miga-base 0.3.0.0 → 0.3.0.1

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

@@ -0,0 +1,208 @@
+{
+  "tasks": [
+    {
+      "task": "FastQ.filter.pl",
+      "description": "Extracts a subset of sequences from a FastQ file.",
+      "see_also": ["FastA.filter.pl"],
+      "help_arg": "-h",
+      "options": [
+        {
+	  "name": "Reverse list",
+	  "opt": "-r",
+	  "description": "Extracts sequences NOT present in the list."
+	},
+	{
+	  "name": "Quiet",
+	  "opt": "-q",
+	  "description": "Runs quietly."
+	},
+	{
+	  "name": "List",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "List of sequences to extract."
+	},
+	{
+	  "name": "Seqs.fq",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "FastQ file containing the superset of sequences."
+	},
+	">",
+	{
+	  "name": "Subset.fq",
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": "FastQ file to be created."
+	}
+      ]
+    },
+    {
+      "task": "FastQ.interpose.pl",
+      "description": ["Interposes sequences in FastQ format from two files",
+        "into one output file. If more than two files are provided, the script",
+	"will interpose all the input files."],
+      "warn": ["Note that this script will check for the consistency of the",
+        "names (assuming a pair of related reads contains the same name",
+	"varying only in a trailing slash (/) followed by a digit. If you want",
+	"to turn this feature off just set the -T option to zero. If you want",
+	"to decrease the sampling period (to speed the script up) or increase",
+	"it (to make it more sensitive to errors) just change -T option",
+	"accordingly."],
+      "see_also": ["FastQ.split.pl","FastA.interpose.pl"],
+      "help_arg": "",
+      "options": [
+        {
+	  "name": "Checking period",
+	  "opt": "-T",
+	  "arg": "integer",
+	  "default": 1000,
+	  "description": "Sampling period for names evaluation."
+	},
+	{
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": "Output FastQ file."
+	},
+	{
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "First input FastQ file."
+	},
+	{
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "Second input FastQ file."
+	},
+	{
+	  "arg": "in_file",
+	  "multiple_sep": " ",
+	  "description": "Any additional input FastQ files."
+	}
+      ]
+    },
+    {
+      "task": "FastQ.offset.pl",
+      "description": ["There are several FastQ formats. This script takes a",
+        "FastQ in any of them, identifies the type of FastQ (this is, the",
+	"offset), and generates a FastQ with the given offset."],
+      "warn": ["Note that Solexa+64 FastQ can cause problematic values when",
+        "using the offset 33, since there is no equivalent in Phred+33 for",
+	"negative values (the range of Solexa+64 is -5 to 40)."],
+      "help_arg": "",
+      "options": [
+        {
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": ["Input file in FastQ format (range is automatically",
+	    "detected)."]
+	},
+	{
+	  "name": "Offset",
+	  "arg": "integer",
+	  "default": 33,
+	  "mandatory": true,
+	  "description": ["Offset to use for the output. Use 0 (zero) to",
+	    "detect the input format and exit."]
+	},
+	{
+	  "opt": "force",
+	  "description": ["If set, turns errors into warnings and continues.",
+	    "Out-of-range values are set to the closest range limit."]
+	},
+	">",
+	{
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": ["Output file in FastQ format with the specified",
+	    "offset."]
+	}
+      ]
+    },
+    {
+      "task": "FastQ.split.pl",
+      "description": ["Splits a FastQ file into several FastQ files. This",
+        "script can be used to separate interposed sister reads using any even",
+        "number of output files."],
+      "help_arg": "",
+      "see_also": ["FastQ.interpose.pl","FastA.split.pl"],
+      "options": [
+        {
+          "name": "in_file.fq",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input file in FastQ format."
+        },
+        {
+          "name": "out_base",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": ["Prefix for the name of the output files. It will be",
+            "appended with .<i>.fastq, where <i> is a consecutive number",
+            "starting in 1."]
