miga-base 0.3.0.0 → 0.3.0.1

data/utils/enveomics/Manifest/Tasks/other.json

@@ -0,0 +1,746 @@
+{
+  "tasks": [
+    {
+      "task": "Aln.cat.rb",
+      "description": ["Concatenates several multiple alignments in FastA",
+        "format into a single multiple alignment. The IDs of the sequences",
+        "(or the ID prefixes, if using --ignore-after) must coincide across",
+        "files."],
+      "help_arg": "--help",
+      "options": [
+        {
+          "opt": "--coords",
+          "arg": "out_file",
+          "description": "Output file of coordinates in RAxML-compliant format."
+        },
+        {
+          "opt": "--ignore-after",
+          "arg": "string",
+          "description": ["Remove everything in the IDs after the specified",
+            "string."]
+        },
+        {
+          "opt": "--remove-invariable",
+          "description": "Remove invariable sites.",
+          "note": ["Invariable sites are defined as columns with only one",
+            "state and undefined characters. Additional ambiguous characters",
+            "may exist and should be declared using --undefined."]
+        },
+        {
+          "opt": "--missing-char",
+          "description": "Character denoting missing data.",
+          "arg": "character",
+          "default": "-"
+        },
+        {
+          "opt": "--model",
+          "description": "Name of the model to use if --coords is used.",
+          "note": "See RAxML's documentation for additional information.",
+          "arg": "string",
+          "default": "AUTO"
+        },
+        {
+          "opt": "--undefined",
+          "arg": "string",
+          "description": ["All characters to be regarded as 'undefined'. It",
+            "should include all ambiguous and missing data chars. Ignored",
+            "unless --remove-invariable."],
+          "default": "-.Xx?"
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly (no STDERR output)."
+        },
+        {
+          "name": "Input alignments",
+          "arg": "in_file",
+          "multiple_sep": " ",
+          "mandatory": true,
+          "description": "Input alignments in FastA format."
+        },
+        ">",
+        {
+          "name": "Output alignment",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Output concatenated alignment."
+        }
+      ]
+    },
+    {
+      "task": "Aln.convert.pl",
+      "description": "Translates between different alignment formats.",
+      "help_arg": "",
+      "requires": [
+        {
+	  "perl_lib": "Bio::AlignIO"
+        }
+      ],
+      "cite": [["Stajich et al, 2002, GRes",
+        "http://dx.doi.org/10.1101/gr.361602"]],
+      "options": [
+        {
+          "name": "In-format",
+          "description": "Input file's format.",
+          "mandatory": true,
+          "arg": "select",
+          "values": ["bl2seq", "clustalw", "emboss", "fasta", "maf", "mase",
+            "mega", "meme", "metafasta", "msf", "nexus", "pfam", "phylip", "po",
+            "prodom", "psi", "selex", "stockholm", "XMFA", "arp"]
+        },
+        {
+          "name": "Out-format",
+          "description": "Output file's format.",
+          "mandatory": true,
+          "arg": "select",
+          "values": ["bl2seq", "clustalw", "emboss", "fasta", "maf", "mase",
+            "mega", "meme", "metafasta", "msf", "nexus", "pfam", "phylip", "po",
+            "prodom", "psi", "selex", "stockholm", "XMFA", "arp"]
+        },
+        "<",
+        {
+          "arg": "in_file",
+          "mandatory": true
+        },
+        ">",
+        {
+          "arg": "out_file",
+          "mandatory": true
+        }
+      ]
+    },
+    {
+      "task": "AlphaDiversity.pl",
+      "description": ["Takes a table of OTU abundance in one or more samples",
+        "and calculates the Rao (Q_alpha), Rao-Jost (Q_alpha_eqv), Shannon",
+        "(Hprime), and inverse Simpson (1_lambda) indices of alpha diversity",
+        "for each sample."],
+      "help_arg": "--help",
+      "see_also": ["Chao1.pl"],
+      "options": [
+        {
+          "name": "Input table",
+          "opt": "-i",
+          "arg": "in_file",
+          "description": ["Columns: samples, rows: OTUs, first column: OTU",
+            "names)."],
+          "mandatory": true
+        },
+        {
+          "name": "Discard rows",
+          "opt": "-r",
+          "arg": "integer",
+          "description": "Number of rows to ignore.",
+          "default": 0
+        },
+        {
+          "name": "Discard left columns",
+          "opt": "-c",
+          "arg": "integer",
+          "description": ["Number of columns to ignore after the first column",
+            "(i.e., between the first column, containing the name of the",
+            "categories, and the first column of abundance values)."],
+          "default": 0
+        },
+        {
+          "name": "Discard right columns",
+          "opt": "-C",
+          "arg": "integer",
+          "description": "Number of columns to ignore at the end of each line.",
+          "default": 0
+        },
+        {
+          "name": "Delimiter",
+          "opt": "-d",
+          "arg": "string",
+          "description": "Character (or string) separating columns.",
+          "note": ["Supported escaped characters are: '\\t' (tabulation), and",
+            "'\\0' (null bit)."],
+          "default": "\\t"
+        },
+        {
+          "name": "Headers",
+          "opt": "-h",
+          "description": ["The first row is assumed to have the names of the",
+            "samples."]
