miga-base 1.2.17.0 → 1.2.17.2

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

@@ -0,0 +1,308 @@
+{
+  "tasks": [
+    {
+      "task": "Table.df2dist.R",
+      "description": ["Transform a tab-delimited list of distances into a",
+        "squared matrix."],
+      "help_arg": "--help",
+      "requires": [ { "r_package": "optparse" } ],
+      "options": [
+        {
+          "name": "Input list",
+          "opt": "--x",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "A tab-delimited table with the distances."
+        },
+        {
+          "opt": "--obj1-index",
+          "arg": "integer",
+          "default": 1,
+          "description": ["Index of the column containing the ID of the object",
+            "1."]
+        },
+        {
+          "opt": "--obj2-index",
+          "arg": "integer",
+          "default": 2,
+          "description": ["Index of the column containing the ID of the object",
+            "2."]
+        },
+        {
+          "opt": "--dist-index",
+          "arg": "integer",
+          "default": 3,
+          "description": "Index of the column containing the distance."
+        },
+        {
+          "opt": "--default-d",
+          "arg": "integer",
+          "description": "Default value for missing values. NA if empty."
+        },
+        {
+          "opt": "--max-sim",
+          "arg": "float",
+          "description": ["If not-empty, assumes that the values are",
+            "similarity (not distance) and this is the maximum similarity",
+            "(corresponding to distance 0). Applies transformation:",
+            "distance = (max.sim - values)/max.sim."]
+        },
+        {
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Output squared matrix in tab-separated values format."
+        }
+      ]
+    },
+    {
+      "task": "Table.filter.pl",
+      "description": ["Extracts (and re-orders) a subset of rows from a raw",
+        "table."],
+      "help_arg": "",
+      "options": [
+        {
+          "name": "Key",
+          "opt": "-k",
+          "arg": "integer",
+          "default": 1,
+          "description": "Column of the table to use as key to filter."
+        },
+        {
+          "name": "Sep",
+          "opt": "-s",
+          "arg": "string",
+          "description": ["String to use as separation between rows. By",
+            "default, tabulation."]
+        },
+        {
+          "name": "Inverse",
+          "opt": "-i",
+          "description": ["If set, reports the inverse of the list (i.e.,",
+            "reports only rows absent in the list). Implies 'No re-order'."]
+        },
+        {
+          "name": "Header",
+          "opt": "-h",
+          "description": "Keep first row of the table (header) untouched."
+        },
+        {
+          "name": "No re-order",
+          "opt": "-n",
+          "description": ["The output has the same order of the table. By",
+            "default, it prints in the order of the list."]
+        },
+        {
+          "name": "List",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "List of IDs to extract."
+        },
+        {
+          "name": "Table",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Table file containing the superset."
+        },
+        ">",
+        {
+          "name": "Subset",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Table file to be created."
+        }
+      ]
+    },
+    {
+      "task": "Table.merge.pl",
+      "description": "Merges multiple (two-column) lists into one table.",
+      "see_also": ["Table.split.pl"],
+      "help_arg": "",
+      "options": [
+        {
+          "name": "Strings",
+          "opt": "-s",
+          "description": ["Values are read as Strings. By default, values are",
+            "read as numbers."]
+        },
+        {
+          "name": "Input delimiter",
+          "opt": "-i",
+          "arg": "string",
+          "description": "Input field-delimiter. By default, tabulation."
+        },
+        {
+          "name": "Output delimiter",
+          "opt": "-o",
+          "arg": "string",
+          "description": "Output field-delimiter. By default: tabulation."
+        },
+        {
+          "name": "No header",
+          "opt": "-n",
+          "description": ["By default, the header is determined by the file",
+            "names."]
+        },
+        {
+          "name": "Empty",
+          "opt": "-e",
+          "description": ["Default string when no value is found. By default,",
+            "the 'empty' value is 0 if values are numeric (i.e., unless -s is",
+            "set) or an empty string otherwise."]
+        },
+        {
+          "name": "Header",
+          "opt": "-h",
+          "arg": "string",
+          "default": "Tag",
+          "description": "Header of the first column, containing the IDs."
+        },
+        {
+          "name": "Header format",
+          "opt": "-H",
+          "arg": "string",
+          "default": "(?:.*/)?([^\\.]+)",
+          "description": ["Format of filenames capturing the column header in",
+            "the first capturing parenthesis. Non-capturing paretheses can be",
+            "defined as (?:...). By default: '(?:.*/)?([^\\.]+)', which",
+            "captures the part of the basename of the file before the first",
+            "dot (if any)."]
+        },
+        {
+          "name": "Rows to ignore",
+          "opt": "-r",
+          "arg": "integer",
+          "default": 0,
+          "description": "Number of leading rows to ignore in the input files."
+        },
+        {
+          "arg": "in_file",
+          "mandatory": true,
+          "multiple_sep": " ",
+          "description": "Input two-column lists."
+        },
+        ">",
+        {
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Merged table."
+        }
+      ]
+    },
+    {
+      "task": "Table.round.rb",
+      "description": "Rounds numbers in a table.",
+      "help_arg": "--help",
+      "options": [
+        {
+          "name": "Input file",
+          "opt": "--in",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input table."
+        },
+        {
+          "name": "Output file",
+          "opt": "--out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Output table."
+        },
+        {
+          "name": "Decimals",
+          "opt": "--ndigits",
+          "arg": "integer",
+          "default": 0,
+          "description": "Number of decimal digits."
+        },
+        {
+          "opt": "--floor",
+          "description": ["Floors the values instead of rounding them. Ignores",
+            "'Decimals'."]
+        },
+        {
+          "opt": "--ceil",
+          "description": ["Ceils the values instead of rounding them. Ignores",
+            "'Decimals'."]
+        },
+        {
+          "opt": "--delimiter",
+          "arg": "string",
+          "description": "String delimiting columns. By default, tabulation."
+        }
+      ]
+    },
+    {
+      "task": "Table.split.pl",
+      "description": ["Split a file with multiple columns into multiple",
+        "two-columns lists."],
+      "see_also": ["Table.merge.pl"],
+      "help_arg": "",
+      "options": [
+        {
+          "name": "Input delimiter",
+          "opt": "-i",
+          "arg": "string",
+          "description": "Input field-delimiter. By default, tabulation."
+        },
+        {
+          "name": "Out prefix",
+          "opt": "-o",
+          "arg": "string",
+          "description": "Prefix of the output files."
+        },
+        {
+          "name": "Output directory",
+          "opt": "-d",
+          "arg": "out_dir",
+          "description": "Output directory."
+        },
+        {
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input table."
+        }
+      ]
+    },
+    {
+       "task": "Table.replace.rb",
+       "description": "Replace a field in a table using a mapping file.",
+       "help_arg": "--help",
+       "options": [
+         {
+           "opt": "--map",
+           "arg": "in_file",
+           "mandatory": true,
+           "description": "Mapping file with two columns (key and replacement)."
+         },
+         {
+           "opt": "--in",
+           "arg": "in_file",
+           "mandatory": true,
+           "description": "Input table."
+         },
+         {
+           "opt": "--out",
+           "arg": "out_file",
+           "mandatory": true,
+           "description": "Output table."
+         },
+         {
+           "opt": "--key",
+           "arg": "integer",
+           "default": 1,
+           "description": "Column to replace in Input table."
+         },
+         {
+           "opt": "--unknown",
+           "arg": "string",
+           "description": "String to use whenever the key is not found in Map."
+         },
+         {
+           "opt": "--delimiter",
+           "arg": "string",
+           "description": "String delimiting columns. By default, tabulation."
+         }
+      ]
+    }
+  ]
+}

