_vin_masked_no_aa.tar.gz`: 1000 Genomes Project (order as in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)) and the Vindija Neanderthal, without ancestral allele calls. * `./muc19/zarr_data/tgp_vin_masked_no_aa_chr{1..22}.zarr` * `tgp_{den,alt,cha,vin}_masked_aa.tar.gz` * `tgp_den_masked_aa.tar.gz`: 1000 Genomes Project (order as in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)), the Altai Denisovan, and a placeholder individual \"Ancestor\" who is always homozygous for the ancestral allele. * `./muc19/zarr_data/tgp_den_masked_aa_chr{1..22}.zarr` * `tgp_alt_masked_aa.tar.gz`: 1000 Genomes Project (order as in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)), the Altai Neanderthal, and a placeholder individual \"Ancestor\" who is always homozygous for the ancestral allele. * `./muc19/zarr_data/tgp_alt_masked_aa_chr{1..22}.zarr` * `tgp_cha_masked_aa.tar.gz`: 1000 Genomes Project (order as in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)), the Chagyrskaya Neanderthal, and a placeholder individual \"Ancestor\" who is always homozygous for the ancestral allele. * `./muc19/zarr_data/tgp_cha_masked_aa_chr{1..22}.zarr` * `tgp_vin_masked_aa.tar.gz`: 1000 Genomes Project (order as in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)), the Vindija Neanderthal, and a placeholder individual \"Ancestor\" who is always homozygous for the ancestral allele. * `./muc19/zarr_data/tgp_vin_masked_aa_chr{1..22}.zarr` * `sgdp_arcs_masked_no_aa.tar.gz` * Simon's Genome Diversity Project and all archaic individuals without ancestral allele calls. Individuals are in the following order: Simon's Genome Diversity Project individuals (order as in [`./muc19/meta_data/sgdp.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)), Altai Neanderthal, Chagyrskaya Neanderthal, Vindija Neanderthal, Altai Denisovan. * `./muc19/zarr_data/sgdp_arcs_masked_no_aa_chr{1..22}.zarr` * `sgdp_{den,alt,cha,vin}_masked_no_aa.tar.gz` * `sgdp_den_masked_no_aa.tar.gz`: Simon's Genome Diversity Project (order as in [`./muc19/meta_data/sgdp.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)) and the Altai Denisovan, without ancestral allele calls. * `./muc19/zarr_data/sgdp_den_masked_no_aa_chr{1..22}.zarr` * `sgdp_alt_masked_no_aa.tar.gz`: Simon's Genome Diversity Project (order as in [`./muc19/meta_data/sgdp.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)) and the Altai Neanderthal, without ancestral allele calls. * `./muc19/zarr_data/sgdp_alt_masked_no_aa_chr{1..22}.zarr` * `sgdp_cha_masked_no_aa.tar.gz`: Simon's Genome Diversity Project (order as in [`./muc19/meta_data/sgdp.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)) and the Chagyrskaya Neanderthal, without ancestral allele calls. * `./muc19/zarr_data/sgdp_cha_masked_no_aa_chr{1..22}.zarr` * `sgdp_vin_masked_no_aa.tar.gz`: Simon's Genome Diversity Project (order as in [`./muc19/meta_data/sgdp.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data)) and the Vindija Neanderthal, without ancestral allele calls. * `./muc19/zarr_data/sgdp_vin_masked_no_aa_chr{1..22}.zarr` * `tgp_mod_no_aa.tar.gz` * 1000 Genomes Project without ancestral allele calls. Individuals are in the same order as they appear in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data). * `./muc19/zarr_data/tgp_mod_no_aa_chr{1..22}.zarr` * `tgp_mod_aa.tar.gz` * 1000 Genomes Project with ancestral allele calls. Individuals are in the same order as they appear in [`./muc19/meta_data/tgp_mod.txt`](https://github.com/David-Peede/MUC19/tree/main/meta_data), and a placeholder individual \"Ancestor\" who is always homozygous for the ancestral allele. * `./muc19/zarr_data/tgp_mod_aa_chr{1..22}.zarr` * `cha_phased_ref_panel_all_inds.tar.gz` * Corresponding output from `BEAGLE` before read-based phasing for the focal 72kb region, without ancestral allele calls. Individuals are in the following order: Altai Neanderthal, Chagyrskaya Neanderthal, Altai Denisovan. * `./muc19/zarr_data/cha_phased_ref_panel_all_inds.zarr` * Note that this is a single Zarr array for the focal 72kb region. * The input VCF file can be found [here](https://github.com/David-Peede/MUC19/tree/main/vcf_data/phasing). * `vin_phased_ref_panel_all_inds.tar.gz` * Corresponding output from `BEAGLE` before read-based phasing for the focal 72kb region, without ancestral allele calls. Individuals are in the following order: Altai Neanderthal, Vindija Neanderthal, Altai Denisovan. * `./muc19/zarr_data/vin_phased_ref_panel_all_inds.zarr` * Note that this is a single Zarr array for the focal 72kb region. * The input VCF file can be found [here](https://github.com/David-Peede/MUC19/tree/main/vcf_data/phasing). ### `windowing` #### `arcs_masked_no_aa_window_info_and_eff_seq_len.tar.gz` `arcs_masked_no_aa_window_info_and_eff_seq_len.tar.gz` is the output from `consolidate_all_archaics_tgp_sgdp_windows_v_revisions.py` and `compute_region_effective_sequence_lengths_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/windowing). **Paths** * `arcs_masked_no_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/arcs_masked_no_aa/72kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/arcs_masked_no_aa/72kb_esl_qced_nonoverlapping_variant_windows.txt.gz` * `./muc19/windowing/arcs_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` ##### `72kb_nonoverlapping_{invariant,variant}_windows.csv.gz` One file for invariant (`_invariant_`) and one for variant (`_variant_`) 72kb non-overlapping windows, with the following columns: * `IDX`: Window index with respect to the `CHR` column. * `CHR`: Chromosome. * `START`: Start position (inclusive). * `STOP`: Stop position (inclusive). * `ALT`: Altai Neanderthal effective sequence length. * `CHA`: Chagyrskaya Neanderthal effective sequence length. * `VIN`: Vindija Neanderthal effective sequence length. * `DEN`: Altai Denisovan effective sequence length. * `DEN-ALT`: Effective sequence length for Altai Denisovan-Altai Neanderthal comparisons. * `DEN-CHA`: Effective sequence length for Altai Denisovan-Chagyrskaya Neanderthal comparisons. * `DEN-VIN`: Effective sequence length for Altai Denisovan-Vindija Neanderthal comparisons. * `ALT-CHA`: Effective sequence length for Altai Neanderthal-Chagyrskaya Neanderthal comparisons. * `ALT-VIN`: Effective sequence length for Altai Neanderthal-Vindija Neanderthal comparisons. * `CHA-VIN`: Effective sequence length for Chagyrskaya Neanderthal-Vindija Neanderthal comparisons. * `S`: Number of segregating sites. * `QC`: QC condition (numeric, e.g., 1 if true, 0 if false). **Note**: If only column headers are present in the invariant file (`_invariant_`), no invariant windows passed initial QC. ##### `72kb_esl_qced_nonoverlapping_variant_windows.txt.gz` Indices of 72kb variant windows of comparable effective sequence length, used for subsetting `72kb_nonoverlapping_variant_windows.csv.gz`. ##### `{742,72}kb_eff_seq_len.txt.gz` Effective sequence lengths for the focal regions (`{742,72}kb`) with the following columns: * Column 1: Altai Neanderthal effective sequence length. * Column 2: Chagyrskaya Neanderthal effective sequence length. * Column 3: Vindija Neanderthal effective sequence length. * Column 4: Altai Denisovan effective sequence length. * Column 5: Effective sequence length for Altai Denisovan-Altai Neanderthal comparisons. * Column 6: Effective sequence length for Altai Denisovan-Chagyrskaya Neanderthal comparisons. * Column 7: Effective sequence length for Altai Denisovan-Vindija Neanderthal comparisons. * Column 8: Effective sequence length for Altai Neanderthal-Chagyrskaya Neanderthal comparisons. * Column 9: Effective sequence length for Altai Neanderthal-Vindija Neanderthal comparisons. * Column 10: Effective sequence length for Chagyrskaya Neanderthal-Vindija Neanderthal comparisons. #### `arcs_masked_aa_window_info_and_eff_seq_len.tar.gz` `arcs_masked_aa_window_info_and_eff_seq_len.tar.gz` is the output from `consolidate_all_archaics_tgp_sgdp_windows_v_revisions.py` and `compute_region_effective_sequence_lengths_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/windowing). **Paths** * `arcs_masked_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/arcs_masked_aa/72kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/arcs_masked_aa/72kb_esl_qced_nonoverlapping_variant_windows.txt.gz` * `./muc19/windowing/arcs_masked_aa/{742,72}kb_eff_seq_len.txt.gz` ##### `72kb_nonoverlapping_{invariant,variant}_windows.csv.gz` One file for invariant (`_invariant_`) and one for variant (`_variant_`) 72kb non-overlapping windows, with the following columns: * `IDX`: Window index with respect to the `CHR` column. * `CHR`: Chromosome. * `START`: Start position (inclusive). * `STOP`: Stop position (inclusive). * `ALT`: Altai Neanderthal effective sequence length. * `CHA`: Chagyrskaya Neanderthal effective sequence length. * `VIN`: Vindija Neanderthal effective sequence length. * `DEN`: Altai Denisovan effective sequence length. * `DEN-ALT`: Effective sequence length for Altai Denisovan-Altai Neanderthal comparisons. * `DEN-CHA`: Effective sequence length for Altai Denisovan-Chagyrskaya Neanderthal comparisons. * `DEN-VIN`: Effective sequence length for Altai Denisovan-Vindija Neanderthal comparisons. * `ALT-CHA`: Effective sequence length for Altai Neanderthal-Chagyrskaya Neanderthal comparisons. * `ALT-VIN`: Effective sequence length for Altai Neanderthal-Vindija Neanderthal comparisons. * `CHA-VIN`: Effective sequence length for Chagyrskaya Neanderthal-Vindija Neanderthal comparisons. * `S`: Number of segregating sites. * `QC`: QC condition (numeric, e.g., 1 if true, 0 if false). **Note**: If only column headers are present in the invariant file (`_invariant_`), no invariant windows passed initial QC. ##### `72kb_esl_qced_nonoverlapping_variant_windows.txt.gz` Indices of 72kb variant windows of comparable effective sequence length, used for subsetting `72kb_nonoverlapping_variant_windows.csv.gz`. ##### `{742,72}kb_eff_seq_len.txt.gz` Effective sequence lengths for the focal regions (`{742,72}kb`) with the following columns: * Column 1: Altai Neanderthal effective sequence length. * Column 2: Chagyrskaya Neanderthal effective sequence length. * Column 3: Vindija Neanderthal effective sequence length. * Column 4: Altai Denisovan effective sequence length. * Column 5: Effective sequence length for Altai Denisovan-Altai Neanderthal comparisons. * Column 6: Effective sequence length for Altai Denisovan-Chagyrskaya Neanderthal comparisons. * Column 7: Effective sequence length for Altai Denisovan-Vindija Neanderthal comparisons. * Column 8: Effective sequence length for Altai Neanderthal-Chagyrskaya Neanderthal comparisons. * Column 9: Effective sequence length for Altai Neanderthal-Vindija Neanderthal comparisons. * Column 10: Effective sequence length for Chagyrskaya Neanderthal-Vindija Neanderthal comparisons. #### `{den,alt,cha,vin}_masked_no_aa_window_info_and_eff_seq_len.tar.gz` `arcs_masked_no_aa_window_info_and_eff_seq_len.tar.gz` is the output from `consolidate_all_archaics_tgp_sgdp_windows_v_revisions.py` and `compute_region_effective_sequence_lengths_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/windowing). **Paths** * `den_masked_no_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/den_masked_no_aa/72kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/den_masked_no_aa/72kb_esl_qced_nonoverlapping_{invariant,variant}_windows.txt.gz` * `./muc19/windowing/den_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` * `alt_masked_no_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/alt_masked_no_aa/72kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/alt_masked_no_aa/72kb_esl_qced_nonoverlapping_{invariant,variant}_windows.txt.gz` * `./muc19/windowing/alt_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` * `cha_masked_no_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/cha_masked_no_aa/72kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/cha_masked_no_aa/72kb_esl_qced_nonoverlapping_{invariant,variant}_windows.txt.gz` * `./muc19/windowing/cha_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` * `vin_masked_no_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/vin_masked_no_aa/72kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/vin_masked_no_aa/72kb_esl_qced_nonoverlapping_{invariant,variant}_windows.txt.gz` * `./muc19/windowing/vin_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` ##### `72kb_nonoverlapping_{invariant,variant}_windows.csv.gz` One file for invariant (`_invariant_`) and one for variant (`_variant_`) 72kb non-overlapping windows, with the following columns: * `IDX`: Window index with respect to the `CHR` column. * `CHR`: Chromosome. * `START`: Start position (inclusive). * `STOP`: Stop position (inclusive). * `{ARC}`: Effective sequence length with respect to the given archaic individual (e.g., `DEN` for Altai Denisovan). * `S`: Number of segregating sites. * `QC`: QC condition (numeric, e.g., 1 if true, 0 if false). **Note**: If only column headers are present in the invariant file (`_invariant_`), no invariant windows passed initial QC. ##### `72kb_esl_qced_nonoverlapping_{invariant,variant}_windows.txt.gz` Indices of non-overlapping 72kb invariant (`_invariant_`) and variant (`_variant_`) windows of comparable effective sequence length, used for subsetting the corresponding `72kb_nonoverlapping_{invariant,variant}_windows.csv.gz` file. ##### `{742,72}kb_eff_seq_len.txt.gz` Effective sequence lengths for the focal regions (`{742,72}kb`) with respect to the given archaic individual—singe value per file. #### `tgp_arcs_masked_no_aa_window_info_and_eff_seq_len.tar.gz` `tgp_arcs_masked_no_aa_window_info_and_eff_seq_len.tar.gz` is the output from `consolidate_all_archaics_tgp_sgdp_windows_v_revisions.py` and `compute_region_effective_sequence_lengths_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/windowing). **Paths** * `tgp_arcs_masked_no_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/tgp_arcs_masked_no_aa/{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/tgp_arcs_masked_no_aa/{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` * `./muc19/windowing/tgp_arcs_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` ##### `{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` One file for invariant (`_invariant_`) and one for variant (`_variant_`) per window size (`{742,72}kb`), with the following columns: * `IDX`: Window index with respect to the `CHR` column. * `CHR`: Chromosome. * `START`: Start position (inclusive). * `STOP`: Stop position (inclusive). * `ALT`: Effective sequence length for Altai Neanderthal comparisons. * `CHA`: Effective sequence length for Chagyrskaya Neanderthal comparisons. * `VIN`: Effective sequence length for Vindija Neanderthal comparisons. * `DEN`: Effective sequence length for Altai Denisovan comparisons. * `DEN-ALT`: Effective sequence length for Altai Denisovan-Altai Neanderthal comparisons. * `DEN-CHA`: Effective sequence length for Altai Denisovan-Chagyrskaya Neanderthal comparisons. * `DEN-VIN`: Effective sequence length for Altai Denisovan-Vindija Neanderthal comparisons. * `ALT-CHA`: Effective sequence length for Altai Neanderthal-Chagyrskaya Neanderthal comparisons. * `ALT-VIN`: Effective sequence length for Altai Neanderthal-Vindija Neanderthal comparisons. * `CHA-VIN`: Effective sequence length for Chagyrskaya Neanderthal-Vindija Neanderthal comparisons. * `S`: Number of segregating sites. * `QC`: QC condition (numeric, e.g., 1 if true, 0 if false). **Note**: If only column headers are present in the invariant file (`_invariant_`), no invariant windows passed initial QC. ##### `{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` Indices of variant windows per window size (`{742,72}kb`) of comparable effective sequence length, used for subsetting `{742,72}kb_nonoverlapping_variant_windows.csv.gz`. ##### `{742,72}kb_eff_seq_len.txt.gz` Effective sequence lengths for the focal regions (`{742,72}kb`) with the following columns: * Column 1: Effective sequence length for Altai Neanderthal comparisons. * Column 2: Effective sequence length for Chagyrskaya Neanderthal comparisons. * Column 3: Effective sequence length for Vindija Neanderthal comparisons. * Column 4: Effective sequence length for Altai Denisovan comparisons. * Column 5: Effective sequence length for Altai Denisovan-Altai Neanderthal comparisons. * Column 6: Effective sequence length for Altai Denisovan-Chagyrskaya Neanderthal comparisons. * Column 7: Effective sequence length for Altai Denisovan-Vindija Neanderthal comparisons. * Column 8: Effective sequence length for Altai Neanderthal-Chagyrskaya Neanderthal comparisons. * Column 9: Effective sequence length for Altai Neanderthal-Vindija Neanderthal comparisons. * Column 10: Effective sequence length for Chagyrskaya Neanderthal-Vindija Neanderthal comparisons. #### `tgp_{den,alt,cha,vin}_masked_no_aa_window_info_and_eff_seq_len.tar.gz` `tgp_{den,alt,cha,vin}_masked_no_aa_window_info_and_eff_seq_len.tar.gz` is the output from `consolidate_all_archaics_tgp_sgdp_windows_v_revisions.py` and `compute_region_effective_sequence_lengths_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/windowing). **Paths** * `tgp_den_masked_no_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/tgp_den_masked_no_aa/{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/tgp_den_masked_no_aa/{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` * `./muc19/windowing/tgp_den_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` * `tgp_alt_masked_no_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/tgp_alt_masked_no_aa/{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/tgp_alt_masked_no_aa/{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` * `./muc19/windowing/tgp_alt_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` * `tgp_cha_masked_no_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/tgp_cha_masked_no_aa/{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/tgp_cha_masked_no_aa/{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` * `./muc19/windowing/tgp_cha_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` * `tgp_vin_masked_no_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/tgp_vin_masked_no_aa/{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/tgp_vin_masked_no_aa/{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` * `./muc19/windowing/tgp_vin_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` ##### `{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` One file for invariant (`_invariant_`) and one for variant (`_variant_`) per window size (`{742,72}kb`), with the following columns: * `IDX`: Window index with respect to the `CHR` column. * `CHR`: Chromosome. * `START`: Start position (inclusive). * `STOP`: Stop position (inclusive). * `{ARC}`: Effective sequence length with respect to the given archaic individual (e.g., `DEN` for Altai Denisovan). * `S`: Number of segregating sites. * `QC`: QC condition (numeric, e.g., 1 if true, 0 if false). **Note**: If only column headers are present in the invariant file (`_invariant_`), no invariant windows passed initial QC. ##### `{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` Indices of variant windows per window size (`{742,72}kb`) of comparable effective sequence length, used for subsetting `{742,72}kb_nonoverlapping_variant_windows.csv.gz`. ##### `{742,72}kb_eff_seq_len.txt.gz` Effective sequence lengths for the focal regions (`{742,72}kb`) with respect to the given archaic individual—singe value per file. #### `tgp_{den,alt,cha,vin}_masked_aa_window_info_and_eff_seq_len.tar.gz` `tgp_{den,alt,cha,vin}_masked_aa_window_info_and_eff_seq_len.tar.gz` is the output from `consolidate_all_archaics_tgp_sgdp_windows_v_revisions.py` and `compute_region_effective_sequence_lengths_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/windowing). **Paths** * `tgp_den_masked_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/tgp_den_masked_aa/{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/tgp_den_masked_aa/{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` * `./muc19/windowing/tgp_den_masked_aa/{742,72}kb_eff_seq_len.txt.gz` * `tgp_alt_masked_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/tgp_alt_masked_aa/{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/tgp_alt_masked_aa/{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` * `./muc19/windowing/tgp_alt_masked_aa/{742,72}kb_eff_seq_len.txt.gz` * `tgp_cha_masked_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/tgp_cha_masked_aa/{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/tgp_cha_masked_aa/{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` * `./muc19/windowing/tgp_cha_masked_aa/{742,72}kb_eff_seq_len.txt.gz` * `tgp_vin_masked_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/tgp_vin_masked_aa/{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/tgp_vin_masked_aa/{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` * `./muc19/windowing/tgp_vin_masked_aa/{742,72}kb_eff_seq_len.txt.gz` ##### `{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` One file for invariant (`_invariant_`) and one for variant (`_variant_`) per window size (`{742,72}kb`), with the following columns: * `IDX`: Window index with respect to the `CHR` column. * `CHR`: Chromosome. * `START`: Start position (inclusive). * `STOP`: Stop position (inclusive). * `{ARC}`: Effective sequence length with respect to the given archaic individual (e.g., `DEN` for Altai Denisovan). * `S`: Number of segregating sites. * `QC`: QC condition (numeric, e.g., 1 if true, 0 if false). **Note**: If only column headers are present in the invariant file (`_invariant_`), no invariant windows passed initial QC. ##### `{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` Indices of variant windows per window size (`{742,72}kb`) of comparable effective sequence length, used for subsetting `{742,72}kb_nonoverlapping_variant_windows.csv.gz`. ##### `{742,72}kb_eff_seq_len.txt.gz` Effective sequence lengths for