+        },
+        {
+          "name": "Distances file",
+          "opt": "-D",
+          "arg": "in_file",
+          "description": ["A squared matrix (or bottom-left half matrix) with",
+            "the distances between categories (OTUs or functions). The first",
+            "column must contain the names of the categories, and it shouldn't",
+            "have headers. If not set, all distances are assumed to be one."],
+          "note": "Only used for Rao."
+        },
+        {
+          "name": "Skip Rao",
+          "opt": "-R",
+          "description": "Do not calculate Rao indices.",
+          "note": ["This significantly decreases the total running time. Note",
+            "that Rao indices are highly susceptible to precision errors, and",
+            "shouldn't be trusted for very big numbers."]
+        },
+        {
+          "name": "q for qD",
+          "opt": "-q",
+          "arg": "integer",
+          "description": "Estimate the qD index (true diversity order q).",
+          "default": 0
+        },
+        ">",
+        {
+          "arg": "out_file",
+          "mandatory": true
+        }
+      ]
+    },
+    {
+      "task": "Chao1.pl",
+      "description": ["Takes a table of OTU abundance in one or more samples",
+        "and calculates the chao1 index (with 95% Confidence Interval) for",
+	"each sample. To use it with Qiime OTU Tables, run it ignoring 1",
+	"left column and with header."],
+      "see_also": ["AlphaDiversity.pl"],
+      "help_arg": "--help",
+      "options": [
+        {
+	  "name": "Input file",
+	  "opt": "-i",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "Input table (columns:samples, rows:OTUs)."
+	},
+	{
+	  "name": "Rows",
+	  "opt": "-r",
+	  "arg": "integer",
+	  "default": 0,
+	  "description": "Number of rows to ignore."
+	},
+	{
+	  "name": "Left columns to ignore",
+	  "opt": "-c",
+	  "arg": "integer",
+	  "default": 0,
+	  "description": "Number of columns to ignore."
+	},
+	{
+	  "name": "Right columns to ignore",
+	  "opt": "-C",
+	  "arg": "integer",
+	  "default": 0,
+	  "description": "Number of columns to ignore at the end."
+	},
+	{
+	  "name": "Delimiter",
+	  "opt": "-d",
+	  "arg": "string",
+	  "default": "\\t",
+	  "description": "Delimiter between columns.",
+	  "note": ["Supported escaped characters are: \\t (tabulation),",
+	    "and \\0 (null bit)."]
+	},
+	{
+	  "name": "Header",
+	  "opt": "-h",
+	  "description": ["If set, the first row is assumed to have the names",
+	    "of the samples."]
+	},
+	">",
+	{
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": ["Chao1 index and 95% CI bounds for each sample, in",
+	    "tab-delimited format."]
+	}
+      ]
+    },
+    {
+      "task": "CharTable.classify.rb",
+      "description": ["Uses a dichotomous key to classify objects parsing a",
+        "character table."],
+      "help_arg": "--help",
+      "options": [
+        {
+	  "opt": "--table",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": ["Input table containing the states (columns) per",
+	    "object (row). It must be tab-delimited and with row and column",
+	    "names."]
+	},
+	{
+	  "opt": "--key",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": ["Input table containing the dychotomous key in",
+	    "linked style, defined in four columns (can contain #-lead comment",
+	    "lines): (1) ID of the step, typically a sequential integer. (2)",
+	    "Name of character to evaluate. Must coincide with the -t headers.",
+	    "(3) First character decision (see below). (4) Second character",
+	    "decision (see below).\nA character decision must be formated as:",
+	    "state (must coincide with the values in -t), colon (:), step to",
+	    "follow. If the state is * (star) any state triggers the decision",
+	    "(this should be the norm in column 4). The step to follow should",
+	    "be a step ID in square brackets, or the name of the",
+	    "classification."]