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

@@ -0,0 +1,68 @@
+{
+  "tasks": [
+    {
+      "task": "Newick.autoprune.R",
+      "description": ["Automatically prunes a tree, to keep representatives of",
+        "each clade."],
+      "requires": [ { "r_package": "optparse" }, { "r_package": "ape" } ],
+      "cite": [["Paradis et al, 2004, Bioinf",
+        "http://dx.doi.org/10.1093/bioinformatics/btg412"]],
+      "help_arg": "--help",
+      "options": [
+        {
+          "name": "Input tree",
+          "opt": "--t",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "A tree to prune in Newick format."
+        },
+        {
+          "opt": "--dist-quantile",
+          "arg": "float",
+          "default": 0.25,
+          "description": "The quantile of edge lengths."
+        },
+        {
+          "opt": "--min_dist",
+          "arg": "float",
+          "description": ["The minimum distance to allow between two tips. If",
+            "not set, dist.quantile is used instead to calculate it."]
+        },
+        {
+          "opt": "--quiet",
+          "description": ["Boolean indicating if the function must run without",
+            "output."]
+        },
+        {
+          "opt": "--max_iters",
+          "arg": "integer",
+          "default": 1000,
+          "description": "Maximum number of iterations."
+        },
+        {
+          "opt": "--min_nodes_random",
+          "arg": "integer",
+          "default": 40000,
+          "description": ["Minimum number of nodes to trigger 'tip-pairs'",
+            "nodes sampling. This sampling is less reproducible and more",
+            "computationally expensive, but it's the only solution if the",
+            "cophenetic matrix exceeds 2^31-1 entries; above that, it cannot",
+            "be represented in R."]
+        },
+        {
+          "opt": "--random_nodes_frx",
+          "arg": "float",
+          "default": 1.0,
+          "description": ["Fraction of the nodes to be sampled if more than",
+            "'Min nodes random'."]
+        },
+        {
+          "arg": "out_file",
+          "mandatory": true,
+          "description": ["Output file in Newick format containing the pruned",
+            "tree."]
+        }
+      ]
+    }
+  ]
+}

