miga-base 0.3.0.0 → 0.3.0.1

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

@@ -0,0 +1,355 @@
+{
+  "tasks": [
+    {
+      "task": "BlastTab.kegg_pep2path_rest.pl",
+      "description": ["Takes a BLAST against KEGG_PEP (or KO) and retrieves",
+        "the pathways in which the subject peptides are involved."],
+      "requires": [
+        { "perl_lib": "JSON" },
+	{ "perl_lib": "LWP::Simple" }
+      ],
+      "help_arg": "",
+      "options": [
+        {
+          "name": "blast.txt",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Input tabular BLAST file."
+        },
+        {
+          "name": "Cache file",
+          "arg": "out_file",
+          "description": ["(optional) File containing the saved cache. If",
+            "unset, the cache won't be recoverable across instances of this",
+            "script. It is strongly recommended to set a file. Multiple",
+            "parallel instances of this script may use the same cache file."]
+        },
+        ">",
+        {
+          "name": "output.txt",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": ["Tab-delimited output file, with the columns: (1)",
+            "Query ID, (2) Subject ID, (3) Pathway ID, (4) Pathway (reference)",
+            "description, (5) Organism."]
+        }
+      ]
+    },
+    {
+      "task": "M5nr.getSequences.rb",
+      "description": ["Downloads a set of sequences from M5nr with a given",
+        "functional annotation."],
+      "help_arg": "--help",
+      "requires": [
+        { "ruby_gem": "restclient" },
+        { "ruby_gem": "open-uri" },
+        { "ruby_gem": "JSON" }
+      ],
+      "options": [
+        {
+          "opt": "--function",
+          "arg": "string",
+          "mandatory": true,
+          "description": "Functional annotation."
+        },
+        {
+          "name": "Output file",
+          "opt": "--out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "File containing the sequences."
+        },
+        {
+          "opt": "--max",
+          "arg": "integer",
+          "default": 0,
+          "description": ["Maximum number of sequences to download. Set to",
+            "0 to download all."]
+        },
+        {
+          "opt": "--recover",
+          "description": "If set, tries to recover a previous FastA."
+        },
+        {
+          "name": "URL",
+          "opt": "--url",
+          "arg": "string",
+          "default": "http://api.metagenomics.anl.gov/m5nr",
+          "description": "URL for M5nr API."
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly (no STDERR output)."
+        }
+      ]
+    },
+    {
+      "task": "EBIseq2tax.rb",
+      "description": ["Maps a list of EBI-supported IDs to their corresponding",
+        "NCBI taxonomy using EBI RESTful API."],
+      "warn": ["Avoid using this script on millions of entries at a time,",
+        "since each entry elicits requests to EBI and NCBI servers."],
+      "requires": [
+        { "ruby_gem": "nokogiri" }
+      ],
+      "see_also": ["NCBIacc2tax.rb"],
+      "help_arg": "--help",
+      "options": [
+        {
+          "name": "IDs",
+          "opt": "--ids",
+          "arg": "string",
+          "description": "Comma-separated list of EBI IDs.",
+          "note": "Required unless 'Input file' is passed."
+        },
+        {
+          "name": "Input file",
+          "opt": "--infile",
+          "arg": "in_file",
+          "description": ["Raw text file containing the list of EBI IDs,",
+            "one per line."],
+          "note": "Required unless 'IDs' is passed."
+        },
+        {
+          "opt": "--database",
+          "arg": "string",
+          "default": "uniprotkb",
+          "description": "EBI database defining the EBI IDs."
+        },
+        {
+          "opt": "--ranks",
+          "arg": "string",
+          "description": "Comma-delimited list of taxonomic ranks to report.",
+          "default": "superkingdom,phylum,class,order,family,genus,species"
+        },
+        {
+          "opt": "--noheader",
+          "description": "Do not includ a header in the output."
+        },
+        {
+          "opt": "--taxids",
+          "description": "Return Taxonomy IDs instead of scientific names."
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly."
