[ { "id": "gstacks_refMap", "name": "gstacks_refMap", "article": "10.1111\/mec.15253", "website": "http:\/\/catchenlab.life.illinois.edu\/stacks\/comp\/gstacks.php", "git": "", "description": "gstacks build loci from the single and\/or paired-end reads before calling SNPs", "version": "2.64", "documentation": "http:\/\/catchenlab.life.illinois.edu\/stacks\/comp\/gstacks.php", "multiqc": "custom", "commands": [ { "name": "gstacks_refMap", "cname": "gstacks_refMap", "command": "gstacks", "category": "stacks", "output_dir": "gstacks_refMap", "inputs": [ { "name": "bams", "type": "bams", "file": "{sample}.bam", "expand": true }, { "name": "popmap", "type": "popmap" } ], "outputs": [ { "name": "catalog_calls", "type": "stacks_calls", "file": "catalog.calls", "description": "Consensus sequence for each assembled locus in the data" }, { "name": "catalog_fa", "type": "fa.gz", "file": "catalog.fa.gz", "description": "Custom file that contains genotyping data" }, { "name": "stats", "type": "distribs", "file": "gstacks.log.distribs", "description": "Distributions statistics (bam stats, coverage and phasing_rates per sample)" } ], "options": [ { "name": "gstacks_refMap_threads", "prefix": "-t", "type": "numeric", "value": 4, "min": 1, "max": "NA", "step": 1, "label": "Number of threads to use" }, { "name": "gstacks_refMap_model", "prefix": "--model", "type": "select", "value": "marukilow", "choices": [ { "marukilow": "marukilow" }, { "marukihigh": "marukihigh" }, { "snp": "snp" } ], "label": "Model to use to call variants and genotypes" }, { "name": "gstacks_refMap_var_alpha", "prefix": "--var-alpha", "type": "numeric", "value": 0.05, "min": 0, "max": "NA", "step": "NA", "label": "Alpha threshold for discovering SNPs" }, { "name": "gstacks_refMap_gt_alpha", "prefix": "--gt-alpha", "type": "numeric", "value": 0.05, "min": 0, "max": "NA", "step": "NA", "label": "Alpha threshold for calling genotypes" }, { "name": "gstacks_refMap_min_mapq", "prefix": "--min-mapq", "type": "numeric", "value": 20, "min": 0, "max": "NA", "step": 1, "label": "Minimum PHRED-scaled mapping quality to consider a read" }, { "name": "gstacks_refMap_max_clipped", "prefix": "--max-clipped", "type": "numeric", "value": 0.2, "min": 0, "max": "NA", "step": "NA", "label": "Maximum soft-clipping level, in fraction of read length" }, { "name": "gstacks_refMap_max_insert", "prefix": "--max-insert-len", "type": "numeric", "value": 1000, "min": 50, "max": "NA", "step": 10, "label": "maximum allowed sequencing insert length" }, { "name": "gstacks_refMap_rm_pcr_duplicates", "prefix": "--rm-pcr-duplicates", "type": "checkbox", "value": false, "label": "remove read pairs of the same insert length (WARN !! implies --rm-unpaired-reads)" } ] } ], "prepare_report_script": "gstacks_refMap.prepare.report.R", "prepare_report_outputs": [ "bam_stats_per_sample_mqc.tsv", "effective_coverages_per_sample_mqc.tsv", "phasing_rates_per_sample_mqc.tsv" ], "install": [], "citations": { "stacks": [ " Rochette, NC, Rivera-Col\u00f3n, AG, Catchen, JM. Stacks 2: Analytical methods for paired-end sequencing improve RADseq\u2010based population genomics. Mol Ecol. 2019; 28: 4737- 4754. https:\/\/doi.org\/10.1111\/mec.15253" ] }, "yaml": "{\n id: gstacks_refMap,\n name: gstacks_refMap,\n article: 10.1111\/mec.15253,\n website: \"http:\/\/catchenlab.life.illinois.edu\/stacks\/comp\/gstacks.php\",\n git: \"\",\n description: \"gstacks build loci from the single and\/or paired-end reads before calling SNPs\",\n version: \"2.64\",\n documentation: \"http:\/\/catchenlab.life.illinois.edu\/stacks\/comp\/gstacks.php\",\n multiqc: \"custom\",\n commands:\n [\n {\n name: gstacks_refMap,\n cname: \"gstacks_refMap\",\n command: gstacks,\n category: \"stacks\",\n output_dir: gstacks_refMap,\n inputs: [{ name: bams, type: \"bams\", file: \"{sample}.bam\", expand: true}, #all bams must be in the same dir that will be determined from the first bam filename\n { name: popmap, type: \"popmap\" }\n ],\n outputs:\n [\n { name: catalog_calls, type: \"stacks_calls\", file: \"catalog.calls\", description: \"Consensus sequence for each assembled locus in the data\" },\n { name: catalog_fa, type: \"fa.gz\", file: \"catalog.fa.gz\", description: \"Custom file that contains genotyping data\" },\n { name: stats, type: \"distribs\", file: \"gstacks.log.distribs\", description: \"Distributions statistics (bam stats, coverage and phasing_rates per sample)\" },\n ],\n options:\n [\n {\n name: gstacks_refMap_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: gstacks_refMap_model,\n prefix: --model,\n type: select,\n value: marukilow,\n choices: [marukilow: marukilow, marukihigh: marukihigh, snp: snp],\n label: \"Model to use to call variants and genotypes\",\n },\n {\n name: gstacks_refMap_var_alpha,\n prefix: --var-alpha,\n type: numeric,\n value: 0.05,\n min: 0,\n max: NA,\n step: NA,\n label: \"Alpha threshold for discovering SNPs\",\n },\n {\n name: gstacks_refMap_gt_alpha,\n prefix: --gt-alpha,\n type: numeric,\n value: 0.05,\n min: 0,\n max: NA,\n step: NA,\n label: \"Alpha threshold for calling genotypes\",\n },\n {\n name: gstacks_refMap_min_mapq,\n prefix: --min-mapq,\n type: numeric,\n value: 20,\n min: 0,\n max: NA,\n step: 1,\n label: \"Minimum PHRED-scaled mapping quality to consider a read\",\n },\n {\n name: gstacks_refMap_max_clipped,\n prefix: --max-clipped,\n type: numeric,\n value: 0.20,\n min: 0,\n max: NA,\n step: NA,\n label: \"Maximum soft-clipping level, in fraction of read length\",\n },\n {\n name: gstacks_refMap_max_insert,\n prefix: --max-insert-len,\n type: numeric,\n value: 1000,\n min: 50,\n max: NA,\n step: 10,\n label: \"maximum allowed sequencing insert length\",\n },\n {\n name: gstacks_refMap_rm_pcr_duplicates,\n prefix: --rm-pcr-duplicates,\n type: \"checkbox\",\n value: FALSE,\n label: \"remove read pairs of the same insert length (WARN !! implies --rm-unpaired-reads)\",\n },\n ],\n },\n ],\n prepare_report_script: gstacks_refMap.prepare.report.R,\n prepare_report_outputs: [\n bam_stats_per_sample_mqc.tsv,\n effective_coverages_per_sample_mqc.tsv,\n phasing_rates_per_sample_mqc.tsv\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 },\n citations: {\n stacks: [\n \" Rochette, NC, Rivera-Col\u00f3n, AG, Catchen, JM. Stacks 2: Analytical methods for paired-end sequencing improve RADseq\u2010based population genomics. Mol Ecol. 2019; 28: 4737- 4754. https:\/\/doi.org\/10.1111\/mec.15253\"\n ]\n }\n}\n" } ]