the focal regions (`{742,72}kb`) with respect to the given archaic individual—singe value per file. #### `sgdp_{den,alt,cha,vin}_masked_no_aa_eff_seq_len.tar.gz` `sgdp_{den,alt,cha,vin}_masked_no_aa_eff_seq_len.tar.gz` is the output from `compute_region_effective_sequence_lengths_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/windowing). **Paths** * `sgdp_den_masked_no_aa_eff_seq_len.tar.gz` * `./muc19/windowing/sgdp_den_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` * `sgdp_alt_masked_no_aa_eff_seq_len.tar.gz` * `./muc19/windowing/sgdp_alt_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` * `sgdp_cha_masked_no_aa_eff_seq_len.tar.gz` * `./muc19/windowing/sgdp_cha_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` * `sgdp_vin_masked_no_aa_eff_seq_len.tar.gz` * `./muc19/windowing/sgdp_vin_masked_no_aa/{742,72}kb_eff_seq_len.txt.gz` ##### `{742,72}kb_eff_seq_len.txt.gz` Effective sequence lengths for the focal regions (`{742,72}kb`) with respect to the given archaic individual—singe value per file. #### `tgp_mod_no_aa_window_info_and_eff_seq_len.tar.gz` `tgp_mod_no_aa_window_info_and_eff_seq_len.tar.gz` is the output from `consolidate_all_archaics_tgp_sgdp_windows_v_revisions.py` and `compute_region_effective_sequence_lengths_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/windowing). **Paths** * `tgp_mod_no_aa_window_info_and_eff_seq_len.tar.gz` * `./muc19/windowing/tgp_mod_no_aa/{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` * `./muc19/windowing/tgp_mod_no_aa/{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` * `./muc19/windowing/tgp_mod_no_aa/{742,72}kb_eff_seq_len.txt.gz` ##### `{742,72}kb_nonoverlapping_{invariant,variant}_windows.csv.gz` One file for invariant (`_invariant_`) and one for variant (`_variant_`) per window size (`{742,72}kb`), with the following columns: * `IDX`: Window index with respect to the `CHR` column. * `CHR`: Chromosome. * `START`: Start position (inclusive). * `STOP`: Stop position (inclusive). * `HUM`: Effective sequence length. * `S`: Number of segregating sites. * `QC`: QC condition (numeric, e.g., 1 if true, 0 if false). **Note**: If only column headers are present in the invariant file (`_invariant_`), no invariant windows passed initial QC. ##### `{742,72}kb_esl_qced_nonoverlapping_variant_windows.txt.gz` Indices of variant windows per window size (`{742,72}kb`) of comparable effective sequence length, used for subsetting `{742,72}kb_nonoverlapping_variant_windows.csv.gz`. ##### `{742,72}kb_eff_seq_len.txt.gz` Effective sequence lengths for the focal regions (`{742,72}kb`) with respect to the given archaic individual—singe value per file. #### `sgdp_denisovan_intro_tracts_in_papuans_qc_info.tar.gz` `sgdp_denisovan_intro_tracts_in_papuans_qc_info.tar.gz` is the output from `consolidate_sgdp_denisovan_intro_tracts_in_papuans_v_revisions.py` found [here](https://github.com/David-Peede/MUC19/tree/main/windowing). **Paths** * `sgdp_denisovan_intro_tracts_in_papuans_qc_info.tar.gz` * `./muc19/windowing/sgdp_den_masked_no_aa/{pap_ind}_hap{1,2}_den_intro_{invariant,variant}_tracts.csv.gz` ##### `sgdp_denisovan_intro_tracts_in_papuans_qc_info.tar.gz` For each Papuan individual (`{pap_ind}`), there is one file for invariant (`_invariant_`) and one for variant (`_variant_`) for each haploid genome (`hap{1,2}`), with the following columns: * `IDX`: Denisovan introgressed tract index with respect to the `CHR` column. * `CHR`: Chromosome. * `START`: Start position (inclusive). * `STOP`: Stop position (inclusive). * `DEN`: Effective sequence length for Altai Denisovan comparisons. * `S`: Number of segregating sites. * `QC`: QC condition (numeric, e.g., 1 if true, 0 if false)."}],"geoLocations":[],"fundingReferences":[{"funderIdentifierType":"ROR","funderName":"National Institute of General Medical Sciences","funderIdentifier":"https://ror.org/04q48ey07","awardTitle":"\n        Characterizing modes of natural selection via diverse ancient and modern\n        samples\n      ","awardNumber":"1R35GM128946-01","awardUri":"https://reporter.nih.gov/project-details/9576271"},{"funderIdentifierType":"ROR","funderName":"National Institute of General Medical Sciences","funderIdentifier":"https://ror.org/04q48ey07","awardTitle":"Predoctoral Training Program in Biological Data Science at Brown University","awardNumber":"5T32GM128596-05","awardUri":"https://reporter.nih.gov/project-details/10447019"},{"funderIdentifierType":"ROR","funderName":"National Institute of General Medical Sciences","funderIdentifier":"https://ror.org/04q48ey07","awardNumber":"R35GM142978"},{"funderIdentifierType":"ROR","funderName":"National Institute of Neurological Disorders and Stroke","funderIdentifier":"https://ror.org/01s5ya894","awardNumber":"R01NS122766"},{"funderIdentifierType":"ROR","funderName":"Burroughs Wellcome Fund","funderIdentifier":"https://ror.org/01d35cw23","awardNumber":"Career Award at the Scientific Interface"},{"funderIdentifierType":"ROR","funderName":"Alfred P. Sloan Foundation","funderIdentifier":"https://ror.org/052csg198"},{"funderIdentifierType":"ROR","funderName":"International Human Frontier Science Program Organization","funderIdentifier":"https://ror.org/02ebx7v45"},{"funderIdentifierType":"ROR","funderName":"Leakey Foundation","funderIdentifier":"https://ror.org/018kdpd27"},{"funderIdentifierType":"ROR","funderName":"Blavatnik Family Foundation","funderIdentifier":"https://ror.org/049hmt962"}],"url":"https://datadryad.org/dataset/doi:10.5061/dryad.z612jm6pj","contentUrl":null,"metadataVersion":5,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":47,"downloadCount":16,"referenceCount":0,"citationCount":2,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2025-08-21T16:42:33Z","registered":"2025-08-21T16:42:34Z","published":null,"updated":"2026-11-02T19:42:18Z"},"relationships":{"client":{"data":{"id":"dryad.dryad","type":"clients"}}}},{"id":"10.5061/dryad.0k6djhb89","type":"dois","attributes":{"doi":"10.5061/dryad.0k6djhb89","identifiers":[],"creators":[{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Rodriguez de la Vega, Ricardo","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-9852-6654"}]},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Lucotte, Elise","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["University of Louisville"],"name":"Hayes, Roxanne","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["University of Louisville"],"name":"Baruri, Shikhi","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["University of Louisville"],"name":"Perlin, Michael","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["Amherst College"],"name":"Hood, MIchael","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0003-4379-0711"}]},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Giraud, Tatiana","nameIdentifiers":[]}],"titles":[{"title":"Data from: Repeated loss of function at HD mating-type genes and of recombination suppression without mating-type locus linkage in anther-smut fungi"}],"publisher":"Dryad","container":{},"publicationYear":2025,"subjects":[{"schemeUri":"https://web-archive.oecd.org/2012-06-15/138575-38235147.pdf","subject":"FOS: Biological sciences","subjectScheme":"fos"},{"schemeUri":"https://github.com/PLOS/plos-thesaurus","subject":"Genome evolution","subjectScheme":"PLOS Subject Area Thesaurus"},{"schemeUri":"https://github.com/PLOS/plos-thesaurus","subject":"Bioinformatics","subjectScheme":"PLOS Subject Area Thesaurus"},{"schemeUri":"https://github.com/PLOS/plos-thesaurus","subject":"Fungi","subjectScheme":"PLOS Subject Area Thesaurus"},{"schemeUri":"https://github.com/PLOS/plos-thesaurus","subject":"Sex chromosomes","subjectScheme":"PLOS Subject Area Thesaurus"}],"contributors":[{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Rodriguez de la Vega, Ricardo","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-9852-6654"}],"contributorType":"ContactPerson"},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Lucotte, Elise","contributorType":"ContactPerson","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["University of Louisville"],"name":"Hayes, Roxanne","contributorType":"ContactPerson","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["University of Louisville"],"name":"Baruri, Shikhi","contributorType":"ContactPerson","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["University of Louisville"],"name":"Perlin, Michael","contributorType":"ContactPerson","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["Amherst College"],"name":"Hood, MIchael","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0003-4379-0711"}],"contributorType":"ContactPerson"},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Giraud, Tatiana","contributorType":"ContactPerson","nameIdentifiers":[]}],"dates":[{"date":"2024-05-06T10:46:29Z","dateType":"Created"},{"date":"2025-02-26T04:06:31Z","dateType":"Submitted"},{"date":"2025-03-14T00:00:00Z","dateType":"Issued"},{"date":"2025-03-14T00:00:00Z","dateType":"Available"}],"language":"en","types":{"schemaOrg":"Dataset","resourceTypeGeneral":"Dataset","citeproc":"dataset","bibtex":"misc","ris":"DATA","resourceType":"dataset"},"relatedIdentifiers":[{"relationType":"IsCitedBy","relatedIdentifier":"10.1101/2024.03.03.583181","relatedIdentifierType":"DOI"},{"relationType":"IsCitedBy","relatedIdentifier":"10.1038/s41467-025-60222-5","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["326692813 bytes"],"formats":[],"version":"9","rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/publicdomain/zero/1.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Zero v1.0 Universal","rightsIdentifier":"cc0-1.0"}],"descriptions":[{"descriptionType":"Abstract","description":"A wide diversity of mating systems occur in nature, with frequent\n evolutionary transitions in mating-compatibility mechanisms. Basidiomycete\n fungi typically have two mating-type loci controlling mating\n compatibility, HD and PR, usually residing on different chromosomes. In\n Microbotryum anther-smut fungi, there have been repeated events of linkage\n between the two mating-type loci through chromosome fusions, leading to\n large non-recombining regions. By generating high-quality genome\n assemblies, we found that two sister Microbotryum species parasitizing\n Dianthus plants, M. superbum and M. shykoffianum, as well as the distantly\n related M. scorzonarae, have their HD and PR mating-type loci on different\n chromosomes, but with the PR mating-type chromosome fused with part of the\n ancestral HD chromosome. Furthermore, progressive extensions of\n recombination suppression have generated evolutionary strata. In all three\n species, rearrangements suggest the existence of a transient stage of\n HD-PR linkage by whole chromosome fusion, and, unexpectedly, the HD genes\n lost their function. In M. superbum, multiple natural diploid strains were\n homozygous, and the disrupted HD2 gene was hardly expressed. Mating tests\n confirmed that a single genetic factor controlled mating compatibility\n (i.e. PR) and that haploid strains with identical HD alleles could mate\n and produce infectious hyphae. The HD genes have therefore lost their\n function in the control of mating compatibility in these Microbotryum\n species. While the loss of function of PR genes in mating compatibility\n has been reported in a few basidiomycete fungi, these are the first\n documented cases for the loss of mating-type determination by HD genes in\n heterothallic fungi. The control of mating compatibility by a single\n genetic factor is beneficial under selfing and can thus be achieved\n repeatedly, through evolutionary convergence in distant lineages,\n involving different genomic or similar pathways."