+        }
+      ]
+    },
+    {
+      "task": "RefSeq.download.bash",
+      "description": ["Downloads a collection of sequences and/or annotations",
+        "from NCBI's RefSeq."],
+      "help_arg": "",
+      "requires": [
+        {
+          "description": "curl",
+          "test": "curl --version"
+        }
+      ],
+      "options": [
+        {
+          "name": "Organism",
+          "arg": "string",
+          "mandatory": true,
+          "description": ["The organism to download (e.g.,",
+            "Streptococcus_pneumoniae)."]
+        },
+        {
+          "name": "Extension",
+          "arg": "string",
+          "mandatory": true,
+          "default": ".*.gz",
+          "description": ["Extension to download. Common extensions include",
+            ".fna.gz (genomic sequences), .faa.gz (protein sequences),",
+            ".gff.gz (annotations), and .*.gz (all data)."]
+        },
+        {
+          "name": "Level",
+          "arg": "string",
+          "mandatory": true,
+          "default": "Any",
+          "description": ["Use only genomes with this assembly level. Common",
+            "levels are 'Complete Genome' and 'Contig'. By default, any",
+            "assembly level is allowed ('Any')."]
+        },
+        {
+          "name": "Directory",
+          "arg": "out_dir",
+          "description": ["Directory where the files are to be downladed.",
+            "By default, same as 'Organism'."]
+        }
+      ]
+    },
+    {
+      "task": "SRA.download.bash",
+      "description": ["Downloads the set of runs from a project, sample, or",
+        "experiment in SRA."],
+      "help_arg": "",
+      "requires": [
+        {
+          "description": "curl",
+          "test": "curl --version"
+        }
+      ],
+      "options": [
+        {
+          "name": "SRA ID",
+          "arg": "string",
+          "mandatory": true,
+          "description": "ID of the SRA Project, Sample, or Experiment."
+        },
+        {
+          "name": "dir",
+          "arg": "out_dir",
+          "description": ["Directory where the files are to be downladed. By",
+            "default, same as 'SRA ID'."]
+        }
+      ]
+    },
+    {
+      "task": "gi2tax.rb",
+      "description": ["Maps a list of NCBI GIs to their corresponding taxonomy",
+        "using the NCBI EUtilities."],
+      "warn": ["Avoid using this script on millions of entries at a time,",
+        "since each entry elicits two requests to NCBI's servers.",
+        "*IMPORTANT NOTE*: NCBI is phasing out support for GIs. Please use",
+        "acc.ver instead with NCBIacc2tax.rb."],
+      "requires": [
+        { "ruby_gem": "nokogiri" },
+        { "ruby_gem": "json" }
+      ],
+      "see_also": ["NCBIacc2tax.rb"],
+      "help_arg": "--help",
+      "options": [
+        {
+          "name": "GIs",
+          "opt": "--gis",
+          "arg": "string",
+          "description": "Comma-separated list of GIs.",
+          "note": "Required unless 'Input file' is passed."
+        },
+        {
+          "name": "Input file",
+          "opt": "--infile",
+          "arg": "in_file",
+          "description": ["Raw text file containing the list of GIs, one per",
+            "line."],
+          "note": "Required unless 'GIs' is passed."
+        },
+        {
+          "opt": "--protein",
+          "description": ["Use if the GIs are proteins. Otherwise, GIs are",
+            "assumed to be from the Nuccore Database."]
+        },
+        {
+          "opt": "--ranks",
+          "arg": "string",
+          "description": "Taxonomic ranks to report, separated by commas.",
+          "default": "superkingdom,phylum,class,order,family,genus,species"
+        },
+        {
+          "name": "No header",
+          "opt": "--noheader",
+          "description": "Do not include a header in the output."
+        },
+        {
+          "name": "Tax IDs",
+          "opt": "--taxids",
+          "description": "Return Taxonomy IDs instead of scientific names."