+	},
+	{
+	  "opt": "--classification",
+	  "arg": "out_file",
+	  "description": ["Two-column table with the classification of the",
+	    "input objects."]
+	},
+	{
+	  "opt": "--newick",
+	  "arg": "out_file",
+	  "description": ["Tree containing all the classified objects. This",
+	    "only makes sense for synoptic keys."]
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly (no STDERR output)."
+	}
+      ]
+    },
+    {
+      "task": "GenBank.add_fields.rb",
+      "description": "Adds annotations to GenBank files.",
+      "help_arg": "--help",
+      "options": [
+        {
+	  "opt": "--genbank",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "Input GenBank file."
+	},
+	{
+	  "opt": "--table",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": ["Input file containing the annotations. It must be a",
+	    "tab-delimited raw table including a header row with the names of",
+	    "the fields."]
+	},
+	{
+	  "opt": "--out",
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": "Output file containing the annotated GenBank."
+	},
+	{
+	  "opt": "--key",
+	  "arg": "integer",
+	  "default": 1,
+	  "description": "Key of the column to use as identifier."
+	},
+	{
+	  "opt": "--split",
+	  "arg": "string",
+	  "default": "#",
+	  "description": ["String that separates multiple entries in the",
+	    "annotation features."]
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly (no STDERR output)."
+	}
+      ]
+    },
+    {
+      "task": "HMM.essential.rb",
+      "description": ["Finds and extracts a collection of essential proteins",
+        "suitable for genome completeness evaluation and phylogenetic",
+	"analyses in Archaea and Bacteria."],
+      "warn": ["Most complete bacterial genomes contain only 106/111 genes in",
+        "this collection, therefore producing a completeness of 95.5%, and",
+	"most archaeal genomes only contain 26/111 genes, producing a",
+	"completeness of 23.4%. Use the options --bacteria and/or --archaea to",
+	"ignore models often missing in one or both domains. Note that even",
+	"with these options, some complete archaeal genomes result in very low",
+	"values of completeness (e.g., Nanoarchaeum equitans returns 88.5%)."],
+      "help_arg": "--help",
+      "requires": [
+        {
+	  "description": "HMMer 3.0+",
+	  "test": "hmmsearch -h",
+	  "source_url": "http://hmmer.janelia.org/software"
+	}
+      ],
+      "cite": [["Eddy, 2011, PLoS CB",
+        "http://dx.doi.org/10.1371/journal.pcbi.1002195"]],
+      "options": [
+        {
+	  "name": "Input file",
+	  "opt": "--in",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "FastA file containing all the proteins in the genome."
+	},
+	{
+	  "name": "Output file",
+	  "opt": "--out",
+	  "arg": "out_file",
+	  "description": ["FastA file with the translated essential genes. By",
+	    "default the file is not produced."]
+	},
+	{
+	  "opt": "--per-model",
+	  "arg": "out_file",
+	  "description": ["Prefix of translated genes in independent files",
+	    "with the name of the model appended. By default files are not",
+	    "produced."]
+	},
+	{
+	  "opt": "--report",
+	  "arg": "out_file",
+	  "description": ["Path to the report file. By default, the report is",
+	    "sent to the STDOUT."]
+	},
+	{
+	  "opt": "--bacteria",
+	  "description": "If set, ignores models typically missing in Bacteria."
+	},
+	{
+	  "opt": "--archaea",
+	  "description": "If set, ignores models typically missing in Archaea."
+	},
+	{
+	  "opt": "--genome-eq",
+	  "description": ["If set, ignores models not suitable for",
+	    "genome-equivalents estimations. See Rodriguez-R et al, 2015, ISME",
+	    "J 9(9):1928-1940."],
+	  "source_url": "http://www.nature.com/ismej/journal/vaop/ncurrent/full/ismej20155a.html"
+	},
+	{
+	  "opt": "--rename",
+	  "arg": "string",
+	  "description": ["If set, renames the sequences with the string",
+	    "provided and appends it with pipe (|) and the gene name (except",
+	    "in --per-model files)."]
+	},
+	{
+	  "opt": "--no-stats",
+	  "description": ["If set, no statistics are reported on genome",
+	    "evaluation."]