+        },
+        {
+          "name": "no_files",
+          "arg": "integer",
+          "default": 2,
+          "description": "Number of files to generate."
+        }
+      ]
+    },
+    {
+      "task": "FastQ.tag.rb",
+      "description": "Generates easy-to-parse tagged reads from FastQ files.",
+      "see_also": ["FastA.tag.rb"],
+      "help_arg": "--help",
+      "options": [
+        {
+	  "name": "Input file",
+	  "opt": "--in",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "FastQ file containing the sequences."
+	},
+	{
+	  "name": "Output file",
+	  "opt": "--out",
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": "FastQ to create."
+	},
+	{
+	  "opt": "--prefix",
+	  "arg": "string",
+	  "description": "Prefix to use in all IDs."
+	},
+	{
+	  "opt": "--suffix",
+	  "arg": "string",
+	  "description": "Suffix to use in all IDs."
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly (no STDERR output)."
+	}
+      ]
+    },
+    {
+      "task": "FastQ.toFastA.awk",
+      "description": "Translates FastQ files into FastA.",
+      "help_arg": "'' --help",
+      "options": [
+	"<",
+	{
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "Input FastQ file."
+	},
+	">",
+	{
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": "Output FastA file."
+	}
+      ]
+    }
+  ]
+}

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

@@ -0,0 +1,126 @@
+{
+  "tasks": [
+    {
+      "task": "Table.barplot.R",
+      "description": "Creates nice barplots from tab-delimited tables.",
+      "requires": [ { "r_package": "optparse" } ],
+      "help_arg": "--help",
+      "options": [
+        {
+	  "name": "Input file",
+	  "opt": "--x",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": ["A tab-delimited file containing header (first row)",
+	    "and row names (first column)."]
+	},
+	{
+	  "opt": "--sizes",
+	  "arg": "string",
+	  "description": ["A numeric vector containing the real size of the",
+	    "samples (columns) in the same order of the input table. If set,",
+	    "the values are assumed to be 100%, otherwise the sum of the",
+	    "columns is used. Separate values by commas."]
+	},
+	{
+	  "opt": "--top",
+	  "arg": "integer",
+	  "default": 25,
+	  "description": ["Maximum number of categories to display. Any",
+	    "additional categories will be listed as 'Others'."]
+	},
+	{
+	  "opt": "--colors-per-group",
+	  "arg": "integer",
+	  "default": 9,
+	  "description": ["Number of categories in the first two saturation",
+	    "groups of colors. The third group contains the remaining",
+	    "categories if needed."]
+	},
+	{
+	  "opt": "--bars-width",
+	  "arg": "integer",
+	  "default": 4,
+	  "description": "Width of the barplot with respect to the legend."
+	},
+	{
+	  "opt": "--legend-ncol",
+	  "arg": "integer",
+	  "default": 1,
+	  "description": "Number of columns in the legend."
+	},
+	{
+	  "opt": "--other-col",
+	  "arg": "string",
+	  "default": "#000000",
+	  "description": "Color of the 'Others' category."
+	},
+	{
+	  "opt": "--add-trend",
+	  "description": ["Controls if semi-transparent areas are to be",
+	    "plotted between the bars to connect the regions (trend regions)."]
+	},
+	{
+	  "opt": "--organic-trend",
+	  "description": ["Controls if the trend regions are to be smoothed",
+	    "(curves). By default, trend regions have straight edges. If TRUE,",
+	    "forces add.trend=TRUE."]
+	},
+	{
+	  "opt": "--sort-by",
+	  "arg": "string",
+	  "default": "median",
+	  "description": ["Any function that takes a numeric vector and",
+	    "returns a numeric scalar. This function is applied to each row,",
+	    "and the resulting values are used to sort the rows",
+	    "(decreasingly). Good options include: sd, min, max, mean, median."]