+        },
+        {
+          "name": "Exact GI",
+          "opt": "--exact-gi",
+          "description": ["Returns only taxonomy associated with the exact GI",
+            "passed. By default, it attempts to update accession versions if",
+            "possible."]
+        },
+        {
+          "opt": "--ignore-missing",
+          "description": ["Does not report missing GIs in the output file. By",
+            "default, it reports GI and empty values for all other columns."]
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly."
+        },
+        ">",
+        {
+          "arg": "out_file",
+          "mandatory": true,
+          "description": ["Tab-delimited table with GIs and taxonomic",
+            "classification."]
+        }
+      ]
+    },
+    {
+      "task": "NCBIacc2tax.rb",
+      "description": ["Maps a list of NCBI accessions to their corresponding",
+        "taxonomy using the NCBI EUtilities."],
+      "warn": ["Avoid using this script on millions of entries at a time,",
+        "since each entry elicits two requests to NCBI's servers."],
+      "requires": [
+        { "ruby_gem": "nokogiri" },
+        { "ruby_gem": "json" }
+      ],
+      "see_also": ["EBIseq2tax.rb"],
+      "help_arg": "--help",
+      "options": [
+        {
+          "name": "Accessions",
+          "opt": "--acc",
+          "arg": "string",
+          "description": "Comma-separated list of accessions.",
+          "note": "Required unless 'Input file' is passed."
+        },
+        {
+          "name": "Input file",
+          "opt": "--infile",
+          "arg": "in_file",
+          "description": ["Raw text file containing the list of accessions,",
+            "one per line."],
+          "note": "Required unless 'Accessions' is passed."
+        },
+        {
+          "opt": "--protein",
+          "description": ["Use if the accessions are proteins. Otherwise,",
+            "accessions are assumed to be from the Nuccore Database."]
+        },
+        {
+          "opt": "--ranks",
+          "arg": "string",
+          "description": "Taxonomic ranks to report, separated by commas.",
+          "default": "superkingdom,phylum,class,order,family,genus,species"
+        },
+        {
+          "name": "No header",
+          "opt": "--noheader",
+          "description": "Do not include a header in the output."
+        },
+        {
+          "name": "Tax IDs",
+          "opt": "--taxids",
+          "description": "Return Taxonomy IDs instead of scientific names."
+        },
+        {
+          "opt": "--ignore-missing",
+          "description": ["Does not report missing accessions in the output",
+            "file. By default, it reports GI and empty values for all other",
+            "columns."]
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly."
+        },
+        ">",
+        {
+          "arg": "out_file",
+          "mandatory": true,
+          "description": ["Tab-delimited table with accessions and taxonomic",
+            "classification."]
+        }
+      ]
+    }
+  ]
+}

data/utils/enveomics/Manifest/Tasks/sequence-identity.json

@@ -0,0 +1,454 @@
+{
+  "tasks": [
+    {
+      "task": "aai.rb",
+      "description": ["Calculates the Average Amino acid Identity between two",
+        "genomes."],
+      "help_arg": "--help",
+      "see_also": ["ani.rb", "rbm.rb"],
+      "cite": [
+        ["Konstantinidis & Tiedje, 2005, JBac",
+          "http://dx.doi.org/10.1128%2FJB.187.18.6258-6264.2005"],
+        ["Altschul et al, 2000, JMB",
+          "http://dx.doi.org/10.1016/S0022-2836(05)80360-2"]
+      ],
+      "options": [
+        {
+          "name": "Sequence 1",
+          "opt": "--seq1",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "FastA file containing the genome 1 (proteins).",
+          "note": ["Alternatively, you can supply the NCBI-acc of a genome",
+            " (nucleotides) with the format ncbi:CP014272 instead of files."]
+        },
+        {
+          "name": "Sequence 2",
+          "opt": "--seq2",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "FastA file containing the genome 2.",
+          "note": ["Alternatively, you can supply the NCBI-acc of a genome",
+            " (nucleotides) with the format ncbi:NC_004337 instead of files."]
