miga-base 1.2.17.0 → 1.2.17.1

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

@@ -0,0 +1,802 @@
+{
+  "tasks": [
+    {
+      "task": "FastA.N50.pl",
+      "description": ["Calculates the N50 value of a set of sequences.",
+        "Alternatively, it can calculate other N** values. It also calculates",
+        "the total number of sequences, the total added length, and the",
+        "longest sequence length."],
+      "help_arg": "",
+      "see_also": ["FastA.length.pl"],
+      "options": [
+        {
+          "name": "Sequences",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "A FastA file containing the sequences."
+        },
+        {
+          "name": "Minimum length",
+          "arg": "integer",
+          "description": "Minimum length to take into consideration.",
+          "default": 0
+        },
+        {
+          "name": "NXX",
+          "arg": "integer",
+          "description": "Value NXX to calculate.",
+          "default": 50
+        }
+      ]
+    },
+    {
+      "task": "FastA.filter.pl",
+      "description": "Extracts a subset of sequences from a FastA file.",
+      "help_arg": "-h",
+      "see_also": ["FastQ.filter.pl"],
+      "options": [
+        {
+          "opt": "-r",
+          "description": ["Reverse list. Extracts sequences NOT present in the",
+            "list."]
+        },
+        {
+          "opt": "-q",
+          "description": "Runs quietly."
+        },
+        {
+          "name": "List",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "List of sequences to extract."
+        },
+        {
+          "name": "Sequences",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "FastA file containing the superset of sequences."
+        },
+        ">",
+        {
+          "name": "Subset",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "FastA file to be created."
+        }
+      ]
+    },
+    {
+      "task": "FastA.filterLen.pl",
+      "description": "Filters a multi-FastA file by length.",
+      "requires": [ { "perl_lib": "Bio::SeqIO" } ],
+      "cite": [["Stajich et al, 2002, GRes",
+        "http://dx.doi.org/10.1101/gr.361602"]],
+      "help_arg": "",
+      "options": [
+        {
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input FastA file."
+        },
+        {
+          "name": "Minimum length",
+          "arg": "integer",
+          "mandatory": true,
+          "description": "Minimum length to report a sequence."
+        },
+        ">",
+        {
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Filtered FastA file."
+        }
+      ]
+    },
+    {
+      "task": "FastA.filterN.pl",
+      "description": ["Filter sequences by N-content and presence of long",
+        "homopolymers."],
+      "help_arg": "",
+      "options": [
+        {
+          "name": "Sequences",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input file in FastA format."
+        },
+        {
+          "name": "Content",
+          "arg": "float",
+          "default": 0.5,
+          "mandatory": true,
+          "description": ["A number between 0 and 1 indicating the maximum",
+            "proportion of Ns (1 to turn off, 0.5 by default)."]
+        },
+        {
+          "name": "Stretch",
+          "arg": "integer",
+          "default": 100,
+          "description": ["A number indicating the maximum number of",
+            "consecutive identical nucleotides allowed (0 to turn off, 100 by",
+            "default)."]
+        },
+        ">",
+        {
+          "name": "Filtered",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Filtered set of sequences."
+        }
+      ]
+    },
+    {
+      "task": "FastA.gc.pl",
+      "description": "Estimates the G+C content of sequences.",
+      "help_arg": "",
+      "options": [
+        {
+          "name": "seqs.fa",
+          "arg": "in_file",
+          "multiple_sep": " ",
+          "mandatory": true,
+          "description": "One or more FastA files."
+        },
+        ">",
+        {
+          "name": "gc.txt",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "A table with the G+C content of the sequences."
+        }
+      ]
+    },
+    {
+      "task": "FastA.interpose.pl",
+      "description": ["Interpose sequences in FastA format from two files into",
+        "one output file. If more than two files are provided, the script will",
+        "interpose all the input files."],
+      "see_also": ["FastA.split.rb","FastQ.interpose.pl"],
+      "warn": ["Please 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."],
+      "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 FastA file."
+        },
+        {
+          "name": "Input FastA 1",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "First FastA file."
+        },
+        {
+          "name": "Input FastA 2",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Second FastA file."
+        },
+        {
+          "name": "Additional FastA",
+          "arg": "in_file",
+          "multiple_sep": " ",
+          "description": "Any additional FastA files (or none)."
+        }
+      ]
+    },
+    {
+      "task": "FastA.length.pl",
+      "description": "Returns the length of sequences in (multi-)FastA.",
+      "see_also": ["FastA.N50.pl"],
+      "help_arg": "",
+      "options": [
+        {
+          "arg": "in_file",
+          "multiple_sep": " ",
+          "mandatory": true,
+          "description": "One or more FastA files."
+        },
+        ">",
+        {
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "A table with the lengths of the sequences."
