[
    {
        "id": "Picard_MarkDuplicates",
        "name": "Picard Mark Duplicates",
        "article": null,
        "website": "https:\/\/broadinstitute.github.io\/picard\/",
        "git": "https:\/\/github.com\/broadinstitute\/picard",
        "description": "This tool locates and tags duplicate reads in a BAM or SAM file, where duplicate reads are defined as originating from a single fragment of DNA.",
        "version": "3.0.0",
        "documentation": "https:\/\/broadinstitute.github.io\/picard\/command-line-overview.html",
        "multiqc": "picard",
        "commands": [
            {
                "name": "Picard_MarkDuplicates",
                "cname": "Picard Mark Duplicates",
                "command": "java -jar \/opt\/biotools\/bin\/picard.jar MarkDuplicates",
                "category": "bam_correction",
                "output_dir": "Picard_MarkDuplicates",
                "inputs": [
                    {
                        "name": "bam_in",
                        "type": [
                            "bams",
                            "sam"
                        ]
                    }
                ],
                "outputs": [
                    {
                        "name": "sorted_bam",
                        "type": "bams",
                        "file": "{sample}.mapped.dedup.sorted.bam",
                        "description": "Sorted bam"
                    },
                    {
                        "name": "bai",
                        "type": "bai",
                        "file": "{sample}.mapped.dedup.sorted.bam.bai",
                        "description": "Bam index"
                    },
                    {
                        "name": "metric",
                        "type": "txt",
                        "file": "duplicate_metrics_{sample}.txt",
                        "description": "Metrics"
                    }
                ],
                "options": [
                    {
                        "name": "Picard_MarkDuplicates_threads",
                        "type": "numeric",
                        "value": 4,
                        "min": 1,
                        "max": "NA",
                        "step": 1,
                        "label": "Number of threads to use"
                    },
                    {
                        "name": "Picard_MarkDuplicates_remove_all_duplicates",
                        "type": "checkbox",
                        "value": true,
                        "label": "remove_all_duplicates : If true do not write duplicates to the output file instead of writing them with appropriate flags set."
                    },
                    {
                        "name": "Picard_MarkDuplicates_samtools_memory",
                        "type": "numeric",
                        "value": 2,
                        "label": "-m parameter for samtools sort: Memory allocated per thread for samtools_sort (in Gb)."
                    }
                ]
            }
        ],
        "install": [],
        "citations": {
            "picard_tools": [
                "Picard Toolkit. 2019. Broad Institute, GitHub Repository. http:\/\/broadinstitute.github.io\/picard\/; Broad Institute"
            ],
            "samtools": [
                "Heng Li, Bob Handsaker, Alec Wysoker, Tim Fennell, Jue Ruan, Nils Homer, Gabor Marth, Goncalo Abecasis, Richard Durbin, 1000 Genome Project Data Processing Subgroup, The Sequence Alignment\/Map format and SAMtools, Bioinformatics, Volume 25, Issue 16, 15 August 2009, Pages 2078-2079, https:\/\/doi.org\/10.1093\/bioinformatics\/btp352"
            ]
        },
        "yaml": "{\n  id: Picard_MarkDuplicates,\n  name: Picard Mark Duplicates,\n  article: ~,\n  website: \"https:\/\/broadinstitute.github.io\/picard\/\",\n  git: \"https:\/\/github.com\/broadinstitute\/picard\",\n  description: \"This tool locates and tags duplicate reads in a BAM or SAM file, where duplicate reads are defined as originating from a single fragment of DNA.\",\n  version: \"3.0.0\",\n  documentation: \"https:\/\/broadinstitute.github.io\/picard\/command-line-overview.html\",\n  multiqc: \"picard\",\n  commands:\n    [\n      {\n        name: Picard_MarkDuplicates,\n        cname: \"Picard Mark Duplicates\",\n        command: java -jar \/opt\/biotools\/bin\/picard.jar MarkDuplicates,\n        category: \"bam_correction\",\n        output_dir: Picard_MarkDuplicates,\n        inputs: [ {name: \"bam_in\", type: [\"bams\", \"sam\"]} ],\n        outputs:  [\n          #{ name: \"bam\", type: \"bams\", file: \"{sample}.mapped.dedup.bam\", description: \"Output bam\" }, # temp file\n          { name: \"sorted_bam\", type: \"bams\", file: \"{sample}.mapped.dedup.sorted.bam\", description: \"Sorted bam\" },\n          { name: \"bai\", type: \"bai\", file: \"{sample}.mapped.dedup.sorted.bam.bai\", description: \"Bam index\" },\n          { name: \"metric\", type: \"txt\", file: \"duplicate_metrics_{sample}.txt\", description: \"Metrics\" }\n        ],\n        options:\n          [\n            {\n              name: Picard_MarkDuplicates_threads,\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: \"Picard_MarkDuplicates_remove_all_duplicates\",\n              type: \"checkbox\",\n              value: TRUE,\n              label: \"remove_all_duplicates : If true do not write duplicates to the output file instead of writing them with appropriate flags set.\",\n            },\n            {\n              name: \"Picard_MarkDuplicates_samtools_memory\",\n              type: numeric,\n              value: 2,\n              label: \"-m parameter for samtools sort: Memory allocated per thread for samtools_sort (in Gb).\",\n            },\n          ],\n      },\n    ],\n  install: {\n    # samtools: [\n    #   \"cd \/opt\/biotools\",\n    #   \"wget https:\/\/github.com\/samtools\/samtools\/releases\/download\/1.9\/samtools-1.9.tar.bz2\",\n    #   \"tar -xvjf samtools-1.9.tar.bz2\",\n    #   \"cd samtools-1.9\",\n    #   \".\/configure && make\",\n    #   \"cd ..\",\n    #   \"mv samtools-1.9\/samtools bin\/samtools\",\n    #   \"rm -r samtools-1.9 samtools-1.9.tar.bz2\"\n    # ],\n    # picard_tools: [\n    #   \"cd \/opt\/biotools\/bin\",\n    #   \"wget https:\/\/github.com\/broadinstitute\/picard\/releases\/download\/2.20.8\/picard.jar\"\n    # ],\n    # java8: [\n    #   \"apt -y update && apt install -y openjdk-8-jre\"\n    # ]\n  },\n  citations:  {\n    picard_tools: [\n      \"Picard Toolkit. 2019. Broad Institute, GitHub Repository. http:\/\/broadinstitute.github.io\/picard\/; Broad Institute\"\n    ],\n    samtools: [\n      \"Heng Li, Bob Handsaker, Alec Wysoker, Tim Fennell, Jue Ruan, Nils Homer, Gabor Marth, Goncalo Abecasis, Richard Durbin, 1000 Genome Project Data Processing Subgroup, The Sequence Alignment\/Map format and SAMtools, Bioinformatics, Volume 25, Issue 16, 15 August 2009, Pages 2078-2079, https:\/\/doi.org\/10.1093\/bioinformatics\/btp352\"\n    ]\n  }\n}\n"
    }
]