+	},
+	{
+	  "opt": "--no-genes",
+	  "description": ["If set, statistics won't include the lists of",
+	    "missing/multi-copy genes."]
+	},
+	{
+	  "opt": "--metagenome",
+	  "description": ["If set, it allows for multiple copies of each gene",
+	    "and turns on metagenomic report mode."]
+	},
+	{
+	  "opt": "--list-models",
+	  "description": ["If set, it only lists the models and exits.",
+	    "Compatible with 'Archaea', 'Bacteria', 'Genome eq', and 'Quiet';",
+	    "ignores all other parameters."]
+	},
+	{
+	  "opt": "--bin",
+	  "arg": "in_dir",
+	  "description": "Directory containing the binaries of HMMer 3.0+."
+	},
+	{
+	  "opt": "--model-file",
+	  "arg": "in_file",
+	  "description": "External file containing models to search."
+	},
+	{
+	  "opt": "--threads",
+	  "arg": "integer",
+	  "default": 2,
+	  "description": "Number of parallel threads to be used."
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly (no STDERR output)."
+	}
+      ]
+    },
+    {
+      "task": "HMMsearch.extractIds.rb",
+      "description": ["Extracts the sequence IDs and query model form a",
+        "(multiple) HMMsearch report (for HMMer 3.0)."],
+      "help_arg": "--help",
+      "options": [
+        {
+	  "opt": "--all-evalue",
+	  "arg": "float",
+	  "description": "Maximum e-value of sequence to report result."
+	},
+	{
+	  "opt": "--all-score",
+	  "arg": "float",
+	  "description": "Minimum score of sequence to report result."
+	},
+	{
+	  "opt": "--best-evalue",
+	  "arg": "float",
+	  "description": "Maximum e-value of best domain to report result."
+	},
+	{
+	  "opt": "--best-score",
+	  "arg": "float",
+	  "description": "Minimum score of best domain to report result."
+	},
+	{
+	  "opt": "--no-model",
+	  "description": "Do not include the query model in the output list."
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly."
+	},
+	"<",
+	{
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "Input HMMsearch text file."
+	},
+	">",
+	{
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": "Output list of IDs."
+	}
+      ]
+    },
+    {
+      "task": "JPlace.distances.rb",
+      "description": ["Extracts the distance (estimated branch length) of each",
+        "placed read to a given node in a JPlace file."],
+      "requires": [ { "ruby_gem": "json" } ],
+      "help_arg": "--help",
+      "options": [
+        {
+	  "name": "Input file",
+	  "opt": "--in",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": ".jplace input file containing the read placement."
+	},
+	{
+	  "name": "Node",
+	  "opt": "--node",
+	  "arg": "string",
+	  "mandatory": true,
+	  "description": ["Index (number in curly brackets) of the node to",
+	    "which distances should be measured."]
+	},
+	{
+	  "name": "Output file",
+	  "opt": "--out",
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": "Output file in tabular format."
+	},
+	{
+	  "opt": "--in-node",
+	  "arg": "string",
+	  "description": ["Report only reads placed at this node or it's",
+	    "children."]
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly (no STDERR output)."
+	}
+      ]
+    },
+    {
+      "task": "JPlace.to_iToL.rb",
+      "description": ["Generates iToL-compatible files from a .jplace file",
+        "(produced by RAxML's EPA or pplacer), that can be used to draw",
+	"pie-charts in the nodes of the reference tree."],
+      "requires": [ { "ruby_gem": "json" } ],
+      "help_arg": "--help",
+      "options": [
+        {
+	  "name": "Input file",
+	  "opt": "--in",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": ".jplace input file containing the read placement."
+	},
+	{
+	  "name": "Out base",
+	  "opt": "--out",
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": "Base of the output files."
+	},
+	{
+	  "opt": "--unique",
+	  "arg": "string",
+	  "description": ["Name of the dataset (if only one is used).",
+	    "Conflicts with 'Regex' and 'Separator'."]
+	},
+	{
+	  "opt": "--regex",
+	  "arg": "string",
+	  "description": ["Regular expression capturing the sample ID (named",
+	    "dataset) in read names. By default: '^(?<dataset>.+?):.*'.",
+	    "Conflicts with 'Separator'."]
+	},
+	{
+	  "opt": "--separator",
+	  "arg": "string",
+	  "description": ["String separating the dataset name and the rest of",
+	    "the read name. It assumes that the read name starts by the",
+	    "dataset name. Conflicts with 'Regex'."]