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

@@ -0,0 +1,111 @@
+{
+  "tasks": [
+    {
+      "task": "VCF.SNPs.rb",
+      "description": ["Counts the number of Single-Nucleotide Polymorphisms",
+        "(SNPs) in a VCF file."],
+      "help_arg": "--help",
+      "options": [
+        {
+          "opt": "--input",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input file in Variant Call Format (VCF)."
+        },
+        {
+          "name": "Filtered VCF",
+          "opt": "--out",
+          "arg": "out_file",
+          "description": "Output (filtered) file in Variant Call Format (VCF)."
+        },
+        {
+          "name": "Min DP",
+          "opt": "--min-dp",
+          "arg": "integer",
+          "description": "Minimum number of reads covering the position.",
+          "default": 4
+        },
+        {
+          "name": "Max DP",
+          "opt": "--max-dp",
+          "arg": "integer",
+          "description": ["Maximum number of reads covering the position. By",
+            "default no limit."]
+        },
+        {
+          "name": "Min Ref-DP",
+          "opt": "--min-ref-dp",
+          "arg": "integer",
+          "description": "Minimum number of reads supporting the REF allele.",
+          "default": 2
+        },
+        {
+          "name": "Min Alt-DP",
+          "opt": "--min-alt-dp",
+          "arg": "integer",
+          "description": "Minimum number of reads supporting the ALT allele.",
+          "default": 2
+        },
+        {
+          "opt": "--min-quality",
+          "arg": "float",
+          "description": "Minimum quality of the position mapping.",
+          "default": 0.0
+        },
+        {
+          "opt": "--min-shannon",
+          "arg": "integer",
+          "description": "Minimum information content (in bits, from 0 to 1).",
+          "default": 0.0
+        },
+        {
+          "opt": "--indels",
+          "description": "Process indels."
+        }
+      ]
+    },
+    {
+      "task": "VCF.KaKs.rb",
+      "description": ["Estimates the Ka/Ks ratio from the SNPs in a VCF file.",
+        "Ka and Ks are corrected using pseudo-counts, but no corrections for",
+        "multiple substitutions are applied."],
+      "help_arg": "--help",
+      "see_also": ["VCF.SNPs.rb"],
+      "options": [
+        {
+          "opt": "--input",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input file in Variant Call Format (VCF)."
+        },
+        {
+          "opt": "--seqs",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input gene sequences (nucleotides) in FastA format."
+        },
+        {
+          "name": "Synonymous fraction",
+          "opt": "--syn-frx",
+          "arg": "float",
+          "description": ["Fraction of synonymous substitutions. If passed,",
+            "the number of sites are estimated (not counted per gene),",
+            "speeding up the computation ~10X."]
+        },
+        {
+          "name": "Bacterial code synonymous fraction",
+          "opt": "--syn-bacterial-code",
+          "description": ["Sets the synonymous fraction to 0.760417,",
+            "approximately the proportion of synonymous substitutions in the",
+            "bacterial code."]
+        },
+        {
+          "opt": "--codon-file",
+          "arg": "out_file",
+          "description": ["Output file including the codons of substitution",
+            "variants."]
+        }
+      ]
+    }
+  ]
+}