+        },
+        {
+          "name": "Length",
+          "opt": "--len",
+          "arg": "integer",
+          "description": "Minimum alignment length (in aa).",
+          "default": 0
+        },
+        {
+          "name": "Length fraction",
+          "opt": "--len-fraction",
+          "arg": "float",
+          "description": ["Minimum alignment length as a fraction of the",
+            "shorter sequence (range 0-1)."],
+          "default": 0.0
+        },
+        {
+          "name": "Identity",
+          "opt": "--id",
+          "arg": "float",
+          "description": "Minimum alignment identity (in %).",
+          "default": 20.0
+        },
+        {
+          "name": "Bit-score",
+          "opt": "--bitscore",
+          "arg": "float",
+          "description": "Minimum bit score (in bits).",
+          "default": 0.0
+        },
+        {
+          "opt": "--hits",
+          "arg": "float",
+          "description": "Minimum number of hits.",
+          "default": 50.0
+        },
+        {
+          "name": "Nucleotides",
+          "opt": "--nucl",
+          "description": ["The input sequences are nucleotides (genes), not",
+            "proteins."]
+        },
+        {
+          "name": "Max ACTG",
+          "opt": "--max-actg",
+          "arg": "float",
+          "default": 0.95,
+          "description": ["Maximum fraction of ACTGN in the sequences before",
+            "assuming nucleotides."]
+        },
+        {
+          "name": "Executables",
+          "opt": "--bin",
+          "arg": "in_dir",
+          "description": ["Path to the directory containing the binaries of",
+            "the search program."]
+        },
+        {
+          "opt": "--program",
+          "arg": "select",
+          "values": ["blast+","blast","blat"],
+          "default": "blast+",
+          "description": "Search program to be used.",
+          "note": ["Make sure that you have installed the search program you",
+            "want to use. If you have downloaded the program, but it's not",
+            "installed, please use the Executables option above."]
+        },
+        {
+          "opt": "--threads",
+          "arg": "integer",
+          "description": "Number of parallel threads to be used.",
+          "default": 1
+        },
+        {
+          "name": "SQLite3 DB",
+          "opt": "--sqlite3",
+          "arg": "out_file",
+          "description": ["Path to the SQLite3 database to create (or update)",
+            "with the results."]
+        },
+        {
+          "name": "Name 1",
+          "opt": "--name1",
+          "arg": "string",
+          "description": ["Name of Sequence 1 to use in SQLite3 DB. By default",
+            "determined by filename."]
+        },
+        {
+          "name": "Name 2",
+          "opt": "--name2",
+          "arg": "string",
+          "description": ["Name of Sequence 2 to use in SQLite3 DB. By default",
+            "determined by filename."]
+        },
+        {
+          "name": "Don't save RBM",
+          "opt": "--no-save-rbm",
+          "description": ["Don't save the reciprocal best matches in the",
+            "--sqlite3 database."]
+        },
+        {
+          "opt": "--lookup-first",
+          "description": ["Indicates if the AAI should be looked up first in",
+            "the database. Requires SQLite3 DB, Auto, Name 1, and Name 2.",
+            "Incompatible with Result, Tab, Out, and RBM."]
+        },
+        {
+          "name": "Precision",
+          "opt": "--dec",
+          "arg": "integer",
+          "default": 2,
+          "description": "Decimal positions to report."
+        },
+        {
+          "name": "RBM",
+          "opt": "--rbm",
+          "arg": "out_file",
+          "description": "Saves a file with the reciprocal best matches."
+        },
+        {
+          "opt": "--out",
+          "arg": "out_file",
+          "description": ["Saves a file describing the alignments used for",
+            "two-way AAI."]
+        },
+        {
+          "name": "Result",
+          "opt": "--res",
+          "arg": "out_file",
+          "description": "Saves a file with the final results."
+        },
+        {
+          "opt": "--tab",
+          "arg": "out_file",
+          "description": ["Saves a file with the final two-way results in a",
+            "tab-delimited form. The columns are (in that order): AAI,",
+            "standard deviation, proteins used, proteins in the smallest",
+            "genome."]