},{"descriptionType":"Methods","description":"\u003cstrong\u003eRead mapping and\n quantification\u003c/strong\u003e Reference genome matching\n reads were obtained with bbduk from bbmap [Ref:https://sourceforge.net/projects/bbmap/] with deffault options for quality and adapter trimming. Matching reads were mapped back to the reference genome with STAR 2.7.11a [Ref:https://doi.org/10.1093/bioinformatics/bts635] with the deffault options for paired end reads. Reads with inserts larger than 5 kbp were filtered out. Read counts by transcript feature were obtained with featureCounts from subread 2.0.2 suite [Ref:https://doi.org/10.1093/bioinformatics/btt656].  \u003cstrong\u003eTrans-specific polymorphism\u003c/strong\u003e Gene trees were obtained with IQ-TREE 2.2.6 based on macse v2.05 codon-based alignments. Gene trees were midpoint rooted with gotree [Ref:https://doi.org/10.1093/nargab/lqab075] and subtrees containing the \u003cem\u003eM. shykoffianum\u003c/em\u003e and \u003cem\u003eM. superbum\u003c/em\u003e A1 alleles recovered with nw_clade from Newick utils [Ref: https://doi.org/10.1093/bioinformatics/btq243]. If the subtree contains a single branch connecting only two tips it means that A1 alleles were recovered as monophyletic (i.e. displaying transpecific polymorphism), we repeated the procedure for the A2 alleles and counted the number trees showing full (both alleles recovered as monophyletic clades) or partial (either A1 or A2 were recovered as monophyletic) transpecific polymorphism. Gene trees in which neither A1 nor A2 were recovered as monophyletic were collated as \"Other\" topologies, often following the species phylogeny (i.e. alternative alleles from the same species clustered together, \u003cem\u003eM. superbum\u003c/em\u003e and \u003cem\u003eM. shykoffianum\u003c/em\u003e being recovered as sister clades)."},{"descriptionType":"TechnicalInfo","description":"# Data from: Repeated loss of function at HD mating-type genes and of\n recombination suppression without mating-type locus linkage in anther-smut\n fungi ## Data description This repository includes three types of data\n associated with [Lucotte et al.,\n 2025](https://doi.org/10.1101/2024.03.03.583181). 1. Genome assemblies and\n annotation. 2. RNAseq quantification to explore HD expression. 3. Gene\n trees to explore transpecific polymorphism in non recombining regions. ##\n Files and variables ### FILES #### File: MPbarcode50.fa **Description:**\n Whole genome assembly in fasta format obtained with flye from ONT reads of\n an haploid sample. #### File: Mscorzo-A1\\_renamed.fa **Description:**\n Whole genome assembly in fasta format obtained with canu from ONT reads of\n an haploid sample. #### File: Mscorzo-A2\\_renamed.fa **Description:**\n Whole genome assembly in fasta format obtained with canu from ONT reads of\n an haploid sample. #### File: Mv-cat-C212-A1.fa **Description:** Whole\n genome assembly in fasta format obtained with hifiasm from HiFi reads of a\n diploid sample (haplotype 2). #### File: Mv-cat-C212-A2.fa\n **Description:** Whole genome assembly in fasta format obtained with\n hifiasm from HiFi reads of a diploid sample (haplotype 1). #### File:\n Mv-sup-1065-A1.fa **Description:** Whole genome assembly in fasta format\n obtained with canu from HiFi reads of an haploid sample. #### File:\n Mv-sup-1065-A2.fa **Description:** Whole genome assembly in fasta format\n obtained with canu from HiFi reads of an haploid sample. #### File:\n Mv-lyc-1064\\_impuntedMAT\\_region\\_gene.gtf **Description:** General\n Transfer Format (gtf). Nine columns, tab separated #### File:\n MPbarcode50\\_tsebra.gtf **Description:** General Transfer Format (gtf).\n Nine columns, tab separated #### File:\n featurecounts\\_noLinsert\\_a1a2\\_mated\\_48-1\\_on\\_Mv-lyc-1064-A2\\_A1impMAT\n **Description:** Fractional read mapping per gene feature. Seven columns,\n tab separated. #### File:\n featurecounts\\_noLinsert\\_a1a2\\_mated\\_48-2\\_on\\_Mv-lyc-1064-A2\\_A1impMAT\n **Description:** Fractional read mapping per gene feature. Seven columns,\n tab separated. #### File: featurecounts\\_noLinsert\\_A\\_on\\_MPbarcode50flye\n **Description:** Fractional read mapping per gene feature. Seven columns,\n tab separated. #### File: featurecounts\\_noLinsert\\_B\\_on\\_MPbarcode50flye\n **Description:** Fractional read mapping per gene feature. Seven columns,\n tab separated. #### File: featurecounts\\_noLinsert\\_C\\_on\\_MPbarcode50flye\n **Description:** Fractional read mapping per gene feature. Seven columns,\n tab separated. #### File: gene\\_trees **Description:** Two columns file\n with stratum imputation and gene tree in newick format #### File:\n speciestree.tre **Description:** Newick format ### DATA DESCRIPTION Each\n `*gtf` has nine tab separated columns as follows, see [GFF/GTF\n specification](https://www.ensembl.org/info/website/upload/gff.html) 1.\n **seqname** - name of the chromosome or scaffold; chromosome names can be\n given with or without the 'chr' prefix. 2. **source** - name of\n the program that generated this feature, or the data source (database or\n project name) 3. **feature** - feature type name, e.g. Gene, Variation,\n Similarity 4. **start** - Start position* of the feature, with sequence\n numbering starting at 1. 5. **end** - End position* of the feature, with\n sequence numbering starting at 1. 6. **score** - A floating point value.\n 7. **strand** - defined as + (forward) or - (reverse). 8. **frame** - One\n of '0', '1' or '2'. '0' indicates\n that the first base of the feature is the first base of a codon,\n '1' that the second base is the first base of a codon, and so\n on.. 9. **attribute** - A semicolon-separated list of tag-value pairs,\n providing additional information about each feature. Each `featurecounts*`\n file has seven tab separate columns as follows. Command used is recorded\n in the first row, columns names are defined in the second row and data\n starts at the third row. 1. **Geneid** - Gene/transcript identifier as in\n the **attribute** column of the `gtf` file 2. **Chr** - Assembled\n pseudomolecule identifier as in the **seqname** column of the `gtf` file\n 3. **Start** - Semicolon separated list of CDS features **start**\n positions 4. **End** - Semicolon separated list of CDS features **end**\n positions 5. **Strand** - defined as + (forward) or - (reverse) 6.\n **Length** - Sum length of the CDS features associated to the same\n **Geneid** 7. \\ - Total fractional read counts across the\n feature ## Code/software #### Genome assembly * `Mscorzo-A[12]_renamed.fa\n canu 1.7b` with default parameters on ONT reads * `Mv-cat-C212-A[12].fa\n hifiasm 0.16.1-r375` with default parameters on HiFi reads *\n `Mv-sup-1065-A[12].fa canu 2.2` with `-pacbio-hifi` parameter on HiFi\n reads * `MPbarcode50.fa flye 2.9.4-b1799` with `-g 48.7m -i 3 --nano-raw`\n parameters on ONT reads #### Genome annotation Whole genome shotgun\n assemblies were annotated with Braker2 based on RNAseq or conserved\n proteins evidence and combined with TSEBRA. Genome annotation workflow\n correspond to **Step I** described\n [here](https://github.com/QuentinRougemont/EASYstrata?tab=readme-ov-file#operations-of-step-i-te-and-gene-prediction). #### RNAseq quantification Fractional read counts per transcript feature were summarized with `featureCounts` from `subread` package, based on `STAR 2.7.11a` read alignments. Specific commands are recorded at the first row of each `featurecounts*` file. #### Phylogenetic trees Species (concatenation of monocopy genes alignments) and individual gene trees were obtained with `IQTree2 2.2.6` and processed as described in the methods section of this repository (`gotree` and `newick_utils`). ## Access information Other publicly accessible locations of the data: * Additional custom scripts are available at [https://github.com/eliselucotte/MicrobotryumOnDianthus](https://github.com/eliselucotte/MicrobotryumOnDianthus) * Additional data, including SRA with WGS and RNAseq reads, can be found at GenBank associated to BioProjects [PRJNA1169769](https://www.ncbi.nlm.nih.gov/bioproject/1169769), [PRJNA1206992](https://www.ncbi.nlm.nih.gov/bioproject/1206992) and [PRJNA1206994](https://www.ncbi.nlm.nih.gov/bioproject/1206994) Data was derived from the following sources: * Previously obtained RNAseq data is available at BioProject [PRJNA246470](https://www.ncbi.nlm.nih.gov/bioproject/246470)"}],"geoLocations":[],"fundingReferences":[{"funderIdentifierType":"ROR","funderName":"European Research Council","funderIdentifier":"https://ror.org/0472cxd90","awardNumber":"832352"},{"funderIdentifierType":"ROR","funderName":"Division of Integrative Organismal Systems","funderIdentifier":"https://ror.org/01rvays47","awardTitle":"\n        Functional characterization of effectors of the Microbotryum complex of\n        fungal phytopathogens\n      ","awardNumber":"2007449"},{"funderIdentifierType":"ROR","funderName":"Division of Integrative Organismal Systems","funderIdentifier":"https://ror.org/01rvays47","awardTitle":"\n        OSIB:Mechanisms determining spatial and temporal dynamics of infectious\n        processes for Microbotryum complex phytopathogenic fungi and host\n        immunity\n      ","awardNumber":"2419465"},{"funderIdentifierType":"ROR","funderName":"National Institute of General Medical Sciences","funderIdentifier":"https://ror.org/04q48ey07","awardTitle":"Mating Compatibility and Degeneration of Non-Recombining Chromosomes","awardNumber":"1R15GM119092-01A1","awardUri":"https://reporter.nih.gov/project-details/9232348"}],"url":"https://datadryad.org/dataset/doi:10.5061/dryad.0k6djhb89","contentUrl":null,"metadataVersion":4,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":53,"downloadCount":4,"referenceCount":0,"citationCount":2,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2025-03-14T05:36:53Z","registered":"2025-03-14T05:36:54Z","published":null,"updated":"2026-11-02T18:52:29Z"},"relationships":{"client":{"data":{"id":"dryad.dryad","type":"clients"}}}},{"id":"10.5061/dryad.pnvx0k6ps","type":"dois","attributes":{"doi":"10.5061/dryad.pnvx0k6ps","identifiers":[],"creators":[{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Rodriguez de la