miga-base 1.2.17.0 → 1.2.17.1

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

@@ -0,0 +1,291 @@
+{
+  "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 checking period 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 the",
+        "checking period 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.maskQual.rb",
+      "description": "Masks low-quality bases in a FastQ file.",
+      "help_arg": "--help",
+      "options": [
+        {
+          "opt": "--input",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": ["Path to the FastQ file containing the sequences.",
+            "Supports compression with .gz extension."]
+        },
+        {
+          "opt": "--output",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": ["Path to the output FastQ file.",
+            "Supports compression with .gz extension."]
+        },
+        {
+          "opt": "--qual",
+          "arg": "integer",
+          "default": 15,
+          "description": "Minimum quality score to allow a base."
+        },
+        {
+          "opt": "--offset",
+          "arg": "integer",
+          "default": 33,
+          "description": "Q-score offset."
+        },
+        {
+          "opt": "--fasta",
+          "description": "Output sequences in FastA format."
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly."
+        }
+      ]
+    },
+    {
+      "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.",
+            "Supports compression with .gz extension."
+          ]
+        },
+        {
+          "name": "Output file",
+          "opt": "--out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": [
+            "FastQ to create.",
+            "Supports compression with .gz extension."
+          ]
+        },
+        {
+          "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.",
+      "see_also": "FastA.toFastQ.rb",
+      "help_arg": "'' --help",
+      "options": [
+        "<",
+        {
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input FastQ file."
+        },
+        ">",
+        {
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Output FastA file."
+        }
+      ]
+    },
+    {
+      "task": "FastQ.test-error.rb",
+      "description": ["Compares the estimated error of sequencing reads",
+        "(Q-score) with observed mismatches (identity against a know",
+        "reference sequence)."],
+      "help_arg": "--help",
+      "options": [
+        {
+          "name": "FastQ",
+          "opt": "--fastq",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "FastQ file containing the sequences."
+        },
+        {
+          "name": "Tabular BLAST",
+          "opt": "--blast",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": ["Tabular BLAST file mapping reads to reference",
+            "sequences."]
+        },
+        {
+          "name": "Output",
+          "opt": "--out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Output tab-delimited file to create."
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly (no STDERR output)."
+        }
+      ]
+    }
+  ]
+}

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/mapping.json

@@ -0,0 +1,137 @@
+{
+  "tasks": [
+    {
+      "task": "BedGraph.tad.rb",
+      "description": ["Estimates the truncated average sequencing depth (TAD)",
+        "from a BedGraph file."],
+      "warn": ["This script doesn't consider zero-coverage positions if",
+        "missing from the file. If you produce your BedGraph file with",
+        "bedtools genomecov and want to consider zero-coverage position, be",
+        "sure to use -bga (not -bg)."],
+      "see_also": ["BedGraph.window.rb",
+        "BlastTab.seqdepth.pl", "BlastTab.seqdepth_ZIP.pl"],
+      "help_arg": "--help",
+      "options": [
+        {
+          "opt": "--input",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input BedGraph file."
+        },
+        {
+          "opt": "--range",
+          "arg": "float",
+          "default": 0.5,
+          "description": ["Central range to consider, between 0 and 1. By",
+            "default: inter-quartile range (0.5)."]
+        },
+        {
+          "opt": "--per-seq",
+          "description": ["Calculate averages per reference sequence, not",
+            "total. Assumes a sorted BedGraph file."]
+        },
+        {
+          "opt": "--length",
+          "description": "Add sequence length to the output."
+        }
+      ]
+    },
+    {
+      "task": "BedGraph.window.rb",
+      "description": ["Estimates the sequencing depth per windows from a",
+        "BedGraph file."],
+      "warn": ["This script doesn't consider zero-coverage positions if",
+        "missing from the file. If you produce your BedGraph file with",
+        "bedtools genomecov and want to consider zero-coverage position, be",
+        "sure to use -bga (not -bg)."],
+      "see_also": ["BedGraph.tad.rb",
+        "BlastTab.seqdepth.pl", "BlastTab.seqdepth_ZIP.pl"],
+      "help_arg": "--help",
+      "options": [
+        {
+          "opt": "--input",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input BedGraph file."
+        },
+        {
+          "name": "Window size",
+          "opt": "--win",
+          "arg": "float",
+          "default": 1000,
+          "description": "Window size, in base pairs."
+        }
+      ]
+    },
+    {
+      "task": "sam.filter.rb",
+      "description": ["Filters a SAM or BAM file by target sequences and/or",
+        "identity."],
+      "see_also": ["anir.rb"],
+      "help_arg": "--help",
+      "options": [
+        {
+          "opt": "--genome",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": ["Genome assembly.",
+            "Supports compression with .gz extension."]
+        },
+        {
+          "opt": "--mapping",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": ["Mapping file.",
+            "Supports compression with .gz extension."]
+        },
+        {
+          "opt": "--out-sam",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": ["Output filtered file in SAM format.",
+            "Supports compression with .gz extension."]
+        },
+        {
+          "opt": "--g-format",
+          "arg": "select",
+          "values": ["fasta", "list"],
+          "default": "fasta",
+          "description": ["Genome assembly format."]
+        },
+        {
+          "opt": "--m-format",
+          "arg": "select",
+          "values": ["sam", "bam"],
+          "default": "sam",
+          "description": ["Mapping file format. SAM supports compression with",
+            ".gz file extension."]
+        },
+        {
+          "opt": "--identity",
+          "arg": "float",
+          "description": "Set a fixed threshold of percent identity.",
+          "default": 95.0
+        },
+        {
+          "opt": "--no-header",
+          "description": "Do not include the headers."
+        },
+        {
+          "opt": "--threads",
+          "arg": "integer",
+          "description": "Threads to use.",
+          "default": 2
+        },
+        {
+          "opt": "--log",
+          "arg": "out_file",
+          "description": "Log file to save output."
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly."
+        }
+      ]
+    }
+  ]
+}