+        },
+        {
+          "opt": "--auto",
+          "description": ["ONLY outputs the AAI value in STDOUT (or nothing,",
+            "if calculation fails)."]
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly (no STDERR output)."
+        }
+      ]
+    },
+    {
+      "task": "ani.rb",
+      "description": ["Calculates the Average Nucleotide Identity between two",
+        "genomes."],
+      "help_arg": "--help",
+      "see_also": ["aai.rb","rbm.rb"],
+      "cite": [
+        ["Konstantinidis & Tiedje, 2005, PNAS",
+          "http://dx.doi.org/10.1073%2Fpnas.0409727102"],
+        ["Altschul et al, 2000, JMB",
+          "http://dx.doi.org/10.1016/S0022-2836(05)80360-2"]
+      ],
+      "options": [
+        {
+          "name": "Sequence 1",
+          "opt": "--seq1",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "FastA file containing the genome 1.",
+          "note": ["Alternatively, you can supply an NCBI-acc with the format",
+            "ncbi:CP014272 instead of files."]
+        },
+        {
+          "name": "Sequence 2",
+          "opt": "--seq2",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "FastA file containing the genome 2.",
+          "note": ["Alternatively, you can supply an NCBI-acc with the format",
+            "ncbi:AE005174 instead of files."]
+        },
+        {
+          "name": "Window",
+          "opt": "--win",
+          "arg": "integer",
+          "description": "Window size in the ANI calculation (in bp).",
+          "default": 1000
+        },
+        {
+          "opt": "--step",
+          "arg": "integer",
+          "description": "Step size in the ANI calculation (in bp).",
+          "default": 200
+        },
+        {
+          "name": "Length",
+          "opt": "--len",
+          "arg": "integer",
+          "description": "Minimum alignment length (in bp).",
+          "default": 700
+        },
+        {
+          "name": "Identity",
+          "opt": "--id",
+          "arg": "float",
+          "description": "Minimum alignment identity (in %).",
+          "default": 70.0
+        },
+        {
+          "opt": "--hits",
+          "arg": "integer",
+          "description": "Minimum number of hits.",
+          "default": 50
+        },
+        {
+          "name": "No correction",
+          "opt": "--nocorrection",
+          "description": "Report values without post-hoc correction."
+        },
+        {
+          "name": "Min ACTG",
+          "opt": "--min-actg",
+          "arg": "float",
+          "default": 0.95,
+          "description": ["Minimum fraction of ACTGN in the sequences before",
+            "assuming proteins."]
+        },
+        {
+          "name": "Executables",
+          "opt": "--bin",
+          "arg": "in_dir",
+          "description": ["Directory containing the binaries of the search",
+            "program."]
+        },
+        {
+          "opt": "--program",
+          "arg": "select",
+          "values": ["blast+", "blast", "blat"],
+          "default": "blast+",
+          "description": "Search program to be used.",
+          "note": ["Make sure that you have installed the search program you",
+            "want to use. If you have downloaded the program, but it's not",
+            "installed, please use the Executables option above."]
+        },
+        {
+          "opt": "--threads",
+          "arg": "integer",
+          "description": "Number of parallel threads to be used.",
+          "default": 1
+        },
+        {
+          "name": "SQLite3 DB",
+          "opt": "--sqlite3",
+          "arg": "out_file",
+          "description": ["Path to the SQLite3 database to create (or update)",
+            "with the results."]
+        },
+        {
+          "name": "Name 1",
+          "opt": "--name1",
+          "arg": "string",
+          "description": ["Name of Sequence 1 to use in SQLite3 DB. By default",
+            "it's determined by the filename."]
+        },
+        {
+          "name": "Name 2",
+          "opt": "--name2",
+          "arg": "string",
+          "description": ["Name of Sequence 2 to use in SQLite3 DB. By default",
+            "it's determined by the filename."]