Vega, Ricardo","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-9852-6654"}]},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Carpentier, Fantin","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Jay, Paul","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Duhamel, Marine","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Shykoff, Jacqui A.","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["University of Louisville"],"name":"Perlin, Michael H.","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["University of Louisville"],"name":"Wallen, R. Margaret","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["Amherst College"],"name":"Hood, Michael E.","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Giraud, Tatiana","nameIdentifiers":[]}],"titles":[{"title":"Data from: Tempo of degeneration across independently evolved nonrecombining regions"}],"publisher":"Dryad","container":{},"publicationYear":2025,"subjects":[{"schemeUri":"https://github.com/PLOS/plos-thesaurus","subject":"Genome evolution","subjectScheme":"PLOS Subject Area Thesaurus"},{"schemeUri":"https://github.com/PLOS/plos-thesaurus","subject":"Bioinformatics","subjectScheme":"PLOS Subject Area Thesaurus"},{"schemeUri":"https://web-archive.oecd.org/2012-06-15/138575-38235147.pdf","subject":"FOS: Biological sciences","subjectScheme":"fos"},{"subject":"genomic degeneration"},{"subject":"recombination suppression"}],"contributors":[{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Rodriguez de la Vega, Ricardo","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-9852-6654"}],"contributorType":"ContactPerson"},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"name":"Carpentier, Fantin","contributorType":"ContactPerson","nameIdentifiers":[]}],"dates":[{"date":"2025-01-17T10:13:30Z","dateType":"Created"},{"date":"2025-01-17T10:13:39Z","dateType":"Submitted"},{"date":"2025-02-27T00:00:00Z","dateType":"Issued"},{"date":"2025-02-27T00:00:00Z","dateType":"Available"}],"language":"en","types":{"schemaOrg":"Dataset","resourceTypeGeneral":"Dataset","citeproc":"dataset","bibtex":"misc","ris":"DATA","resourceType":"dataset"},"relatedIdentifiers":[{"relationType":"IsCitedBy","relatedIdentifier":"10.1101/2021.07.20.453045","relatedIdentifierType":"DOI"},{"relationType":"IsCitedBy","relatedIdentifier":"10.1093/molbev/msac060","relatedIdentifierType":"DOI"},{"relationType":"IsDerivedFrom","relatedIdentifier":"https://zenodo.org/records/6334670","relatedIdentifierType":"URL"}],"relatedItems":[],"sizes":["13553962 bytes"],"formats":[],"version":"5","rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/publicdomain/zero/1.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Zero v1.0 Universal","rightsIdentifier":"cc0-1.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Recombination is beneficial over the long term, allowing more effective\n selection. Despite long-term advantages of recombination, local\n recombination suppression can evolve and lead to genomic degeneration, in\n particular on sex chromosomes. Here, we investigated the tempo of\n degeneration in nonrecombining regions, that is, the function curve for\n the accumulation of deleterious mutations over time, leveraging on 22\n independent events of recombination suppression identified on mating-type\n chromosomes of anther-smut fungi, including newly identified ones. Using\n previously available and newly generated high-quality genome assemblies of\n alternative mating types of 13 Microbotryum species, we estimated\n degeneration levels in terms of accumulation of nonoptimal codons and\n nonsynonymous substitutions in nonrecombining regions. We found a reduced\n frequency of optimal codons in the nonrecombining regions compared with\n autosomes, which was not due to less frequent GC-biased gene conversion or\n lower ancestral expression levels compared with recombining regions. The\n frequency of optimal codons rapidly decreased following recombination\n suppression and reached an asymptote after ca. 3 Ma. The strength of\n purifying selection remained virtually constant at dN/dS = 0.55, that is,\n at an intermediate level between purifying selection and neutral\n evolution. Accordingly, nonsynonymous differences between mating-type\n chromosomes increased linearly with stratum age, at a rate of 0.015 per\n My. We thus develop a method for disentangling the effects of reduced\n selection efficacy from GC-biased gene conversion in the evolution of\n codon usage and we quantify the tempo of degeneration in nonrecombining\n regions, which is important for our knowledge of genomic evolution and the\n maintenance of regions without recombination."},{"descriptionType":"Methods","description":"\u003cstrong\u003eCodon usage\u003c/strong\u003e\n Optimal codons where identified as the most often used synonymous\n codon among the 10% most highly expressed genes in two\n \u003cem\u003eMicrobotryum\u003c/em\u003e species grown in two conditions. The\n most highly expressed genes correspond to the genes with the lowest PC1\n coordinates in a within-group correspondence analysis (WCA, see http://pbil.univ-lyon1.fr/datasets/charif04/). Input data were the best TPM (from kallisto pseudo alignmet of trimmed paired-end reads on \u003cem\u003eM. intermedium\u003c/em\u003e) per gene. We checked that expression was highly correlated between single-copy orthologous genes of \u003cem\u003eMicrobotryum intermedium\u003c/em\u003e and \u003cem\u003eM. lychnidis-dioicae\u003c/em\u003e. \u003cstrong\u003eMolecular dating\u003c/strong\u003e Single-copy genes were assigned to genome compartments based on orthology with genes in \u003cem\u003eM. lagerheimi\u003c/em\u003e and rearrangement scenarios. Concatenated codon-based alignments (obtained per orthologous group with macse v2.04) were imported into beauti to generate beast2's XML input files. We estimated the species and genome compartment divergence times under a calibrated Yule model and a HKY substitution model (kappa = 2, estimated frequencies) with 10,000,000 or 20,000,000 mcmc generations in beast v2.5.0. We used three unlinked site models (one per codon position). The clock model and tree parameters were kept linked. We used the split of \u003cem\u003eM. lychnidis-dioicae\u003c/em\u003e and \u003cem\u003eM. silenes-dioicae\u003c/em\u003e as a calibration point, with a normal prior with a mean of 0.42 Ma and sigma of 0.04."},{"descriptionType":"Other","description":"\u003cstrong\u003eExternal software used\u003c/strong\u003e\n Beast v2.5.0\n https://github.com/CompEvol/beast2/releases R\n 3.6.3 \u003cem\u003eR packages and\n libraries\u003c/em\u003e\n ade4\u003cbr\u003eape\u003cbr\u003ecar\u003cbr\u003ecowplot\u003cbr\u003edplyr\u003cbr\u003eggplot2\u003cbr\u003eggpubr\u003cbr\u003egrid\u003cbr\u003einteractions\u003cbr\u003eplyr\u003cbr\u003epscl\u003cbr\u003ereshape2\u003cbr\u003eseqinr\u003cbr\u003esjmisc\u003cbr\u003esjPlot\u003cbr\u003etidyr"},{"descriptionType":"TechnicalInfo","description":"# Tempo of Degeneration Across Independently Evolved Nonrecombining\n Regions\n [https://doi.org/10.5061/dryad.pnvx0k6ps](https://doi.org/10.5061/dryad.pnvx0k6ps) This repo pertains to the analysis of optimal codon usage in non-recombining regions of fungal mating type chromosomes ## Description of the data and file structure All associated data is described in [https://doi.org/10.1093/molbev/msac060](https://doi.org/10.1093/molbev/msac060) The file `dS_dN_FOP_FINAL.txt` contains per gene tabular data with synonymous substitutions per synonymous site, non-synonymous substitutions per non-synonymous site (yn00) and fraction of optimal codons obtained with scripts available at https://zenodo.org/records/6334670 (using transcripts per million of mapped reads per gene). ## Sharing/Access information Data was derived from the following sources: * [https://www.ncbi.nlm.nih.gov/bioproject/PRJNA747176](https://www.ncbi.nlm.nih.gov/bioproject/PRJNA747176) * [https://www.ncbi.nlm.nih.gov/bioproject/PRJNA246470](https://www.ncbi.nlm.nih.gov/bioproject/PRJNA246470) ## Code/Software See Usage Note for external software and package versions. See accompanying scripts for Tempo of degeneration across independently evolved non-recombining regions available at [https://zenodo.org/records/6334670](https://zenodo.org/records/6334670)"}],"geoLocations":[],"fundingReferences":[{"funderIdentifierType":"ROR","funderName":"European Research Council","funderIdentifier":"https://ror.org/0472cxd90","awardNumber":"832352"},{"funderIdentifierType":"ROR","funderName":"National Cancer Institute","funderIdentifier":"https://ror.org/040gcmg81","awardNumber":"RR15GM119092"},{"funderIdentifierType":"ROR","funderName":"Office of International Science and Engineering","funderIdentifier":"https://ror.org/01k638r21","awardTitle":"Track I IRES Sites: Training with Smut Fungi in Germany","awardNumber":"1824851"},{"funderIdentifierType":"ROR","funderName":"National Institutes of Health","funderIdentifier":"https://ror.org/01cwqze88","awardNumber":"R15GM119092"},{"funderName":"EvolSexChrom","awardNumber":"832352"}],"url":"https://datadryad.org/dataset/doi:10.5061/dryad.pnvx0k6ps","contentUrl":null,"metadataVersion":3,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":30,"downloadCount":4,"referenceCount":0,"citationCount":2,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2025-02-27T07:03:07Z","registered":"2025-02-27T07:03:08Z","published":null,"updated":"2026-11-02T18:52:18Z"},"relationships":{"client":{"data":{"id":"dryad.dryad","type":"clients"}}}},{"id":"10.5281/zenodo.14507773","type":"dois","attributes":{"doi":"10.5281/zenodo.14507773","identifiers":[{"identifier":"oai:zenodo.org:14507773","identifierType":"oai"}],"creators":[{"nameType":"Personal","affiliation":["Laboratoire Méthodes Formelles","Institut national de recherche en sciences et technologies du numérique","Université Paris-Saclay"],"givenName":"Diane","familyName":"Golfouse","name":"Golfouse, Diane","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["Laboratoire Méthodes Formelles","Institut national de recherche en sciences et technologies du numérique","Université Paris-Saclay"],"givenName":"Paul","familyName":"Patault","name":"Patault, Paul","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["ETH Zurich"],"givenName":"Xavier","familyName":"Denis","name":"Denis, Xavier","nameIdentifiers":[]}],"titles":[{"title":"Exemples pour \"Remonter les barrières pour ouvrir une clôture\", JFLA 2025"}],"publisher":"Zenodo","container":{},"publicationYear":2024,"subjects":[{"subject":"Computer and information sciences","subjectScheme":"EuroSciVoc"}],"contributors":[],"dates":[{"date":"2024-12-17","dateType":"Issued"}],"language":"fr","types":{"schemaOrg":"SoftwareSourceCode","resourceTypeGeneral":"Software","citeproc":"article","bibtex":"misc","ris":"COMP","resourceType":""},"relatedIdentifiers":[{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.13941844","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":null,"rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"First install creusot using the closure-inference branch.