+	},
+	{
+	  "opt": "--min-report",
+	  "arg": "integer",
+	  "default": 101,
+	  "description": ["Minimum percentage to report the value in the plot.",
+	    "Any value above 100 indicates that no values are to be reported."]
+	},
+	{
+	  "opt": "--order",
+	  "arg": "string",
+	  "description": ["Controls how the rows should be ordered. If empty",
+	    "(default), sort.by is applied per row and the results are sorted",
+	    "decreasingly. If NA, no sorting is performed, i.e., the original",
+	    "order is respected. If a vector is provided, it is assumed to be",
+	    "the custom order to be used (either by numeric index or by row",
+	    "names). Separate values by commas."]
+	},
+	{
+	  "opt": "--col",
+	  "arg": "string",
+	  "description": ["Colors to use. If provided, overrides the variables",
+	    "`top` and `colors.per.group`, but `other.col` is still used if",
+	    "the vector is insufficient for all the rows. Separate values by",
+            "commas. An additional palette is available when using value",
+            "'coto' (palette contributed by Luis (Coto) Orellana)."]
+	},
+	{
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": "Output file in PDF format."
+	},
+	{
+	  "name": "width",
+	  "arg": "float",
+	  "mandatory": true,
+	  "default": 7,
+	  "description": "Width of the plot (in inches)."
+	},
+	{
+	  "name": "height",
+	  "arg": "float",
+	  "mandatory": true,
+	  "default": 7,
+	  "description": "Height of the plot (in inches)."
+	}
+      ]
+    }
+  ]
+}

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

@@ -0,0 +1,339 @@
+{
+  "tasks": [
+    {
+      "task": "ogs.annotate.rb",
+      "description": ["Annotates Orthology Groups (OGs) using one or more",
+        "reference genomes."],
+      "see_also": ["ogs.mcl.rb"],
+      "help_arg": "--help",
+      "options": [
+        {
+	  "name": "Input file",
+	  "opt": "--in",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": ["Input file containing the OGs (as generated by",
+	    "ogs.mcl.rb)."]
+	},
+	{
+	  "name": "Output file",
+	  "opt": "--out",
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": "Output file containing the annotated OGs."
+	},
+	{
+	  "name": "Annotations",
+	  "opt": "-a",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "multiple_sep": ",",
+	  "description": ["Input file(s) containing the annotations. One or",
+	    "more tab-delimited files with the gene names in the first column",
+	    "and the annotation in the second."]
+	},
+	{
+	  "opt": "--format",
+	  "arg": "string",
+	  "default": "(\\S+)\\.txt",
+	  "description": ["Format of the filenames for the annotation files,",
+	    "using regex syntax."]
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly (no STDERR output)."
+	}
+      ]
+    },
+    {
+      "task": "ogs.core-pan.rb",
+      "description": ["Subsamples the genomes in a set of Orthology Groups",
+        "(OGs) and estimates the trend of core genome and pangenome sizes."],
+      "help_arg": "--help",
+      "requires": [
+        {
+	  "ruby_gem": "json"
+	}
+      ],
+      "see_also": ["ogs.mcl.rb"],
+      "options": [
+        {
+	  "opt": "--ogs",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "Input file containing the precomputed OGs."
+	},
+	{
+	  "opt": "--summary",
+	  "arg": "out_file",
+	  "description": ["Output file in tabular format with summary",
+	    "statistics."]
+	},
+	{
+	  "opt": "--tab",
+	  "arg": "out_file",
+	  "description": "Output file in tabular format."
+	},
+	{
+	  "opt": "--json",
+	  "arg": "out_file",
+	  "description": "Output file in JSON format."
+	},
+	{
+	  "opt": "--replicates",
+	  "arg": "integer",
+	  "description": "Number of replicates to estimate.",
+	  "default": 100
+	},
+	{
+	  "opt": "--threads",
+	  "arg": "integer",
+	  "description": "Children threads to spawn."