+        }
+      ]
+    },
+    {
+      "task": "FastA.mask.rb",
+      "description": "Mask sequence region(s) in a FastA file.",
+      "help_arg": "--help",
+      "options": [
+        {
+          "opt": "--in",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input FastA file."
+        },
+        {
+          "opt": "--out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Output FastA file."
+        },
+        {
+          "opt": "--regions",
+          "arg": "string",
+          "mandatory": true,
+          "description": ["Regions to mask separated by commas.",
+            "Each region must be in the format \"sequence_id:from..to\"."]
+        },
+        {
+          "opt": "--symbol",
+          "arg": "string",
+          "default": "N",
+          "description": "Character used to mask the region(s)."
+        },
+        {
+          "opt": "--trim",
+          "description": ["Trim masked regions extending to the edge of a",
+            "sequence."]
+        },
+        {
+          "opt": "--wrap",
+          "arg": "integer",
+          "default": 70,
+          "description": ["Line length to wrap sequences. Use 0 to generate",
+            "1-line sequences."]
+        }
+      ]
+    },
+    {
+      "task": "FastA.qlen.pl",
+      "description": ["Calculates the quartiles of the length in a set of",
+        "sequences. The Q2 is also known as the median. Q0 is the minimum",
+        "length, and Q4 is the maximum length. It also calculates TOTAL, the",
+        "added length of the sequences in the file, and AVG, the average",
+        "length."],
+      "help_arg": "",
+      "options": [
+        {
+          "name": "Sequences",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "A FastA file containing the sequences."
+        },
+        {
+          "name": "Minimum Length",
+          "arg": "integer",
+          "default": 0,
+          "description": "The minimum length to take into consideration."
+        }
+      ]
+    },
+    {
+      "task": "FastA.rename.pl",
+      "description": "Renames a set of sequences in FastA format.",
+      "help_arg": "-h",
+      "options": [
+        {
+          "name": "Filter list",
+          "opt": "-f",
+          "description": "Ignore sequences NOT present in the list."
+        },
+        {
+          "name": "Quiet",
+          "opt": "-q",
+          "description": "Runs quietly."
+        },
+        {
+          "name": "List.txt",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": ["Tab-delimited list of sequences, with the original",
+            "ID in the first column and the ID to use in the second."]
+        },
+        {
+          "name": "Seqs.fa",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "FastA file containing the superset of sequences."
+        },
+        ">",
+        {
+          "name": "Renamed.fa",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "FastA file to be created."
+        }
+      ]
+    },
+    {
+      "task": "FastA.revcom.pl",
+      "description": "Reverse-complement sequences in FastA format.",
+      "requires": [ { "perl_lib": "Bio::SeqIO" } ],
+      "cite": [["Stajich et al, 2002, GRes",
+        "http://dx.doi.org/10.1101/gr.361602"]],
+      "help_arg": "--help",
+      "options": [
+        "<",
+        {
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input file in FastA format."
+        },
+        ">",
+        {
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Output file in FastA format."
+        }
+      ]
+    },
+    {
+      "task": "FastA.sample.rb",
+      "description": ["Samples a random set of sequences from a multi-FastA",
+        "file."],
+      "help_arg": "--help",
+      "see_also": "FastA.subsample.pl",
+      "options": [
+        {
+          "name": "Input File",
+          "opt": "--in",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input FastA file (supports .gz compression)."
+        },
+        {
+          "name": "Output file",
+          "opt": "--out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Output FastA file (supports .gz compression)."
+        },
+        {
+          "opt": "--fraction",
+          "arg": "float",
+          "description": ["Fraction of sequences to sample [0-1].",
+            "Mandatory unless Number is provided."]
+        },
+        {
+          "opt": "--number",
+          "arg": "integer",
+          "description": ["Number of sequences to sample.",
+            "Mandatory unless -f is provided."]
+        },
+        {
+          "opt": "--replacement",
+          "description": "Sample with replacement."
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly (no STDERR output)."
+        }
+      ]
+    },
+    {
+      "task": "FastA.slider.pl",
+      "description": "Slices sequences in fixed- or variable-length windows.",
+      "help_arg": "-help",
+      "options": [
+        {
+          "opt": "-seq",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input file in FastA format."
+        },
+        {
+          "opt": "-out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Output file in FastA format."
+        },
+        {
+          "opt": "-win",
+          "arg": "integer",
+          "default": 18,
+          "description": "Window size."
+        },
+        {
+          "opt": "-step",
+          "arg": "integer",
+          "default": 1,
+          "description": "Step size."
+        },
+        {
+          "name": "Length error",
+          "opt": "-lerr",
+          "arg": "integer",
+          "default": 2,
+          "description": "Expected error in chunks length."
