miga-base 1.2.17.0 → 1.2.17.2

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

@@ -0,0 +1,650 @@
+{
+  "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",
+          "https://dx.doi.org/10.1128%2FJB.187.18.6258-6264.2005"],
+        ["Altschul et al, 2000, JMB (BLAST)",
+          "https://dx.doi.org/10.1016/S0022-2836(05)80360-2"],
+        ["Kent WJ, 2002, Genome Res (BLAT)",
+          "https://dx.doi.org/10.1101/gr.229202"],
+        ["Buchfink B, Xie C, Huson D, 2015, Nat Meth (Diamond)",
+          "https://dx.doi.org/10.1038/nmeth.3176"]
+      ],
+      "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","diamond"],
+          "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","HMM.essential.rb"],
+      "cite": [
+        ["Konstantinidis & Tiedje, 2005, PNAS",
+          "http://dx.doi.org/10.1073%2Fpnas.0409727102"],
+        ["Altschul et al, 2000, JMB (BLAST)",
+          "http://dx.doi.org/10.1016/S0022-2836(05)80360-2"],
+        ["Kent WJ, 2002, Genome Res (BLAT)",
+          "https://dx.doi.org/10.1101/gr.229202"]
+      ],
+      "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": "anir.rb",
+      "description": ["Estimates ANIr: the Average Nucleotide Identity of",
+        "reads against a genome."],
+      "help_arg": "--help",
+      "see_also": ["ani.rb", "sam.filter.rb"],
+      "options": [
+        {
+          "opt": "--reads",
+          "arg": "in_file",
+          "description": "Metagenomic reads."
+        },
+        {
+          "opt": "--genome",
+          "arg": "in_file",
+          "description": "Genome assembly."
+        },
+        {
+          "opt": "--mapping",
+          "arg": "in_file",
+          "description": "Mapping file."
+        },
+        {
+          "opt": "--list",
+          "arg": "in_file",
+          "description": "Output file with identities."
+        },
+        {
+          "opt": "--hist",
+          "arg": "in_file",
+          "description": "Output file with histogram."
+        },
+        {
+          "opt": "--tab",
+          "arg": "out_file",
+          "description": "Output file with results in tabular format."
+        },
+        {
+          "name": "Reads format",
+          "opt": "--r-format",
+          "arg": "select",
+          "description": ["Metagenomic reads format: fastq or fasta.",
+            "Both options support compression with .gz file extension."],
+          "values": ["fastq", "fasta"],
+          "default": "fastq"
+        },
+        {
+          "name": "Reads type",
+          "opt": "--r-type",
+          "arg": "select",
+          "description": ["Type of metagenomic reads: Single reads (single),",
+            "coupled reads in separate files (-m must be comma-delimited;",
+            "coupled), or coupled reads in a single interposed file",
+            "(interleaved)."],
+          "values": ["single", "coupled", "interleaved"],
+          "default": "single"
+        },
+        {
+          "name": "Genome format",
+          "opt": "--g-format",
+          "arg": "select",
+          "description": ["Genome assembly format: fasta or list.",
+            "Both options support compression with .gz file extension.",
+            "If passed in mapping-read mode, filters only matches to these",
+            "contigs."],
+          "values": ["fasta", "list"],
+          "default": "fasta"
+        },
+        {
+          "name": "Mapping format",
+          "opt": "--m-format",
+          "arg": "select",
+          "description": ["Mapping file format: sam, bam, tab, or list.",
+            "All except bam support compression with .gz file extension."],
+          "values": ["sam", "bam", "tab", "list"],
+          "default": "sam"
+        },
+        {
+          "opt": "--identity",
+          "arg": "float",
+          "description": "Set a fixed threshold of percent identity.",
+          "default": 95.0
+        },
+        {
+          "opt": "--algorithm",
+          "arg": "select",
+          "description": ["Set an algorithm to automatically detect identity",
+            "threshold: Valley detection by E-M of Gaussian Mixture Model",
+            "(gmm), fixed threshold (see Identity; fix),",
+            "Pick gmm or fix depending on bimodality (see Bimodality; auto)."],
+          "values": ["gmm", "fix", "auto"],
+          "default": "auto"
+        },
+        {
+          "opt": "--bimodality",
+          "arg": "float",
+          "description": ["Threshold of bimodality below which the algorithm",
+            "is set to fix. The coefficient used is the de Michele & Accantino",
+            "(2014) B index."],
+          "default": 0.5
+        },
+        {
+          "opt": "--coefficient",
+          "arg": "select",
+          "description": ["Coefficient of bimodality for Algorithm auto: ",
+            "Sarle's bimodality coefficient b (sarle), or",
+            "de Michele and Accatino (2014 PLoS ONE) B index",
+            "(use with Bimodality 0.1, dma)."],
+          "values": ["sarle", "dma"],
+          "default": "sarle"
+        },
+        {
+          "opt": "--bin-size",
+          "arg": "float",
+          "description": "Width of histogram bins (in percent identity).",
+          "default": 1.0
+        },
+        {
+          "opt": "--threads",
+          "arg": "integer",
+          "description": "Threads to use."
+        },
+        {
+          "opt": "--log",
+          "arg": "out_file",
+          "description": "Log file to save output."
+        },
+        {
+          "opt": "--quiet",
+          "description": "Run quietly."
+        }
+      ]
+    },
+    {
+      "task": "HMM.haai.rb",
+      "description": ["Estimates Average Amino Acid Identity (AAI) from the",
+        "essential genes extracted and aligned by HMM.essential.rb (see",
+        "Alignments)."],
+      "help_arg": "--help",
+      "see_also": ["HMM.essential.rb","aai.rb"],
+      "options": [
+        {
+          "name": "Alignments 1",
+          "opt": "-1",
+          "arg": "in_file",
+          "description": "Input alignments file for genome 1."
+        },
+        {
+          "name": "Alignments 2",
+          "opt": "-2",
+          "arg": "in_file",
+          "description": "Input alignments file for genome 2."
+        },
+        {
+          "name": "Alignment output",
+          "opt": "--aln-out",
+          "arg": "out_file",
+          "description": "Output file containing the aligned proteins."
+        },
+	{
+	  "opt": "--components",
+	  "arg": "out_file",
+	  "description": ["Output file containing the components of the",
+	    "estimation. Tab-delimited file with model name, matches, and",
+	    "columns."]
+	},
+        {
+          "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":[
+        ["Camacho et al, 2009, BMC Bioinf (BLAST+)",
+          "https://doi.org/10.1186/1471-2105-10-421"],
+        ["Altschul et al, 2000, JMB (BLAST)",
+          "http://dx.doi.org/10.1016/S0022-2836(05)80360-2"],
+        ["Buchfink B, Xie C, Huson D, 2015, Nat Meth (Diamond)",
+          "https://dx.doi.org/10.1038/nmeth.3176"],
+        ["Kent, 2002, Genome Res (BLAT)",
+          "https://doi.org/10.1101/gr.229202"]
+      ],
+      "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": "Output",
+          "opt": "--out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": [
+            "Reciprocal Best Matches in BLAST tabular format.",
+            "Supports compression with .gz extension."
+          ]
+        },
+        {
+          "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+ or Diamond (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", "diamond"],
+          "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)."
+        }
+      ]
+    }
+  ]
+}