\n\nThen run the following commands.$ ./mlcfg file.rs$ ./ide   generated_file.coma"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.14507773","contentUrl":null,"metadataVersion":1,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":1,"created":"2024-12-17T14:21:30Z","registered":"2024-12-17T14:21:30Z","published":null,"updated":"2026-11-02T10:40:00Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.13941844","type":"dois","attributes":{"doi":"10.5281/zenodo.13941844","identifiers":[],"creators":[{"nameType":"Personal","affiliation":["Laboratoire Méthodes Formelles","Institut national de recherche en sciences et technologies du numérique","Université Paris-Saclay"],"givenName":"Diane","familyName":"Golfouse","name":"Golfouse, Diane","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["Laboratoire Méthodes Formelles","Institut national de recherche en sciences et technologies du numérique","Université Paris-Saclay"],"givenName":"Paul","familyName":"Patault","name":"Patault, Paul","nameIdentifiers":[]},{"nameType":"Personal","affiliation":["ETH Zurich"],"givenName":"Xavier","familyName":"Denis","name":"Denis, Xavier","nameIdentifiers":[]}],"titles":[{"title":"Exemples pour \"Remonter les barrières pour ouvrir une clôture\", JFLA 2025"}],"publisher":"Zenodo","container":{},"publicationYear":2024,"subjects":[{"subject":"Computer and information sciences","subjectScheme":"EuroSciVoc"}],"contributors":[],"dates":[{"date":"2024-12-17","dateType":"Issued"}],"language":"fr","types":{"schemaOrg":"SoftwareSourceCode","resourceTypeGeneral":"Software","citeproc":"article","bibtex":"misc","ris":"COMP","resourceType":""},"relatedIdentifiers":[{"relationType":"HasVersion","relatedIdentifier":"10.5281/zenodo.14265319","relatedIdentifierType":"DOI"},{"relationType":"HasVersion","relatedIdentifier":"10.5281/zenodo.14505617","relatedIdentifierType":"DOI"},{"relationType":"HasVersion","relatedIdentifier":"10.5281/zenodo.13941845","relatedIdentifierType":"DOI"},{"relationType":"HasVersion","relatedIdentifier":"10.5281/zenodo.14507773","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":null,"rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"First install creusot using the closure-inference branch.\n\nThen run the following commands.$ ./mlcfg file.rs$ ./ide   generated_file.coma"}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.13941844","contentUrl":null,"metadataVersion":7,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":4,"versionOfCount":0,"created":"2024-10-16T17:17:03Z","registered":"2024-10-16T17:17:04Z","published":null,"updated":"2026-11-02T10:40:00Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.17632/r9pdnnn76t.1","type":"dois","attributes":{"doi":"10.17632/r9pdnnn76t.1","identifiers":[],"creators":[{"nameType":"Personal","givenName":"Jakub","familyName":"Chrobak","name":"Chrobak, Jakub","affiliation":[],"nameIdentifiers":[]},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"givenName":"Graciela","familyName":"Alvarez","name":"Alvarez, Graciela","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-0667-9128"}]},{"nameType":"Personal","affiliation":["Silesian University of Technology"],"givenName":"Michal","familyName":"Palacz","name":"Palacz, Michal","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-7222-6303"}]},{"nameType":"Personal","affiliation":["Silesian University of Technology"],"givenName":"Jacek","familyName":"Smolka","name":"Smolka, Jacek","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0001-5502-2686"}]},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"givenName":"Fatou-Toutie","familyName":"Ndoye","name":"Ndoye, Fatou-Toutie","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0003-3553-8399"}]}],"titles":[{"title":"Experimental data of the impact of the freezing method on the microstructure of the freeze-dried food products"}],"publisher":"Mendeley Data","container":{},"publicationYear":2026,"subjects":[{"subject":"Food Analysis"},{"subject":"Microstructure"},{"subject":"Freeze-Drying"},{"subject":"Freezing (Food Preservation)"},{"subject":"Vacuum Evaporation"}],"contributors":[{"nameType":"Organizational","name":"Silesian University of Technology","nameIdentifiers":[{"nameIdentifierScheme":"ROR","schemeUri":"https://ror.org","nameIdentifier":"https://ror.org/02dyjk442"}],"contributorType":"Other","affiliation":[]},{"nameType":"Organizational","name":"Université Paris-Saclay","nameIdentifiers":[{"nameIdentifierScheme":"ROR","schemeUri":"https://ror.org","nameIdentifier":"https://ror.org/03xjwb503"}],"contributorType":"Other","affiliation":[]}],"dates":[{"date":"2026-11-01T15:29:30Z","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"Dataset","resourceTypeGeneral":"Dataset","citeproc":"dataset","bibtex":"misc","ris":"DATA","resourceType":"Dataset"},"relatedIdentifiers":[{"relationType":"IsVersionOf","resourceTypeGeneral":"Dataset","relatedIdentifier":"10.17632/r9pdnnn76t","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":null,"rightsList":[{"rightsUri":"info:eu-repo/semantics/openAccess"},{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"This study examines how the pre-freezing method affects the microstructure of freeze-dried food products. Cylindrical potato and apple samples were pre-frozen either by convective freezing or vacuum freezing and then identically freeze-dried. High-resolution X-ray micro-computed tomography with a voxel size of 6.17 μm quantified air volume fraction, pore diameter distributions, sphericity and tortuosity. Segmentation consisted of image smoothing, artefacts removal, image binarisation, object separation and labelling. A one-way analysis of variance (𝛼 = 0.05) assessed the effect of pre-freezing within each product. Apples exhibited higher air fractions than potatoes (0.78 versus 0.75), and also a greater share of mid-range pores but lower sphericity (0.11 versus 0.28), consistent with the intrinsic tissue architecture differences. Between convective and vacuum freezing of the same samples, the group means did not differ significantly for any property, except sphericity for apples. Thus, under the conditions studied, product type dominated pore formation, while the pre-freezing method induced only minor, non-significant changes. Nevertheless, the trends observed under vacuum freezing imply prospective advantages for mass-transfer efficiency and rehydration behaviour that merit further exploration. These findings support a view in which freezing sets the pore network later conserved by sublimation.\n\nThe data shows the results obtained from the Avizo software from images obtained by micro-ct scanner."}],"geoLocations":[],"fundingReferences":[{"funderIdentifierType":"ROR","funderName":"European Commission","funderIdentifier":"https://ror.org/00k4n6c32"},{"funderIdentifierType":"ROR","funderName":"National Science Centre","funderIdentifier":"https://ror.org/03ha2q922"}],"url":"https://data.mendeley.com/datasets/r9pdnnn76t/1","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":1,"created":"2026-11-01T15:29:32Z","registered":"2026-11-01T15:29:33Z","published":null,"updated":"2026-11-01T15:29:33Z"},"relationships":{"client":{"data":{"id":"bl.mendeley","type":"clients"}}}},{"id":"10.17632/r9pdnnn76t","type":"dois","attributes":{"doi":"10.17632/r9pdnnn76t","identifiers":[],"creators":[{"nameType":"Personal","givenName":"Jakub","familyName":"Chrobak","name":"Chrobak, Jakub","affiliation":[],"nameIdentifiers":[]},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"givenName":"Graciela","familyName":"Alvarez","name":"Alvarez, Graciela","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-0667-9128"}]},{"nameType":"Personal","affiliation":["Silesian University of Technology"],"givenName":"Michal","familyName":"Palacz","name":"Palacz, Michal","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0002-7222-6303"}]},{"nameType":"Personal","affiliation":["Silesian University of Technology"],"givenName":"Jacek","familyName":"Smolka","name":"Smolka, Jacek","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0001-5502-2686"}]},{"nameType":"Personal","affiliation":["Université Paris-Saclay"],"givenName":"Fatou-Toutie","familyName":"Ndoye","name":"Ndoye, Fatou-Toutie","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","schemeUri":"https://orcid.org","nameIdentifier":"https://orcid.org/0000-0003-3553-8399"}]}],"titles":[{"title":"Experimental data of the impact of the freezing method on the microstructure of the freeze-dried food products"}],"publisher":"Mendeley Data","container":{},"publicationYear":2026,"subjects":[{"subject":"Food Analysis"},{"subject":"Microstructure"},{"subject":"Freeze-Drying"},{"subject":"Freezing (Food Preservation)"},{"subject":"Vacuum Evaporation"}],"contributors":[{"nameType":"Organizational","name":"Silesian University of Technology","nameIdentifiers":[{"nameIdentifierScheme":"ROR","schemeUri":"https://ror.org","nameIdentifier":"https://ror.org/02dyjk442"}],"contributorType":"Other","affiliation":[]},{"nameType":"Organizational","name":"Université Paris-Saclay","nameIdentifiers":[{"nameIdentifierScheme":"ROR","schemeUri":"https://ror.org","nameIdentifier":"https://ror.org/03xjwb503"}],"contributorType":"Other","affiliation":[]}],"dates":[{"date":"2026-11-01T15:29:30Z","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"Dataset","resourceTypeGeneral":"Dataset","citeproc":"dataset","bibtex":"misc","ris":"DATA","resourceType":"Dataset"},"relatedIdentifiers":[{"relationType":"HasVersion","resourceTypeGeneral":"Dataset","relatedIdentifier":"10.17632/r9pdnnn76t.1","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":null,"rightsList":[{"rightsUri":"info:eu-repo/semantics/openAccess"},{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"This study examines how the pre-freezing method affects the microstructure of freeze-dried food products. Cylindrical potato and apple samples were pre-frozen either by convective freezing or vacuum freezing and then identically freeze-dried. High-resolution X-ray micro-computed tomography with a voxel size of 6.17 μm quantified air volume fraction, pore diameter distributions, sphericity and tortuosity. Segmentation consisted of image smoothing, artefacts removal, image binarisation, object separation and labelling. A one-way analysis of variance (𝛼 = 0.05) assessed the effect of pre-freezing within each product. Apples exhibited higher air fractions than potatoes (0.78 versus 0.75), and also a greater share of mid-range pores but lower sphericity (0.11 versus 0.28), consistent with the intrinsic tissue architecture differences. Between convective and vacuum freezing of the same samples, the group means did not differ significantly for any property, except sphericity for apples. Thus, under the conditions studied, product type dominated pore formation, while the pre-freezing method induced only minor, non-significant changes. Nevertheless, the trends observed under vacuum freezing imply prospective advantages for mass-transfer efficiency and rehydration behaviour that merit further exploration. These findings support a view in which freezing sets the pore network later conserved by sublimation.