data/utils/enveomics/Manifest/categories.json

@@ -0,0 +1,165 @@
+{
+  "categories": {
+    "Sequence similarity search": {
+      "Statistics": [
+        "BedGraph.tad.rb",
+        "BedGraph.window.rb",
+        "BlastPairwise.AAsubs.pl",
+        "BlastTab.advance.bash",
+        "BlastTab.recplot2.R",
+        "BlastTab.seqdepth.pl",
+        "BlastTab.seqdepth_nomedian.pl",
+        "BlastTab.seqdepth_ZIP.pl",
+        "BlastTab.sumPerHit.pl",
+        "FastQ.test-error.rb",
+        "RecPlot2.compareIdentities.R"
+      ],
+      "Manipulation": [
+        "BlastTab.addlen.rb",
+        "BlastTab.best_hit_sorted.pl",
+        "BlastTab.catsbj.pl",
+        "BlastTab.cogCat.rb",
+        "BlastTab.filter.pl",
+        "BlastTab.kegg_pep2path_rest.pl",
+        "BlastTab.pairedHits.rb",
+        "BlastTab.subsample.pl",
+        "BlastTab.taxid2taxrank.pl",
+        "BlastTab.topHits_sorted.rb",
+        "sam.filter.rb"
+      ],
+      "Execution": [
+        "aai.rb",
+        "ani.rb",
+        "anir.rb",
+        "HMM.haai.rb",
+        "rbm.rb"
+      ]
+    },
+    "Sequence analyses": {
+      "Statistics": [
+        "FastA.gc.pl",
+        "FastA.length.pl",
+        "FastA.N50.pl",
+        "FastA.qlen.pl",
+        "FastQ.test-error.rb"
+      ],
+      "Manipulation": [
+        "FastA.extract.rb",
+        "FastA.filter.pl",
+        "FastA.filterLen.pl",
+        "FastA.filterN.pl",
+        "FastA.fragment.rb",
+        "FastA.interpose.pl",
+        "FastA.mask.rb",
+        "FastA.per_file.pl",
+        "FastA.rename.pl",
+        "FastA.revcom.pl",
+        "FastA.sample.rb",
+        "FastA.slider.pl",
+        "FastA.split.pl",
+        "FastA.split.rb",
+        "FastA.subsample.pl",
+        "FastA.tag.rb",
+        "FastA.toFastQ.rb",
+        "FastA.wrap.rb",
+        "FastQ.filter.pl",
+        "FastQ.interpose.pl",
+        "FastQ.maskQual.rb",
+        "FastQ.offset.pl",
+        "FastQ.split.pl",
+        "FastQ.tag.rb",
+        "FastQ.toFastA.awk"
+      ]
+    },
+    "Diversity": {
+      "Community": [
+        "AlphaDiversity.pl",
+        "Chao1.pl",
+        "Table.barplot.R",
+        "Table.prefScore.R"
+      ],
+      "Population": [
+        "VCF.SNPs.rb",
+        "VCF.KaKs.rb",
+        "Table.prefScore.R"
+      ]
+    },
+    "Annotation": {
+      "Database mapping": [
+        "BlastTab.kegg_pep2path_rest.pl",
+        "BlastTab.taxid2taxrank.pl",
+        "EBIseq2tax.rb",
+        "NCBIacc2tax.rb",
+        "gi2tax.rb",
+        "M5nr.getSequences.rb",
+        "RefSeq.download.bash",
+        "SRA.download.bash"
+      ],
+      "Tables": [
+        "Table.barplot.R",
+        "GenBank.add_fields.rb",
+        "MyTaxa.fragsByTax.pl",
+        "Table.df2dist.R",
+        "Table.filter.pl",
+        "Table.merge.pl",
+        "Table.replace.rb",
+        "Table.round.rb",
+        "Table.split.pl"
+      ],
+      "Search": [
+        "HMM.essential.rb",
+        "HMM.haai.rb",
+        "HMMsearch.extractIds.rb",
+        "ogs.annotate.rb",
+        "ogs.core-pan.rb",
+        "ogs.extract.rb",
+        "ogs.mcl.rb",
+        "ogs.stats.rb",
+        "ogs.rb"
+      ]
+    },
+    "Other data": {
+      "Phylogenetic and other distances": [
+        "CharTable.classify.rb",
+        "JPlace.distances.rb",
+        "JPlace.to_iToL.rb",
+        "Newick.autoprune.R",
+        "TRIBS.test.R",
+        "TRIBS.plot-test.R",
+        "Table.df2dist.R"
+      ],
+      "Taxonomic": [
+        "CharTable.classify.rb",
+        "EBIseq2tax.rb",
+        "NCBIacc2tax.rb",
+        "Table.barplot.R",
+        "gi2tax.rb",
+        "MyTaxa.fragsByTax.pl",
+        "MyTaxa.seq-taxrank.rb",
+        "Taxonomy.silva2ncbi.rb"
+      ],
+      "Alignments": [
+        "AAsubs.log2ratio.rb",
+        "Aln.cat.rb",
+        "Aln.convert.pl",
+        "BlastPairwise.AAsubs.pl"
+      ],
+      "Clustering": [
+        "ogs.mcl.rb",
+        "clust.rand.rb"
+      ],
+      "Read recruitments": [
+        "anir.rb",
+        "BedGraph.tad.rb",
+        "BedGraph.window.rb",
+        "BlastTab.catsbj.pl",
+        "BlastTab.pairedHits.rb",
+        "BlastTab.recplot2.R",
+        "FastQ.test-error.rb",
+        "GFF.catsbj.pl",
+        "RecPlot2.compareIdentities.R",
+        "sam.filter.rb"
+      ]
+    }
+  }
+}