[
    {
        "id": "pca_gds",
        "name": "Principal Component Analysis",
        "article": "",
        "website": "",
        "git": "",
        "description": "Principal Component Analysis (PCA) on genotypes with SNPRelate R package",
        "version": "0.3.3",
        "documentation": "",
        "multiqc": "custom",
        "commands": [
            {
                "name": "pca_gds",
                "command": "",
                "category": "genet_pop",
                "output_dir": "pca_gds",
                "inputs": [
                    {
                        "name": "gds",
                        "type": "gds",
                        "file": "",
                        "description": "gds file"
                    },
                    {
                        "name": "popmap_file",
                        "type": "popmap",
                        "file": "",
                        "description": "Path to tsv file with samples group"
                    }
                ],
                "outputs": [
                    {
                        "name": "eigenvectors",
                        "type": "txt",
                        "file": "*_eigenvects.txt",
                        "description": "Eigenvectors"
                    },
                    {
                        "name": "eigenvalues",
                        "type": "txt",
                        "file": "*_eigenvals.txt",
                        "description": "Eigenvalues"
                    },
                    {
                        "name": "varprop",
                        "type": "txt",
                        "file": "pca_varprop_mqc.txt",
                        "description": "variance proportion"
                    },
                    {
                        "name": "pca_png",
                        "type": "png",
                        "file": "pca_topaxes_plot_mqc.png",
                        "description": "First 6 eigenvectors plots"
                    },
                    {
                        "name": "axe1axe2_png",
                        "type": "png",
                        "file": "pca_axe1axe2_plot_mqc.png",
                        "description": "First 2 eigenvectors plots"
                    }
                ],
                "options": [
                    {
                        "name": "pca_gds_minmaf",
                        "prefix": "--minmaf",
                        "value": 0,
                        "min": 0,
                        "max": 1,
                        "step": 0.01,
                        "label": "minor allel frequency",
                        "type": "numeric"
                    },
                    {
                        "name": "pca_gds_missing",
                        "prefix": "--missing",
                        "value": 1,
                        "min": 0,
                        "max": 1,
                        "step": 0.01,
                        "label": "max missing snps(1 allows sites completely missing 0 no missing data allowed)",
                        "type": "numeric"
                    },
                    {
                        "name": "pca_gds_threads",
                        "prefix": "--threads",
                        "value": 16,
                        "min": 1,
                        "max": 64,
                        "step": 1,
                        "label": "Threads to use",
                        "type": "numeric"
                    }
                ]
            }
        ],
        "script": "pca_gds.script.R",
        "install": [],
        "citations": {
            "SNPRelate": [
                "Zheng X, Levine D, Shen J, Gogarten S, Laurie C, Weir B (2012). A High-performance Computing Toolset for Relatedness and Principal Component Analysis of SNP Data. Bioinformatics, 28(24), 3326-3328. doi: 10.1093\/bioinformatics\/bts606. "
            ],
            "SeqArray": [
                "Zheng X, Gogarten S, Lawrence M, Stilp A, Conomos M, Weir B, Laurie C, Levine D (2017). SeqArray - A storage-efficient high-performance data format for WGS variant calls. Bioinformatics. doi: 10.1093\/bioinformatics\/btx145."
            ]
        },
        "yaml": "{\n  id: pca_gds,\n  name: Principal Component Analysis,\n  article: \"\",\n  website: \"\",\n  git: \"\",\n  description: \"Principal Component Analysis (PCA) on genotypes with SNPRelate R package\",\n  version: \"0.3.3\",\n  documentation: \"\",\n  multiqc: \"custom\",\n  commands:\n    [\n      {\n        name: pca_gds,\n        command: \"\",\n        category: \"genet_pop\",\n        output_dir: pca_gds,\n        inputs: [{ name: gds, type: \"gds\", file: \"\",description: \"gds file\"} ,\n                 { name: popmap_file, type: \"popmap\", file: \"\", description: \"Path to tsv file with samples group\"}\n                ],\n        outputs: [\n          { name: eigenvectors, type: \"txt\", file: \"*_eigenvects.txt\", description: \"Eigenvectors\" },\n          { name: eigenvalues, type: \"txt\", file: \"*_eigenvals.txt\", description: \"Eigenvalues\" },\n          { name: varprop, type: \"txt\", file: \"pca_varprop_mqc.txt\", description: \"variance proportion\" },\n          { name: pca_png, type: \"png\", file: \"pca_topaxes_plot_mqc.png\", description: \"First 6 eigenvectors plots\" },\n          { name: axe1axe2_png, type: \"png\", file: \"pca_axe1axe2_plot_mqc.png\", description: \"First 2 eigenvectors plots\" },\n        ],\n        options: [\n          {\n              name: \"pca_gds_minmaf\",\n              prefix: \"--minmaf\",\n              value: 0,\n              min: 0,\n              max: 1,\n              step: 0.01,\n              label: \"minor allel frequency\",\n              type: \"numeric\",\n          },      \n          {\n              name: \"pca_gds_missing\",\n              prefix: \"--missing\",\n              value: 1,\n              min: 0,\n              max: 1,\n              step: 0.01,\n              label: \"max missing snps(1 allows sites completely missing 0 no missing data allowed)\",\n              type: \"numeric\",\n          },\n          {\n              name: \"pca_gds_threads\",\n              prefix: \"--threads\",\n              value: 16,\n              min: 1,\n              max: 64,\n              step: 1,\n              label: \"Threads to use\",\n              type: \"numeric\",\n          },\n        ],\n      },\n    ],\n  script: pca_gds.script.R,\n  install:\n    {\n    #   SNPRelate: [\n    #     'Rscript -e ''if (!requireNamespace(\"BiocManager\", quietly = TRUE))  install.packages(\"BiocManager\");\n    #      BiocManager::install(\"SNPRelate\", update = TRUE, ask = FALSE)'' '\n    #   ],\n    #   SeqArray: [\n    #     'Rscript -e ''if (!requireNamespace(\"BiocManager\", quietly = TRUE))  install.packages(\"BiocManager\");\n    #      BiocManager::install(\"SeqArray\", update = TRUE, ask = FALSE)'' '\n    #   ],\n    #   pandoc: [apt-get install -y pandoc],\n    #   rgl: ['Rscript -e ''install.packages(\"rgl\");'' ' ],\n    #   threejs: ['Rscript -e ''install.packages(\"threejs\");'' ' ]\n    },\n  citations:\n    {\n     SNPRelate: [\n       \"Zheng X, Levine D, Shen J, Gogarten S, Laurie C, Weir B (2012). A High-performance Computing Toolset for Relatedness and Principal Component Analysis of SNP Data. Bioinformatics, 28(24), 3326-3328. doi: 10.1093\/bioinformatics\/bts606. \" \n       ],\n     SeqArray: [\n       \"Zheng X, Gogarten S, Lawrence M, Stilp A, Conomos M, Weir B, Laurie C, Levine D (2017). SeqArray - A storage-efficient high-performance data format for WGS variant calls. Bioinformatics. doi: 10.1093\/bioinformatics\/btx145.\" \n       ],\n    },\n}\n"
    }
]