+        },
+        {
+          "opt": "-comm",
+          "arg": "select",
+          "values": [0,1],
+          "default": 0,
+          "description": ["Generate FastA comments (leaded by semi-colon) to",
+            "separate input sequences. Set to 0 for no-comments, to 1 for",
+            "comments."]
+        },
+        {
+          "opt": "-short",
+          "arg": "select",
+          "values": [0,1],
+          "default": 0,
+          "description": ["Use chunks shorter than the window size 'as is'.",
+            "Set to 0 to discard those chunks, to 1 to use them."]
+        }
+      ]
+    },
+    {
+      "task": "FastA.split.rb",
+      "description": ["Evenly splits a multi-FastA file into multiple",
+        "multi-FastA files."],
+      "see_also": ["FastA.interpose.pl","FastQ.split.pl"],
+      "help_arg": "--help",
+      "options": [
+        {
+          "opt": "--input",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input FastA file."
+        },
+        {
+          "opt": "--prefix",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Prefix of output FastA files."
+        },
+        {
+          "opt": "--number",
+          "arg": "integer",
+          "default": 12,
+          "description": "Number of output files to produce."
+        },
+        {
+          "opt": "--zero-padded",
+          "description": "Use zero-padded numbers as output index."
+        },
+        {
+          "opt": "--lowercase-letters",
+          "description": "Use lowercase letters as output index."
+        },
+        {
+          "name": "Output format",
+          "opt": "--out",
+          "arg": "string",
+          "default": "%s.%s.fa",
+          "description": ["Format of output filenames, where %s are replaced",
+            "by prefix and index."]
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly (no STDERR output)."
+        }
+      ]
+    },
+    {
+      "task": "FastA.split.pl",
+      "description": "Splits a FastA file into two or more files.",
+      "warn": "Deprecated in favor of FastA.split.rb.",
+      "see_also": ["FastA.split.rb","FastA.interpose.pl","FastQ.split.pl"],
+      "help_arg": "",
+      "options": [
+        {
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input file in FastA format."
+        },
+        {
+          "name": "Out base",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": ["Prefix for the name of the output files. It will be",
+            "appended with .<i>.fa, where <i> is a consecutive number starting",
+            "in 1."]
+        },
+        {
+          "name": "Number of files",
+          "arg": "integer",
+          "default": 12,
+          "description": "Number of files to generate."
+        }
+      ]
+    },
+    {
+      "task": "FastA.subsample.pl",
+      "description": "Subsamples a set of sequences.",
+      "help_arg": "-h",
+      "see_also": "FastA.sample.rb",
+      "options": [
+        {
+          "name": "Fraction",
+          "opt": "-f",
+          "arg": "string",
+          "default": "10",
+          "description": ["Fraction of the library to be sampled (as",
+            "percentage). It can include several values (separated by comma),",
+            "as well as ranges of values in the form 'from-to/by'. For",
+            "example, the -f value 1-5/1,10-50/10,75,99 will produce 12",
+            "subsamples with expected fractions 1%, 2%, 3%, 4%, 5%, 10%, 20%,",
+            "30%, 40%, 50%, 75%, and 99%."]
+        },
+        {
+          "name": "Replicates",
+          "opt": "-r",
+          "arg": "integer",
+          "default": 1,
+          "description": "Number of replicates per fraction."
+        },
+        {
+          "name": "Out base",
+          "opt": "-o",
+          "arg": "out_file",
+          "description": ["Prefix of the output files to be created. The",
+            "output files will have a suffix of the form",
+            "'.fraction-replicate.fa', where 'fraction' is the percentage",
+            "sampled and 'replicate' is an increasing integer for replicates",
+            "of the same fraction. By default: Path to the input file."]
+        },
+        {
+          "name": "Force",
+          "opt": "-F",
+          "description": "Force overwriting output file(s)."
+        },
+        {
+          "name": "Zeroes",
+          "opt": "-z",
+          "description": ["Include leading zeroes in the numeric parts of the",
+            "output files (e.g., file.002.50-01.fa instead of file.2.50-1.fa),",
+            "so that alphabetic sorting of files reflects the sampled",
+            "fraction."]
+        },
+        {
+          "name": "Quiet",
+          "opt": "-q",
+          "description": "Run quietly."
+        },
+        {
+          "arg": "in_file",
+          "mandatory": true,
+          "multiple_sep": " ",
+          "description": "Input multi-FastA file(s)."
+        }
+      ]
+    },
+    {
+      "task": "FastA.tag.rb",
+      "description": "Generates easy-to-parse tagged reads from FastA files.",
+      "see_also": ["FastQ.tag.rb"],
+      "help_arg": "--help",
+      "options": [
+        {
+          "name": "Input file",
+          "opt": "--in",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "FastA file containing the sequences."