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly (no STDERR output)."
+	}
+      ]
+    },
+    {
+      "task": "ogs.extract.rb",
+      "description": ["Extracts sequences of Orthology Groups (OGs) from",
+        "genomes (proteomes)."],
+      "help_arg": "--help",
+      "see_also": ["ogs.mcl.rb"],
+      "options": [
+        {
+	  "name": "Input file",
+	  "opt": "--in",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": ["Input file containing the OGs (as generated by",
+	    "ogs.mcl.rb)."]
+	},
+	{
+	  "name": "Output file",
+	  "opt": "--out",
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": "Output directory where to place extracted sequences."
+	},
+	{
+	  "name": "Sequences",
+	  "opt": "--seqs",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": ["Path to the proteomes in FastA format, using '%s'",
+	    "to denote the genome. For example: /path/to/seqs/%s.faa."]
+	},
+	{
+	  "opt": "--core",
+	  "arg": "float",
+	  "description": ["Use only OGs present in at least this fraction of",
+	    "the genomes. To use only the strict core genome*, use --core 1."],
+	  "note": ["* To use only the unus genome (OGs with exactly one gene",
+	    "per genome), use: --core 1 --duplicates 1."]
+	},
+	{
+	  "opt": "--duplicates",
+	  "arg": "integer",
+	  "description": ["Use only OGs with less than this number of",
+	    "in-paralogs in a genome. To use only genes without in-paralogs*,",
+	    "use --duplicates 1."],
+	  "note": ["* To use only the unus genome (OGs with exactly one gene",
+	    "per genome), use: --core 1 --duplicates 1."]
+	},
+	{
+	  "opt": "--per-genome",
+	  "description": ["If set, the output is generated per genome. By",
+	    "default, the output is per OG."]
+	},
+	{
+	  "opt": "--prefix",
+	  "description": ["If set, each sequence is prefixed with the genome",
+	    "name (or OG number, if --per-genome) and a dash."]
+	},
+	{
+	  "opt": "--rand",
+	  "description": ["Get only one gene per genome per OG (random)",
+	    "regardless of in-paralogs. By default all genes are extracted."]
+	},
+	{
+	  "opt": "--first",
+	  "description": ["Get only one gene per genome per OG (first)",
+	    "regardless of in-paralogs. By default all genes are extracted.",
+            "Takes precedence over --rand."]
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly (no STDERR output)."
+	}
+      ]
+    },
+    {
+      "task": "ogs.mcl.rb",
+      "description": ["Identifies Orthology Groups (OGs) in Reciprocal Best",
+        "Matches (RBM) between all pairs in a collection of genomes, using the",
+	"Markov Cluster Algorithm."],
+      "see_also": ["ogs.annotate.rb", "ogs.core-pan.rb", "ogs.extract.rb",
+        "ogs.stats.rb"],
+      "cite": [["Enright et al, 2002, NAR",
+        "http://dx.doi.org/10.1093/nar/30.7.1575"]],
+      "help_arg": "--help",
+      "options": [
+        {
+	  "opt": "--out",
+	  "arg": "out_file",
+	  "mandatory": true,
+	  "description": "Output file containing the detected OGs."
+	},
+	{
+	  "opt": "--dir",
+	  "arg": "in_dir",
+	  "description": "Directory containing the RBM files.",
+	  "note": "Mandatory, unless --abc is set to a non-empty file."
+	},
+	{
+	  "opt": "--format",
+	  "arg": "string",
+	  "description": ["Format of the filenames for the RBM files (within",
+	    "--dir), using regex syntax."],
+	  "default": "(\\S+)-(\\S+)\\.rbm"
+	},
+	{
+	  "opt": "--inflation",
+	  "arg": "float",
+	  "description": "Inflation parameter for MCL clustering.",
+	  "default": 1.5
+	},
+	{
+	  "opt": "--blind",
+	  "description": ["If set, computes clusters without taking bitscore",
+	    "into account."]
