miga-base 0.3.9.0 → 0.3.9.1

data/scripts/miga.bash

@@ -2,7 +2,7 @@
 set -e
 #MIGA=${MIGA:-$(cd "$(dirname "$0")/.."; pwd)}
 # shellcheck source=/dev/null
-source "$HOME/.miga_rc"
+. "$HOME/.miga_rc"
 export PATH="$MIGA/bin:$MIGA/utils/enveomics/Scripts:$PATH"
 SCRIPT=${SCRIPT:-$(basename "$0" .bash)}
 
@@ -11,15 +11,18 @@ function fx_exists { [[ $(type -t "$1") == "function" ]] ; }
 
 for i in $(miga plugins -P "$PROJECT") ; do
   # shellcheck source=/dev/null
-  source "$i/scripts-plugin.bash"
+  . "$i/scripts-plugin.bash"
 done
 
-[[ -n $DATASET ]] \
-      && miga add -P "$PROJECT" -D "$DATASET" -m "_step=$SCRIPT" --update
+if [[ "$SCRIPT" != "d" && "$SCRIPT" != "p" ]] ; then
+  echo -n "Date: " ; miga date
+  echo "MiGA: $MIGA"
+  echo "Task: $SCRIPT"
+  echo "Project: $PROJECT"
+  if [[ -n $DATASET ]] ; then
+    echo "Dataset: $DATASET"
+    miga edit -P "$PROJECT" -D "$DATASET" -m "_step=$SCRIPT"
+  fi
+fi
 
 true
-
-#if [[ "$RUNTYPE" == "qsub" ]] ; then
-#elif [[ "$RUNTYPE" == "msub" ]] ; then
-#fi
-

data/scripts/mytaxa.bash

@@ -2,10 +2,8 @@
 # Available variables: $PROJECT, $RUNTYPE, $MIGA, $CORES, $DATASET
 set -e
 SCRIPT="mytaxa"
-echo "MiGA: $MIGA"
-echo "Project: $PROJECT"
 # shellcheck source=scripts/miga.bash
-source "$MIGA/scripts/miga.bash" || exit 1
+. "$MIGA/scripts/miga.bash" || exit 1
 DIR="$PROJECT/data/07.annotation/02.taxonomy/01.mytaxa"
 [[ -d "$DIR" ]] || mkdir -p "$DIR"
 cd "$DIR"

data/scripts/mytaxa_scan.bash

@@ -2,10 +2,8 @@
 # Available variables: $PROJECT, $RUNTYPE, $MIGA, $CORES, $DATASET
 set -e
 SCRIPT="mytaxa_scan"
-echo "MiGA: $MIGA"
-echo "Project: $PROJECT"
 # shellcheck source=scripts/miga.bash
-source "$MIGA/scripts/miga.bash" || exit 1
+. "$MIGA/scripts/miga.bash" || exit 1
 DIR="$PROJECT/data/07.annotation/03.qa/02.mytaxa_scan"
 [[ -d "$DIR" ]] || mkdir -p "$DIR"
 cd "$DIR"

data/scripts/ogs.bash

@@ -2,49 +2,52 @@
 # Available variables: $PROJECT, $RUNTYPE, $MIGA, $CORES
 set -e
 SCRIPT="ogs"
-echo "MiGA: $MIGA"
-echo "Project: $PROJECT"
 # shellcheck source=scripts/miga.bash
-source "$MIGA/scripts/miga.bash" || exit 1
+. "$MIGA/scripts/miga.bash" || exit 1
 cd "$PROJECT/data/10.clades/03.ogs"
 
 # Initialize
 miga date > "miga-project.start"
 
 DS=$(miga ls -P "$PROJECT" --ref --no-multi)
-MIN_ID=$(miga about -P "$PROJECT" -m ogs_identity)
-[[ $MIN_ID == "?" ]] && MIN_ID=80
-if [[ ! -s miga-project.ogs ]] ; then
-  # Extract RBMs
-  if [[ ! -s miga-project.abc ]] ; then
-    [[ -d miga-project.tmp ]] || mkdir miga-project.tmp
-    for i in $DS ; do
-      file="miga-project.tmp/$i.abc"
-      [[ -s "$file" ]] && continue
-      echo "SELECT seq1,id1,seq2,id2,bitscore from rbm where id >= $MIN_ID;" \
-        | sqlite3 "../../09.distances/02.aai/$i.db" | tr "\\|" " " \
-        | awk '{ print $1">"$2"'"\\t"'"$3">"$4"'"\\t"'"$5 }' \
-        > "$file.tmp"
-      mv "$file.tmp" "$file"
-    done
-    cat miga-project.tmp/*.abc > miga-project.abc
-  fi
-  rm -rf miga-project.tmp
 