+	},
+	{
+	  "opt": "--metadata",
+	  "arg": "in_file",
+	  "description": ["Datasets metadata in tab-delimited format with a",
+	    "header row. Valid headers: name (required), color (in Hex),",
+	    "size (# reads), norm (any float)."]
+	},
+	{
+	  "opt": "--norm",
+	  "arg": "string",
+	  "description": ["Normalization strategy. Must be one of:\n",
+	    "none: Direct read counts are reported without normalization.\n",
+	    "count (default): The counts are normalized (divided) by the total",
+	    "counts per dataset.\n",
+	    "size: The counts are normalized (divided) by the size column in",
+	    "metadata (must be integer).\n",
+	    "norm: The counts are normalized (divided) by the norm column in",
+	    "metadata (can be any float)."]
+	},
+	{
+	  "opt": "--old-itol",
+	  "description": ["Generate output file using the old iToL format",
+	    " (pre v3.0)."]
+	},
+	{
+	  "opt": "--collapse",
+	  "arg": "in_file",
+	  "description": "Internal nodes to collapse (requires rootted tree)."
+	},
+	{
+	  "opt": "--area",
+	  "description": ["If set, the area of the pies is proportional to the",
+	    "placements. Otherwise, the radius is."]
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly (no STDERR output)."
+	}
+      ]
+    },
+    {
+      "task": "MyTaxa.fragsByTax.pl",
+      "description": "Identifies fragments annotated as a taxon in MyTaxa.",
+      "help_arg": "",
+      "options": [
+        {
+	  "name": "MyTaxa output",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "Classification file generated by MyTaxa."
+	},
+	{
+	  "name": "Taxon",
+	  "arg": "string",
+	  "mandatory": true,
+	  "description": "Taxon to look for."
+	},
+	{
+	  "name": "Rank",
+	  "arg": "string",
+	  "description": "Rank of taxon (optional). By default: any rank."
+	},
+	">",
+	{
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": "List of fragment IDs."
+	}
+      ]
+    },
+    {
+      "task": "MyTaxa.seq-taxrank.rb",
+      "description": ["Generates a simple tabular file with the classification",
+        "of each sequence at a given taxonomic rank from a MyTaxa output."],
+      "help_arg": "--help",
+      "options": [
+        {
+	  "name": "MyTaxa",
+	  "opt": "--mytaxa",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "Input MyTaxa file."
+	},
+	{
+	  "opt": "--rank",
+	  "arg": "string",
+	  "default": "genus",
+	  "description": "Taxonomic rank."
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly."
+	}
+      ]
+    },
+    {
+      "task": "Taxonomy.silva2ncbi.rb",
+      "description": ["Re-formats Silva taxonomy into NCBI-like taxonomy dump",
+        "files."],
+      "help_arg": "--help",
+      "options": [
+        {
+	  "opt": "--silvaranks",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": ["Input Silva ranks file (e.g.,",
+	    "tax_ranks_ssu_115.txt)."],
+	  "source_url": "https://www.arb-silva.de/no_cache/download/archive/release_115/Exports/"
+	},
+	{
+	  "opt": "--silvaref",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": ["Input Silva ref alignment file (e.g.,",
+	    "SSURef_NR99_115_tax_silva_full_align_trunc.fasta)."],
+	  "source_url": "https://www.arb-silva.de/no_cache/download/archive/release_115/Exports/"
+	},
+	{
+	  "opt": "--patch",
+	  "arg": "in_file",
+	  "description": ["If passed, it replaces the paths specified in the",
+	    "patch."],
+	  "source_url": "http://enve-omics.ce.gatech.edu/data/public_misc/patch_Silva_SSU_r115.txt"
+	},
+	{
+	  "opt": "--seqinfo",
+	  "arg": "out_file",
+	  "description": ["If passed, it creates a CSV seq-info file",
+	    "compatible with taxtastic."]
+	},
+	{
+	  "opt": "--taxfile",
+	  "arg": "out_file",
+	  "description": "If passed, it creates a simple TSV taxonomy file."
+	},
+	{
+	  "opt": "--ncbi",
+	  "arg": "out_dir",
+	  "description": ["If passed, output folder for the NCBI dump files",
+	    "(e.g., taxdmp)."]
+	},
+	{
+	  "opt": "--warns",
+	  "description": "Verbously display warnings."
+	}
+      ]
+    }
+  ]
+}