[ { "id": "populations", "name": "Stacks populations", "article": "10.1111\/mec.15253", "website": "http:\/\/catchenlab.life.illinois.edu\/stacks\/comp\/populations.php", "git": "", "description": "The populations program will analyze a population of individual samples computing a number of population genetics statistics as well as exporting a variety of standard output formats.", "version": "2.64", "documentation": "http:\/\/catchenlab.life.illinois.edu\/stacks\/comp\/populations.php", "multiqc": "stacks", "commands": [ { "name": "populations", "cname": "Populations", "command": "populations", "category": "stacks", "output_dir": "populations", "inputs": [ { "name": "catalog_calls", "type": "stacks_calls", "description": "Binary calls file from stacks output" }, { "name": "popmap", "type": "popmap" } ], "outputs": [ { "name": "sumstats", "type": "tsv", "file": "populations.sumstats.tsv", "description": "summary statistics describing every SNP found in every population. frequecy of alleles, expected\/observed heterozygosity, \u03c0, FIS, and so on." }, { "name": "fstats_pop", "type": "tsv", "file": "populations.fst_{popA}-{popB}.tsv", "description": "SNP and haplotype-based F statistics between each populations" }, { "name": "haplotypes_tab", "type": "tsv", "file": "populations.haplotypes.tsv", "description": "Haplotypes for each sample" }, { "name": "phistats_pop", "type": "tsv", "file": "populations.phistats_{popA}-{popB}.tsv", "description": "Phi statistics between each populations" }, { "name": "vcf", "type": "vcf_file", "file": "populations.snps.vcf.gz", "description": "SNP vcf file" }, { "name": "structure", "type": "structure", "file": "populations.structure", "description": "Output in Structure format" }, { "name": "genepop_haplotypes", "type": "genepop", "file": "populations.haps.genepop", "description": "Haplotypes in GenePop format" }, { "name": "genepop_snps", "type": "genepop", "file": "populations.snps.genepop", "description": "SNP in GenePop format" }, { "name": "phylip", "type": "phylip", "file": "populations.fixed.phylip", "description": "output nucleotides that are fixed-within, and variant among populations in Phylip format (1 seq per pop)" }, { "name": "phylip_var", "type": "phylip", "file": "populations.var.phylip", "description": "include variable sites in the phylip output encoded using IUPAC notation (1 seq per pop)" }, { "name": "sample_phylip", "type": "phylip", "file": "samples.fixed.phylip", "description": "output nucleotides that are variant among samples in Phylip format (1 seq per sample)" } ], "options": [ { "name": "populations_threads", "prefix": "-t", "type": "numeric", "value": 4, "min": 1, "max": "NA", "step": 1, "label": "Number of threads to use" }, { "name": "populations_r", "prefix": "-r", "type": "numeric", "value": 0.7, "min": 0, "max": "NA", "step": "NA", "label": "Minimum percentage of individuals in a population required to process a locus for that population" }, { "name": "populations_max_obs_het", "prefix": "--max-obs-het", "type": "numeric", "value": 1, "min": 0, "max": "NA", "step": "NA", "label": "Specify a maximum observed heterozygosity required to process a nucleotide site at a locus" }, { "name": "populations_min_maf", "prefix": "--min-maf", "type": "numeric", "value": 0.05, "min": 0, "max": 0.5, "step": "NA", "label": "Specify a minimum minor allele frequency required to process a nucleotide site at a locus" }, { "name": "populations_p", "prefix": "-p", "type": "numeric", "value": 2, "min": 1, "max": "NA", "step": 1, "label": "Minimum number of populations a locus must be present in to process a locus" }, { "name": "populations_remove_ctg_info", "prefix": "", "type": "checkbox", "value": true, "label": "Remove ##contig info from vcf header in order not to slow down the conversion to GDS " } ] } ], "prepare_report_script": "populations.prepare.report.R", "prepare_report_outputs": [ "PCA_Eigenvalues_mqc.txt", "PCA_First2axis_mqc.yaml", "Mean_Pairwise_Pop_FST_mqc.csv", "IBS_mqc.png" ], "install": [], "citations": { "stacks": [ "Rochette, NC, Rivera-Col\u00f3n, AG, Catchen, JM. Stacks 2: Analytical methods for paired-end sequencing improve RADseq-based population genomics. Mol Ecol. 2019; 28: 4737- 4754. https:\/\/doi.org\/10.1111\/mec.15253" ] }, "yaml": "{\n id: populations,\n name: Stacks populations,\n article: 10.1111\/mec.15253,\n website: \"http:\/\/catchenlab.life.illinois.edu\/stacks\/comp\/populations.php\",\n git: \"\",\n description: \"The populations program will analyze a population of individual samples computing a number of population genetics statistics as well as exporting a variety of standard output formats.\",\n version: \"2.64\",\n documentation: \"http:\/\/catchenlab.life.illinois.edu\/stacks\/comp\/populations.php\",\n multiqc: \"stacks\",\n commands:\n [\n {\n name: populations,\n cname: \"Populations\",\n command: populations,\n category: \"stacks\",\n output_dir: populations,\n inputs: [{ name: catalog_calls, type: \"stacks_calls\", description: \"Binary calls file from stacks output\" }, { name: popmap, type: \"popmap\" }],\n outputs: [\n {name: sumstats, type: \"tsv\", file: \"populations.sumstats.tsv\", description: \"summary statistics describing every SNP found in every population. frequecy of alleles, expected\/observed heterozygosity, \u03c0, FIS, and so on.\"},\n { name: fstats_pop, type: \"tsv\", file: \"populations.fst_{popA}-{popB}.tsv\", description: \"SNP and haplotype-based F statistics between each populations\" },\n# { name: fstats_summary, type: \"tsv\", file: \"populations.fst_summary.tsv\", description: \"SNP and haplotype-based F statistics summary\" },\n { name: haplotypes_tab, type: \"tsv\", file: populations.haplotypes.tsv, description: \"Haplotypes for each sample\" },\n { name: phistats_pop, type: \"tsv\", file: \"populations.phistats_{popA}-{popB}.tsv\", description: \"Phi statistics between each populations\" },\n# { name: phistats_summary, type: \"tsv\", file: \"populations.phistats_summary.tsv\", description: \"Phi statistics summary\" },\n { name: vcf, type: \"vcf_file\", file: \"populations.snps.vcf.gz\", description: \"SNP vcf file\" },\n { name: structure, type: \"structure\", file: \"populations.structure\", description: \"Output in Structure format\" },\n { name: genepop_haplotypes, type: \"genepop\", file: \"populations.haps.genepop\", description: \"Haplotypes in GenePop format\" },\n { name: genepop_snps, type: \"genepop\", file: \"populations.snps.genepop\", description: \"SNP in GenePop format\" },\n# { name: plink_map, type: \"map\", file: \"populations.plink.map\", description: \"Genotypes in PLINK format\" },\n# { name: plink_ped, type: \"ped\", file: \"populations.plink.ped\", description: \"Genotypes in PLINK format\" },\n# { name: radpainter_haplotypes, type: \"radpainter\", file: \"populations.haps.radpainter\", description: \"Haplotypes fineRADstructure\/RADpainter format\" },\n { name: phylip, type: \"phylip\", file: \"populations.fixed.phylip\", description: \"output nucleotides that are fixed-within, and variant among populations in Phylip format (1 seq per pop)\" },\n { name: phylip_var, type: \"phylip\", file: \"populations.var.phylip\", description: \"include variable sites in the phylip output encoded using IUPAC notation (1 seq per pop)\" },\n { name: sample_phylip, type: \"phylip\", file: \"samples.fixed.phylip\", description: \"output nucleotides that are variant among samples in Phylip format (1 seq per sample)\" },\n# { name: PCA_Eigenvalues_mqc, type: \"txt\", file: PCA_Eigenvalues_mqc.txt ,description: \"PCA eigenvalues\" },\n# { name: PCA_First2axis_mqc, type: \"yaml\", file: PCA_First2axis_mqc.yaml ,description: \"PCA plot on first 2 axis\" },\n# { name: Mean_Pairwise_Pop_FST_mqc, type: \"csv\", file: Mean_Pairwise_Pop_FST_mqc.csv ,description: \"Mean pairwise population Fstats\" },\n# { name: IBS_mqc, type: \"png\", file: IBS_mqc.png ,description: \"IBS heatmap\" },\n ],\n options:\n [\n {\n name: populations_threads,\n prefix: -t,\n type: numeric,\n value: 4,\n min: 1,\n max: NA,\n step: 1,\n label: \"Number of threads to use\",\n },\n {\n name: populations_r,\n prefix: -r,\n type: numeric,\n value: 0.7,\n min: 0,\n max: NA,\n step: NA,\n label: \"Minimum percentage of individuals in a population required to process a locus for that population\",\n },\n {\n name: populations_max_obs_het,\n prefix: --max-obs-het,\n type: numeric,\n value: 1,\n min: 0,\n max: NA,\n step: NA,\n label: \"Specify a maximum observed heterozygosity required to process a nucleotide site at a locus\",\n },\n {\n name: populations_min_maf,\n prefix: --min-maf,\n type: numeric,\n value: 0.05,\n min: 0,\n max: 0.5,\n step: NA,\n label: \"Specify a minimum minor allele frequency required to process a nucleotide site at a locus\",\n },\n {\n name: populations_p,\n prefix: -p,\n type: numeric,\n value: 2,\n min: 1,\n max: NA,\n step: 1,\n label: \"Minimum number of populations a locus must be present in to process a locus\",\n },\n {\n name: populations_remove_ctg_info,\n prefix: '',\n type: checkbox,\n value: TRUE,\n label: \"Remove ##contig info from vcf header in order not to slow down the conversion to GDS \",\n }\n ],\n },\n ],\n prepare_report_script: populations.prepare.report.R,\n prepare_report_outputs: [\n PCA_Eigenvalues_mqc.txt,\n PCA_First2axis_mqc.yaml,\n Mean_Pairwise_Pop_FST_mqc.csv,\n IBS_mqc.png\n ],\n install:\n {\n # stacks: [\n # \"cd \/opt\/biotools\",\n # \"wget http:\/\/catchenlab.life.illinois.edu\/stacks\/source\/stacks-2.61.tar.gz\",\n # \"tar -zxvf stacks-2.61.tar.gz\",\n # \"cd stacks-2.61\/\",\n # \".\/configure\",\n # \"make -j 10\",\n # \"make install\",\n # \"mv -t ..\/bin sstacks kmer_filter gstacks tsv2bam process_shortreads populations ustacks phasedstacks cstacks process_radtags\",\n # \"cd .. && rm -r stacks-2.61 stacks-2.61.tar.gz\"\n # ],\n # calibrate: ['Rscript -e ''install.packages(\"calibrate\",repos=\"https:\/\/cloud.r-project.org\/\",Ncpus=8, clean=TRUE);library(\"calibrate\")'''],\n # SNPRelate: ['Rscript -e ''BiocManager::install(\"SNPRelate\",Ncpus=8, clean=TRUE);library(\"SNPRelate\")'''],\n # ComplexHeatmap: ['apt-get install -y libcairo2-dev libxt-dev ', 'Rscript -e ''library(devtools);install_github(\"jokergoo\/ComplexHeatmap\");library(\"ComplexHeatmap\")'''],\n # tabix: ['apt-get -y install tabix'],\n # bcftools: [\n # \"cd \/opt\/biotools\",\n # \"wget https:\/\/github.com\/samtools\/bcftools\/releases\/download\/1.9\/bcftools-1.9.tar.bz2\",\n # \"tar -xvjf bcftools-1.9.tar.bz2\",\n # \"cd bcftools-1.9\",\n # \".\/configure --prefix=\/opt\/biotools\",\n # \"make -j 10\",\n # \"make install\",\n # \"mv bcftools \/opt\/biotools\/bin\/\",\n # \"cd .. && rm -r bcftools-1.9.tar.bz2 bcftools-1.9\"\n # ]\n },\n citations: {\n stacks: [\n \"Rochette, NC, Rivera-Col\u00f3n, AG, Catchen, JM. Stacks 2: Analytical methods for paired-end sequencing improve RADseq-based population genomics. Mol Ecol. 2019; 28: 4737- 4754. https:\/\/doi.org\/10.1111\/mec.15253\"\n ]\n }\n}\n" } ]