+        },
+        {
+          "name": "Output file",
+          "opt": "--out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "FastA file 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": "--defline",
+          "description": "Keep the original defline after a space."
+        },
+        {
+          "opt": "--list",
+          "arg": "in_file",
+          "description": "Reads a list of IDS."
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly (no STDERR output)."
+        }
+      ]
+    },
+    {
+      "task": "FastA.per_file.pl",
+      "description": ["Extracts all the sequences in a multi-FastA into",
+        "multiple single-FastA files."],
+      "see_also": "FastA.split.rb",
+      "help_arg": "",
+      "options": [
+        {
+          "arg": "out_dir",
+          "mandatory": true,
+          "description": "Output directory for the individual files."
+        },
+        {
+          "arg": "in_file",
+          "mandatory": true,
+          "multiple_sep": " ",
+          "description": "Input multi-FastA file(s)."
+        }
+      ]
+    },
+    {
+      "task": "FastA.extract.rb",
+      "description": ["Extracts a list of sequences and/or coordinates from",
+        "multi-FastA files."],
+      "help_arg": "--help",
+      "options": [
+        {
+          "name": "Input file",
+          "opt": "--in",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input FastA file."
+        },
+        {
+          "name": "Output file",
+          "opt": "--out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Output FastA file."
+        },
+        {
+          "name": "Coordinates",
+          "opt": "--coords",
+          "arg": "string",
+          "description": ["Comma-delimited list of coordinates (mandatory",
+            "unless -C is passed).",
+            "The format of the coordinates is SEQ:FROM..TO or SEQ:FROM~LEN:",
+            "SEQ: Sequence ID, or * (asterisk) to extract range from all",
+              "sequences",
+            "FROM: Integer, position of the first base to include (can be",
+              "negative)",
+            "TO: Integer, last base to include (can be negative)",
+            "LEN: Length of the range to extract."]
+        },
+        {
+          "name": "Coordinates file",
+          "opt": "--coords-file",
+          "arg": "in_file",
+          "description": ["File containing the coordinates, one per line.",
+            "Each line must follow the format described for Coordinates."]
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly (no STDERR output)."
+        }
+      ]
+    },
+    {
+      "task": "FastA.fragment.rb",
+      "description": ["Simulates incomplete (fragmented) drafts from complete",
+        "genomes."],
+      "help_arg": "--help",
+      "options": [
+        {
+          "name": "Input file",
+          "opt": "--in",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "FastA file containing the complete sequences."
+        },
+        {
+          "name": "Output file",
+          "opt": "--out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "FastA to create."
+        },
+        {
+          "opt": "--completeness",
+          "arg": "float",
+          "mandatory": true,
+          "description": ["Fraction of genome completeness to simulate from 0",
+            "to 1."]
+        },
+        {
+          "name": "Minimum length",
+          "opt": "--minlen",
+          "arg": "integer",
+          "description": "Minimum fragment length to report.",
+          "default": 500
+        },
+        {
+          "opt": "--sorted",
+          "description": ["Keep fragments sorted as in the input file. By",
+            "default, fragments are shuffled."]
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly (no STDERR output)."
+        }
+      ]
+    },
+    {
+      "task": "FastA.toFastQ.rb",
+      "description": "Creates a FastQ-compliant file from a FastA file.",
+      "see_also": "FastQ.toFastA.awk",
+      "help_arg": "--help",
+      "options": [
+        {
+          "name": "Input FastA",
+          "opt": "--in",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input FastA file (supports .gz compression)."
+        },
+        {
+          "name": "Output FastQ",
+          "opt": "--out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Output FastQ file (supports .gz compression)."
+        },
+        {
+          "opt": "--quality",
+          "arg": "integer",
+          "default": 31,
+          "description": ["PHRED quality score to use (fixed), in the range",
+            "[-5, 41]."]
+        },
+        {
+          "opt": "--encoding",
+          "arg": "integer",
+          "default": 33,
+          "description": "Base encoding (33 or 64)."
+        }
+      ]
+    },
+    {
+      "task": "FastA.wrap.rb",
+      "description": "Wraps sequences in a FastA to a given line length.",
+      "help_arg": "--help",
+      "options": [
+        {
+          "name": "Input FastA",
+          "opt": "--in",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input FastA file."
+        },
+        {
+          "name": "Output FastA",
+          "opt": "--out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Output FastA file."
+        },
+        {
+          "name": "Wrap length",
+          "opt": "--wrap",
+          "arg": "integer",
+          "description": ["Line length to wrap sequences. Use 0 to generate",
+            "1-line sequences."],
+          "default": 70
+        }
+      ]
+    }
+  ]
+}