+        },
+        {
+          "name": "Don't save regions",
+          "opt": "--no-save-regions",
+          "description": "Don't save the fragments in the SQLite3 database."
+        },
+        {
+          "name": "Don't save RBM",
+          "opt": "--no-save-rbm",
+          "description": ["Don't save the reciprocal best matches in the",
+            "--sqlite3 database."]
+        },
+        {
+          "opt": "--lookup-first",
+          "description": ["Indicates if the ANI should be looked up first in",
+            "the database. Requires SQLite3 DB, Auto, Name 1, and Name 2.",
+            "Incompatible with Result, Tab, and Out."]
+        },
+        {
+          "name": "Precision",
+          "opt": "--dec",
+          "arg": "integer",
+          "description": "Decimal positions to report.",
+          "default": 2
+        },
+        {
+          "opt": "--out",
+          "arg": "out_file",
+          "description": ["Saves a file describing the alignments used for",
+            "two-way ANI."]
+        },
+        {
+          "name": "Result",
+          "opt": "--res",
+          "arg": "out_file",
+          "description": "Saves a file with the final results."
+        },
+        {
+          "opt": "--tab",
+          "arg": "out_file",
+          "description": ["Saves a file with the final two-way results in a",
+            "tab-delimited form. The columns are (in that order): ANI,",
+            "standard deviation, fragments used, fragments in the smallest",
+            "genome."]
+        },
+        {
+          "opt": "--auto",
+          "description": ["ONLY outputs the ANI value in STDOUT (or nothing,",
+            "if calculation fails)."]
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly (no STDERR output)."
+        }
+      ]
+    },
+    {
+      "task": "rbm.rb",
+      "description": ["Finds the reciprocal best matches between two sets of",
+        "sequences."],
+      "help_arg": "--help",
+      "cite":[
+        ["Altschul et al, 2000, JMB",
+          "http://dx.doi.org/10.1016/S0022-2836(05)80360-2"]
+      ],
+      "options": [
+        {
+          "name": "Sequence 1",
+          "opt": "--seq1",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "FastA file containing the genome 1."
+        },
+        {
+          "name": "Sequence 2",
+          "opt": "--seq2",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "FastA file containing the genome 2."
+        },
+        {
+          "name": "Nucleotides",
+          "opt": "--nucl",
+          "description": ["Sequences are assumed to be nucleotides (proteins",
+            "by default)."]
+        },
+        {
+          "name": "Length",
+          "opt": "--len",
+          "arg": "integer",
+          "description": "Minimum alignment length (in residues).",
+          "default": 0
+        },
+        {
+          "name": "Fraction",
+          "opt": "--fract",
+          "arg": "float",
+          "default": 0.0,
+          "description": ["Minimum alignment length (as a fraction of the",
+            "query). If set, requires BLAST+ (see Program)."]
+        },
+        {
+          "name": "Identity",
+          "opt": "--id",
+          "arg": "float",
+          "description": "Minimum alignment identity (in %).",
+          "default": 0.0
+        },
+        {
+          "name": "Bit score",
+          "opt": "--score",
+          "arg": "float",
+          "default": 0.0,
+          "description": "Minimum alignment score (in bits)."
+        },
+        {
+          "name": "Executables",
+          "opt": "--bin",
+          "arg": "in_dir",
+          "description": ["Directory containing the binaries of the search",
+            "program."]
+        },
+        {
+          "opt": "--program",
+          "arg": "select",
+          "values": ["blast+", "blast", "blat"],
+          "default": "blast+",
+          "description": "Search program to be used. Default: blast+.",
+          "note": ["Make sure that you have installed the search program you",
+            "want to use. If you have downloaded the program, but it's not",
+            "installed, please use the Executables option above."]
+        },
+        {
+          "opt": "--threads",
+          "arg": "integer",
+          "description": "Number of parallel threads to be used.",
+          "default": 1
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly (no STDERR output)."
+        },
+        ">",
+        {
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Reciprocal Best Matches in BLAST tabular format."
+        }
+      ]
+    }
+  ]
+}