miga-base 1.2.17.0 → 1.2.17.2

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

@@ -0,0 +1,382 @@
+{
+  "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)."
+        }
+      ]
+    },
+    {
+      "task": "clust.rand.rb",
+      "description": ["Calculates the Rand Index and the Adjusted Rand Index",
+        "between two clusterings. The clustering format is a raw text file",
+        "with one cluster per line, each defined as comma-delimited members,",
+        "and a header line (ignored). Note that this is equivalent to the OGs",
+        "format for 1 genome."],
+      "see_also": ["ogs.mcl.rb"],
+      "help_arg": "--help",
+      "cite": [
+        ["Rand, 1971, J Am Stat Assoc",
+          "https://doi.org/10.2307%2F2284239"],
+        ["Hubert & Arabie, 1985, J Classif",
+          "https://doi.org/10.1007%2FBF01908075"]
+      ],
+      "options": [
+        {
+          "name": "Input file 1",
+          "opt": "--clust1",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "First input file."
+        },
+        {
+          "name": "Input file 2",
+          "opt": "--clust2",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Second input file."
+        },
+        {
+          "name": "Precision",
+          "opt": "--prec",
+          "arg": "integer",
+          "description": "Precision to report.",
+          "default": 6
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly (no STDERR output)."
+        }
+      ]
+    }
+  ]
+}