\n\nThe data shows the results obtained from the Avizo software from images obtained by micro-ct scanner."}],"geoLocations":[],"fundingReferences":[{"funderIdentifierType":"ROR","funderName":"European Commission","funderIdentifier":"https://ror.org/00k4n6c32"},{"funderIdentifierType":"ROR","funderName":"National Science Centre","funderIdentifier":"https://ror.org/03ha2q922"}],"url":"https://data.mendeley.com/datasets/r9pdnnn76t","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":1,"versionOfCount":0,"created":"2026-11-01T15:29:31Z","registered":"2026-11-01T15:29:31Z","published":null,"updated":"2026-11-01T15:29:31Z"},"relationships":{"client":{"data":{"id":"bl.mendeley","type":"clients"}}}},{"id":"10.5281/zenodo.23857120","type":"dois","attributes":{"doi":"10.5281/zenodo.23857120","identifiers":[{"identifier":"oai:zenodo.org:23857120","identifierType":"oai"},{"identifier":"\"Fundamental Neutrino Science at Chooz (CLOUD experiment and Beyond)\" [conference original title]","identifierType":"Other"}],"creators":[{"nameType":"Personal","affiliation":["Centre National de la Recherche Scientifique","Université Paris-Saclay"],"givenName":"Anatael","familyName":"CABRERA SERRA","name":"CABRERA SERRA, Anatael","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","nameIdentifier":"0000-0001-5713-3347"}]}],"titles":[{"title":"CLOUD-II — Demonstrating SuperChooz \u0026 HORUS"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"LiquidO"},{"subject":"CLOUD"},{"subject":"SuperChooz"},{"subject":"HORUS"},{"subject":"neutrino"},{"subject":"antineutrino"},{"subject":"reactor"},{"subject":"solar"}],"contributors":[],"dates":[{"date":"2026-11-01","dateType":"Issued"},{"date":"2026-10-29","dateType":"Copyrighted","dateInformation":"Talk delivered at the NNN-2026 Conference (Seoul, South Korea)"}],"language":"en","types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"Text","citeproc":"article-journal","bibtex":"article","ris":"RPRT","resourceType":"Presentation"},"relatedIdentifiers":[{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.23754599","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":null,"rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"The Double Chooz experiment delivered some of the most precise reactor-antineutrino measurements to date. With its legacy established and backgrounds well characterised, the Chooz underground site — powered by two N4-generation PWR cores — remains one of Europe’s most compelling facilities for reactor-antineutrino physics. Two new programmes, both built on the LiquidO detection paradigm — the deliberate use of opaque scintillating media for event-by-event topology imaging — are now charting the site’s third generation.\n\nThe first is the CLOUD experiment, which inherits from the reactor-based, funded AntiMatterOTech programme (EIC Pathfinder) and is under construction in three experimental phases. Sited in the Ultra-Near-Detector position (~35 m from the reactor core), CLOUD will deploy LiquidO technology at the neutrino-physics scale for the first time, validating positron tagging and heavy-target loading capabilities unique to opaque scintillators. The expected rate of tens of thousands of antineutrinos per day enables a dedicated scientific programme alongside the technology demonstration, including sensitivity to spent-fuel antineutrinos relevant to nuclear safeguards.\n\nThe second strand comprises SuperChooz (introduced in 2022) and HORUS (presented here for the first time). SuperChooz, located at Chooz and reusing the former Chooz-A power reactor cavern (1967–1991; first PWR in France), targets per-mille precision on θ₁₃ and, simultaneously, real-time solar-neutrino spectroscopy — including, for the first time, pp neutrinos via charged-current interactions on indium-loaded opaque scintillator, directly sensitive to vacuum θ₁₂. HORUS scales the solar channel to a dedicated observatory class, repurposing the former CEPSA/MOEVE refinery tank infrastructure in Tenerife (Canary Islands, Spain; 1930–2022). Both exploration programmes pioneer a sustainability-driven paradigm for large-scale scientific infrastructure, enabled by the intrinsic simplicity and industrial compatibility of the LiquidO detection technology.\n\nThis talk presents the physics case, detector concepts, and the status of both the CLOUD demonstration programme — with an emphasis on CLOUD phase II — and, briefly, highlights the rationale for the prospective SuperChooz and HORUS."}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.23857120","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":1,"created":"2026-11-01T11:48:35Z","registered":"2026-11-01T11:48:35Z","published":null,"updated":"2026-11-01T11:48:35Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.5281/zenodo.23754599","type":"dois","attributes":{"doi":"10.5281/zenodo.23754599","identifiers":[{"identifier":"\"Fundamental Neutrino Science at Chooz (CLOUD experiment and Beyond)\" [conference original title]","identifierType":"Other"}],"creators":[{"nameType":"Personal","affiliation":["Centre National de la Recherche Scientifique","Université Paris-Saclay"],"givenName":"Anatael","familyName":"CABRERA SERRA","name":"CABRERA SERRA, Anatael","nameIdentifiers":[{"nameIdentifierScheme":"ORCID","nameIdentifier":"0000-0001-5713-3347"}]}],"titles":[{"title":"CLOUD-II — Demonstrating SuperChooz \u0026 HORUS"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"LiquidO"},{"subject":"CLOUD"},{"subject":"SuperChooz"},{"subject":"HORUS"},{"subject":"neutrino"},{"subject":"antineutrino"},{"subject":"reactor"},{"subject":"solar"}],"contributors":[],"dates":[{"date":"2026-11-01","dateType":"Issued"},{"date":"2026-10-29","dateType":"Copyrighted","dateInformation":"Talk delivered at the NNN-2026 Conference (Seoul, South Korea)"}],"language":"en","types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"Text","citeproc":"article-journal","bibtex":"article","ris":"RPRT","resourceType":"Presentation"},"relatedIdentifiers":[{"relationType":"HasVersion","relatedIdentifier":"10.5281/zenodo.23857120","relatedIdentifierType":"DOI"},{"relationType":"HasVersion","relatedIdentifier":"10.5281/zenodo.23754600","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":null,"rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"The Double Chooz experiment delivered some of the most precise reactor-antineutrino measurements to date. With its legacy established and backgrounds well characterised, the Chooz underground site — powered by two N4-generation PWR cores — remains one of Europe’s most compelling facilities for reactor-antineutrino physics. Two new programmes, both built on the LiquidO detection paradigm — the deliberate use of opaque scintillating media for event-by-event topology imaging — are now charting the site’s third generation.\n\nThe first is the CLOUD experiment, which inherits from the reactor-based, funded AntiMatterOTech programme (EIC Pathfinder) and is under construction in three experimental phases. Sited in the Ultra-Near-Detector position (~35 m from the reactor core), CLOUD will deploy LiquidO technology at the neutrino-physics scale for the first time, validating positron tagging and heavy-target loading capabilities unique to opaque scintillators. The expected rate of tens of thousands of antineutrinos per day enables a dedicated scientific programme alongside the technology demonstration, including sensitivity to spent-fuel antineutrinos relevant to nuclear safeguards.\n\nThe second strand comprises SuperChooz (introduced in 2022) and HORUS (presented here for the first time). SuperChooz, located at Chooz and reusing the former Chooz-A power reactor cavern (1967–1991; first PWR in France), targets per-mille precision on θ₁₃ and, simultaneously, real-time solar-neutrino spectroscopy — including, for the first time, pp neutrinos via charged-current interactions on indium-loaded opaque scintillator, directly sensitive to vacuum θ₁₂. HORUS scales the solar channel to a dedicated observatory class, repurposing the former CEPSA/MOEVE refinery tank infrastructure in Tenerife (Canary Islands, Spain; 1930–2022). Both exploration programmes pioneer a sustainability-driven paradigm for large-scale scientific infrastructure, enabled by the intrinsic simplicity and industrial compatibility of the LiquidO detection technology.\n\nThis talk presents the physics case, detector concepts, and the status of both the CLOUD demonstration programme — with an emphasis on CLOUD phase II — and, briefly, highlights the rationale for the prospective SuperChooz and HORUS."}],"geoLocations":[],"fundingReferences":[],"url":"https://zenodo.org/doi/10.5281/zenodo.23754599","contentUrl":null,"metadataVersion":1,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":0,"partCount":0,"partOfCount":0,"versionCount":2,"versionOfCount":0,"created":"2026-10-30T00:55:40Z","registered":"2026-10-30T00:55:40Z","published":null,"updated":"2026-11-01T11:48:35Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873324.v1","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873324.v1","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 10 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"10.6084/m9.figshare.34873324","relatedIdentifierType":"DOI"},{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["242703 Bytes"],"formats":[],"version":"1","rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 10"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_10_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873324/1","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:50Z","registered":"2026-10-31T04:25:51Z","published":null,"updated":"2026-10-31T04:25:59Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873327.v1","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873327.v1","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 11 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"10.6084/m9.figshare.34873327","relatedIdentifierType":"DOI"},{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["166756 Bytes"],"formats":[],"version":"1","rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 11"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_11_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873327/1","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:52Z","registered":"2026-10-31T04:25:54Z","published":null,"updated":"2026-10-31T04:25:59Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873327","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873327","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 11 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["166756 Bytes"],"formats":[],"version":null,"rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 