+	},
+	{
+	  "opt": "--evalue",
+	  "description": ["If set, uses the e-value to weight edges, instead",
+	    "of the default Bit-Score."]
+	},
+	{
+	  "opt": "--identity",
+	  "description": ["If set, uses the identity to weight edges, instead",
+	    "of the default Bit-Score."]
+	},
+	{
+	  "opt": "--best-match",
+	  "description": ["If set, it assumes best-matches instead reciprocal",
+	    "best matches."]
+	},
+	{
+	  "opt": "--mcl-bin",
+	  "arg": "in_dir",
+	  "description": ["Path to the directory containing the mcl binaries.",
+	    "By default, assumed to be in the PATH."]
+	},
+	{
+	  "name": "abc",
+	  "arg": "out_file",
+	  "opt": "--abc",
+	  "description": "Use this abc file instead of a temporal file."
+	},
+	{
+	  "opt": "--threads",
+	  "arg": "integer",
+	  "default": 2,
+	  "description": "Number of threads to use."
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly (no STDERR output)."
+	}
+      ]
+    },
+    {
+      "task": "ogs.rb",
+      "description": ["Identifies Orthology Groups (OGs) in Reciprocal Best",
+        "Matches (RBM) between all pairs in a collection of genomes."],
+      "warn": ["This script suffers from chaining effect and is very",
+        "sensitive to spurious connections, because it applies a greedy",
+	"clustering algorithm. For most practical purposes, the use of this",
+	"script is discouraged and `ogs.mcl.rb` should be preferred."],
+      "help_arg": "--help",
+      "see_also": ["ogs.mcl.rb"],
+      "options": [
+        {
+	  "opt": "--out",
+	  "mandatory": true,
+	  "arg": "out_file",
+	  "description": "Output file containing the detected OGs."
+	},
+	{
+	  "opt": "--dir",
+	  "arg": "in_dir",
+	  "description": "Directory containing the RBM files.",
+	  "note": "Required unless --pre-ogs is passed."
+	},
+	{
+	  "opt": "--pre-ogs",
+	  "arg": "in_file",
+	  "multiple_sep": ",",
+	  "description": "Pre-computed OGs file(s), separated by commas."
+	},
+	{
+	  "opt": "--unchecked",
+	  "description": "Do not check internal redundancy in OGs."
+	},
+	{
+	  "opt": "--format",
+	  "arg": "string",
+	  "default": "(\\S+)-(\\S+)\\.rbm",
+	  "description": ["Format of the filenames for the RBM files (within",
+	    "-d), using regex syntax."]
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly (no STDERR output)."
+	}
+      ]
+    },
+    {
+      "task": "ogs.stats.rb",
+      "description": ["Estimates some descriptive statistics on a set of",
+        "Orthology Groups (OGs)."],
+      "see_also": ["ogs.mcl.rb"],
+      "help_arg": "--help",
+      "requires": [ { "ruby_gem": "json" } ],
+      "options": [
+        {
+	  "opt": "--ogs",
+	  "arg": "in_file",
+	  "mandatory": true,
+	  "description": "Input file containing the precomputed OGs."
+	},
+	{
+	  "opt": "--json",
+	  "arg": "out_file",
+	  "description": "Output file in JSON format."
+	},
+	{
+	  "opt": "--tab",
+	  "arg": "out_file",
+	  "description": "Output file in tabular format."
+	},
+	{
+	  "opt": "--transposed-tab",
+	  "arg": "out_file",
+	  "description": "Output file in transposed tabular format."
+	},
+	{
+	  "opt": "--auto",
+	  "description": "Run completely quiertly (no STDERR or STDOUT)."
+	},
+	{
+	  "opt": "--quiet",
+	  "description": "Run quietly (no STDERR output)."
+	}
+      ]
+    }
+  ]
+}