[
    {
        "id": "VSEARCH_clustering",
        "name": "VSEARCH clustering rm chimera generate OTU Table",
        "article": "10.7717\/peerj.2584",
        "website": "",
        "git": "https:\/\/github.com\/torognes\/vsearch",
        "description": "Clustering of the fasta sequences in filename according to the UCLUST algorithm (Robert Edgar), chimera removal and OTU output",
        "version": "2.23.0",
        "documentation": "https:\/\/github.com\/torognes\/vsearch\/releases\/download\/v2.21.1\/vsearch_manual.pdf",
        "multiqc": "custom",
        "commands": [
            {
                "name": "VSEARCH_clustering",
                "command": "vsearch ",
                "category": "VSEARCH",
                "output_dir": "VSEARCH_clustering",
                "inputs": [
                    {
                        "name": "fasta",
                        "type": "fasta_file",
                        "description": "dereplicated or unoise (ZOTU) or ASV fasta file"
                    },
                    {
                        "name": "otutab",
                        "type": "tsv",
                        "description": "Abundance table with dereplicates or unoised (ZOTU) or ASV sequences as row and samples as columns"
                    }
                ],
                "outputs": [
                    {
                        "name": "centroids",
                        "type": "fasta_file",
                        "file": "clustered-nonchimeras.fasta",
                        "description": "Fasta Clustered, denovo chimera removed and relabel with OTU_n"
                    },
                    {
                        "name": "otutab",
                        "type": "tsv",
                        "file": "OTU_Table.tsv",
                        "description": "Abundance table with OTU as row"
                    }
                ],
                "options": [
                    {
                        "name": "VSEARCH_clustering_threads",
                        "prefix": "--threads",
                        "value": 16,
                        "min": 1,
                        "max": 64,
                        "step": 1,
                        "label": "Threads to use",
                        "type": "numeric"
                    },
                    {
                        "name": "VSEARCH_clustering_identity",
                        "prefix": "--id",
                        "type": "numeric",
                        "min": "0",
                        "max": "1",
                        "step": "0.01",
                        "value": "0.97",
                        "label": "Pairwize identity to generate cluster\/OTU : ((matching columns) \/ (alignment length - terminal gaps))"
                    },
                    {
                        "name": "VSEARCH_clustering_method",
                        "type": "radio",
                        "value": "nochange",
                        "choices": [
                            {
                                "fasta_input_order": "nochange"
                            },
                            {
                                "abundance": "abundance"
                            },
                            {
                                "length": "length"
                            }
                        ],
                        "label": "For clustering, sequences are processed in order such that an appropriate centroid sequence is found before other members of its cluster. Define how you want to sort your input before to cluster (for abundance the fasta seq id need the field ;size=n i.e. >seq1;size=n)."
                    },
                    {
                        "name": "VSEARCH_clustering_strand",
                        "type": "radio",
                        "value": "--strand plus",
                        "choices": [
                            {
                                "plus": "--strand plus"
                            },
                            {
                                "both": "--strand both"
                            }
                        ],
                        "label": "cluster sequence on plus or both strands"
                    }
                ]
            }
        ],
        "install": [],
        "citations": {
            "VSEARCH": [
                "Rognes T, Flouri T, Nichols B, Quince C, Mah\u00e9 F. (2016) VSEARCH: a versatile open source tool for metagenomics. PeerJ 4:e2584."
            ]
        },
        "yaml": "{\n  id: VSEARCH_clustering,\n  name: VSEARCH clustering rm chimera generate OTU Table,\n  article: \"10.7717\/peerj.2584\",\n  website: \"\",\n  git: \"https:\/\/github.com\/torognes\/vsearch\",\n  description: \"Clustering of the fasta sequences in filename according to the UCLUST algorithm (Robert Edgar), chimera removal and OTU output\",\n  version: \"2.23.0\",\n  documentation: \"https:\/\/github.com\/torognes\/vsearch\/releases\/download\/v2.21.1\/vsearch_manual.pdf\",\n  multiqc: \"custom\",\n  commands:\n    [\n      {\n        name: VSEARCH_clustering,\n        command: \"vsearch \",\n        category: \"VSEARCH\",\n        output_dir: VSEARCH_clustering,\n        inputs: [\n            { name: fasta, type: \"fasta_file\", description: \"dereplicated or unoise (ZOTU) or ASV fasta file\"},\n            { name: otutab, type: \"tsv\", description: \"Abundance table with dereplicates or unoised (ZOTU) or ASV sequences as row and samples as columns\"},\n        ],\n        outputs: [\n          { name: \"centroids\", type: \"fasta_file\", file: \"clustered-nonchimeras.fasta\", description: \"Fasta Clustered, denovo chimera removed and relabel with OTU_n\" },\n          { name: \"otutab\", type: \"tsv\", file: \"OTU_Table.tsv\", description: \"Abundance table with OTU as row\" },\n        ],\n        options: [\n          {\n              name: \"VSEARCH_clustering_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            name: \"VSEARCH_clustering_identity\",\n            prefix: \"--id\",\n            type: \"numeric\",\n            min: \"0\",\n            max: \"1\",\n            step: \"0.01\",\n            value: \"0.97\",\n            label: \"Pairwize identity to generate cluster\/OTU : ((matching columns) \/ (alignment length - terminal gaps))\",\n          },\n          {\n            name: \"VSEARCH_clustering_method\",\n            type: radio,\n            value: \"nochange\",\n            choices: [ fasta_input_order: nochange, abundance: abundance, length: length],\n            label: \"For clustering, sequences are processed in order such that an appropriate centroid sequence is found before other members of its cluster. Define how you want to sort your input before to cluster (for abundance the fasta seq id need the field ;size=n i.e. >seq1;size=n).\",\n          },\n          {\n            name: \"VSEARCH_clustering_strand\",\n            type: radio,\n            value: \"--strand plus\",\n            choices: [ plus: --strand plus, both: --strand both ],\n            label: \"cluster sequence on plus or both strands\",\n          },\n        ],\n      },\n    ],\n  install:\n    {\n      # VSEARCH: [\n      #   \"cd \/opt\/biotools\/\",\n      #   \" wget https:\/\/github.com\/torognes\/vsearch\/releases\/download\/v2.21.1\/vsearch-2.21.1-linux-x86_64.tar.gz\",\n      #   \" tar -zxvf vsearch-2.21.1-linux-x86_64.tar.gz\",\n      #   \" mv vsearch-2.21.1-linux-x86_64\/bin\/vsearch \/opt\/biotools\/bin\",\n      #   \" rm -rf vsearch-2.21.1-linux-x86_64*\"\n      # ]\n    },\n  citations:\n    {\n     VSEARCH: [\n      \"Rognes T, Flouri T, Nichols B, Quince C, Mah\u00e9 F. (2016) VSEARCH: a versatile open source tool for metagenomics. PeerJ 4:e2584.\"\n      ]\n    },\n}\n"
    }
]