11"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_11_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873327","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:52Z","registered":"2026-10-31T04:25:54Z","published":null,"updated":"2026-10-31T04:25:59Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873324","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873324","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 10 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["242703 Bytes"],"formats":[],"version":null,"rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 10"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_10_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873324","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:50Z","registered":"2026-10-31T04:25:51Z","published":null,"updated":"2026-10-31T04:25:58Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873312.v1","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873312.v1","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 6 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"10.6084/m9.figshare.34873312","relatedIdentifierType":"DOI"},{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["158702 Bytes"],"formats":[],"version":"1","rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 6"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_6_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873312/1","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:49Z","registered":"2026-10-31T04:25:50Z","published":null,"updated":"2026-10-31T04:25:57Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873318.v1","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873318.v1","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 8 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"10.6084/m9.figshare.34873318","relatedIdentifierType":"DOI"},{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["152601 Bytes"],"formats":[],"version":"1","rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 8"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_8_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873318/1","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:50Z","registered":"2026-10-31T04:25:51Z","published":null,"updated":"2026-10-31T04:25:57Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873312","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873312","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 6 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["158702 Bytes"],"formats":[],"version":null,"rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 6"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_6_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873312","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:49Z","registered":"2026-10-31T04:25:50Z","published":null,"updated":"2026-10-31T04:25:57Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873321","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873321","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 9 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["170341 Bytes"],"formats":[],"version":null,"rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 9"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_9_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873321","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:50Z","registered":"2026-10-31T04:25:51Z","published":null,"updated":"2026-10-31T04:25:57Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873315","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873315","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 7 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["151653 Bytes"],"formats":[],"version":null,"rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 7"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_7_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873315","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:49Z","registered":"2026-10-31T04:25:51Z","published":null,"updated":"2026-10-31T04:25:57Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873318","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873318","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 8 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["152601 Bytes"],"formats":[],"version":null,"rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 8"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_8_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873318","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:50Z","registered":"2026-10-31T04:25:51Z","published":null,"updated":"2026-10-31T04:25:57Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873321.v1","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873321.v1","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 9 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"10.6084/m9.figshare.34873321","relatedIdentifierType":"DOI"},{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["170341 Bytes"],"formats":[],"version":"1","rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 9"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_9_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873321/1","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:50Z","registered":"2026-10-31T04:25:51Z","published":null,"updated":"2026-10-31T04:25:57Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873315.v1","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873315.v1","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 7 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"10.6084/m9.figshare.34873315","relatedIdentifierType":"DOI"},{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["151653 Bytes"],"formats":[],"version":"1","rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 7"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_7_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873315/1","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:49Z","registered":"2026-10-31T04:25:51Z","published":null,"updated":"2026-10-31T04:25:57Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873309","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873309","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 5 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["159731 Bytes"],"formats":[],"version":null,"rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 5"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_5_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873309","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:46Z","registered":"2026-10-31T04:25:48Z","published":null,"updated":"2026-10-31T04:25:56Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873309.v1","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873309.v1","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 5 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"10.6084/m9.figshare.34873309","relatedIdentifierType":"DOI"},{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["159731 Bytes"],"formats":[],"version":"1","rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 5"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_5_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873309/1","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:47Z","registered":"2026-10-31T04:25:48Z","published":null,"updated":"2026-10-31T04:25:56Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873306","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873306","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 4 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["161722 Bytes"],"formats":[],"version":null,"rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 4"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_4_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873306","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:46Z","registered":"2026-10-31T04:25:47Z","published":null,"updated":"2026-10-31T04:25:55Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}},{"id":"10.6084/m9.figshare.34873306.v1","type":"dois","attributes":{"doi":"10.6084/m9.figshare.34873306.v1","identifiers":[],"creators":[{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Michiel","familyName":"Van Niekerk","name":"Michiel Van Niekerk","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Frederick W. C.","familyName":"Neser","name":"Frederick W. C. Neser","nameIdentifiers":[]},{"affiliation":["University of the Free State"],"givenName":"Jacobus B.","familyName":"Van Wyk","name":"Jacobus B. Van Wyk","nameIdentifiers":[]},{"affiliation":["University of the Free State","University of Paris-Saclay"],"givenName":"Vincent","familyName":"Ducrocq","name":"Vincent Ducrocq","nameIdentifiers":[]}],"titles":[{"title":"Additional file 4 of Genotype by environment interaction under two production systems utilizing a random regression model for milk production traits in multiparous South African Holstein dairy cattle"}],"publisher":"figshare","container":{},"publicationYear":2026,"subjects":[{"subject":"Genetics"}],"contributors":[],"dates":[{"date":"2026-10-31","dateType":"Created"},{"date":"2026-10-31","dateType":"Updated"},{"date":"2026-10-30","dateType":"Issued"}],"language":null,"types":{"schemaOrg":"ScholarlyArticle","resourceTypeGeneral":"JournalArticle","citeproc":"article-journal","bibtex":"article","ris":"JOUR","resourceType":"Journal contribution"},"relatedIdentifiers":[{"relationType":"IsIdenticalTo","relatedIdentifier":"10.6084/m9.figshare.34873306","relatedIdentifierType":"DOI"},{"relationType":"IsSupplementTo","relatedIdentifier":"10.1186/s12711-026-01098-x","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":["161722 Bytes"],"formats":[],"version":"1","rightsList":[{"rightsIdentifierScheme":"SPDX","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rights":"Creative Commons Attribution 4.0 International","rightsIdentifier":"cc-by-4.0"}],"descriptions":[{"descriptionType":"Abstract","description":"Supplementary Material 4"}],"geoLocations":[],"fundingReferences":[],"url":"https://springernature.figshare.com/articles/journal_contribution/Additional_file_4_of_Genotype_by_environment_interaction_under_two_production_systems_utilizing_a_random_regression_model_for_milk_production_traits_in_multiparous_South_African_Holstein_dairy_cattle/34873306/1","contentUrl":null,"metadataVersion":0,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"mds","isActive":true,"state":"findable","reason":null,"viewCount":0,"downloadCount":0,"referenceCount":0,"citationCount":1,"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2026-10-31T04:25:46Z","registered":"2026-10-31T04:25:47Z","published":null,"updated":"2026-10-31T04:25:55Z"},"relationships":{"client":{"data":{"id":"figshare.ars","type":"clients"}}}}],"meta":{"total":3680,"totalPages":148,"page":1},"links":{"self":"https://api.datacite.org/dois?affiliation-id=03xjwb503","next":"https://api.datacite.org/dois?affiliation-id=03xjwb503\u0026page%5Bnumber%5D=2\u0026page%5Bsize%5D=25"}}