-  # Estimate OGs and Clean RBMs
-  ogs.mcl.rb -o miga-project.ogs --abc miga-project.abc -t "$CORES"
-  if [[ $(miga about -P "$PROJECT" -m clean_ogs) == "false" ]] ; then
-    rm miga-project.abc
-  else
-    gzip -9 miga-project.abc
+if [[ -n $DS ]] ; then
+  MIN_ID=$(miga about -P "$PROJECT" -m ogs_identity)
+  [[ $MIN_ID == "?" ]] && MIN_ID=80
+  if [[ ! -s miga-project.ogs ]] ; then
+    # Extract RBMs
+    if [[ ! -s miga-project.abc ]] ; then
+      [[ -d miga-project.tmp ]] || mkdir miga-project.tmp
+      for i in $DS ; do
+        file="miga-project.tmp/$i.abc"
+        [[ -s "$file" ]] && continue
+        echo "SELECT seq1,id1,seq2,id2,bitscore from rbm where id >= $MIN_ID;" \
+          | sqlite3 "../../09.distances/02.aai/$i.db" | tr "\\|" " " \
+          | awk '{ print $1">"$2"'"\\t"'"$3">"$4"'"\\t"'"$5 }' \
+          > "$file.tmp"
+        mv "$file.tmp" "$file"
+      done
+      cat miga-project.tmp/*.abc > miga-project.abc
+    fi
+    rm -rf miga-project.tmp
+
+    # Estimate OGs and Clean RBMs
+    ogs.mcl.rb -o miga-project.ogs --abc miga-project.abc -t "$CORES"
+    if [[ $(miga about -P "$PROJECT" -m clean_ogs) == "false" ]] ; then
+      rm miga-project.abc
+    else
+      gzip -9 miga-project.abc
+    fi
   fi
-fi
 
-# Calculate Statistics
-ogs.stats.rb -o miga-project.ogs -j miga-project.stats
-ogs.core-pan.rb -o miga-project.ogs -s miga-project.core-pan.tsv -t "$CORES"
-Rscript "$MIGA/utils/core-pan-plot.R" \
-  miga-project.core-pan.tsv miga-project.core-pan.pdf
+  # Calculate Statistics
+  ogs.stats.rb -o miga-project.ogs -j miga-project.stats
+  ogs.core-pan.rb -o miga-project.ogs -s miga-project.core-pan.tsv -t "$CORES"
+  Rscript "$MIGA/utils/core-pan-plot.R" \
+    miga-project.core-pan.tsv miga-project.core-pan.pdf
+else
+  touch miga-project.empty
+fi
 
 # Finalize
 miga date > "miga-project.done"

data/scripts/p.bash

@@ -0,0 +1,23 @@
+#!/bin/bash
+# Available variables: $PROJECT, $RUNTYPE, $MIGA, $CORES
+set -e
+SCRIPT="p"
+# shellcheck source=scripts/miga.bash
+. "$MIGA/scripts/miga.bash" || exit 1
+
+while true ; do
+  res="$(miga next_step -P "$PROJECT")"
+  [[ "$res" == '?' ]] && break
+  miga run -P "$PROJECT" -r "$res" -t "$CORES"
+  if [[ "$res" == "$last_res" ]] ; then
+    let k=$k+1
+    if [[ $k -gt 10 ]] ; then
+      miga new --update -P "$PROJECT" \
+        -m "run_$res=false,warn=Too many failed attempts to run $res."
+    fi
+  else
+    k=0
+    last_res=$res
+  fi
+done
+

data/scripts/project_stats.bash

@@ -2,10 +2,8 @@
 # Available variables: $PROJECT, $RUNTYPE, $MIGA, $CORES
 set -e
 SCRIPT="project_stats"
-echo "MiGA: $MIGA"
-echo "Project: $PROJECT"
 # shellcheck source=scripts/miga.bash
-source "$MIGA/scripts/miga.bash" || exit 1
+. "$MIGA/scripts/miga.bash" || exit 1
 DIR="$PROJECT/data/90.stats"
 [[ -d "$DIR" ]] || mkdir -p "$DIR"
 cd "$DIR"

data/scripts/read_quality.bash

@@ -2,10 +2,8 @@
 # Available variables: $PROJECT, $RUNTYPE, $MIGA, $CORES, $DATASET
 set -e
 SCRIPT="read_quality"
-echo "MiGA: $MIGA"
-echo "Project: $PROJECT"
 # shellcheck source=scripts/miga.bash
-source "$MIGA/scripts/miga.bash" || exit 1
+. "$MIGA/scripts/miga.bash" || exit 1
 cd "$PROJECT/data/03.read_quality"
 
 b=$DATASET

data/scripts/ssu.bash

@@ -2,10 +2,8 @@
 # Available variables: $PROJECT, $RUNTYPE, $MIGA, $CORES, $DATASET
 set -e
 SCRIPT="ssu"
-echo "MiGA: $MIGA"
-echo "Project: $PROJECT"
 # shellcheck source=scripts/miga.bash
-source "$MIGA/scripts/miga.bash" || exit 1
+. "$MIGA/scripts/miga.bash" || exit 1
 DIR="$PROJECT/data/07.annotation/01.function/02.ssu"
 [[ -d "$DIR" ]] || mkdir -p "$DIR"
 cd "$DIR"

data/scripts/stats.bash

@@ -2,10 +2,8 @@
 # Available variables: $PROJECT, $RUNTYPE, $MIGA, $CORES, $DATASET
 set -e
 SCRIPT="stats"
-echo "MiGA: $MIGA"
-echo "Project: $PROJECT"
 # shellcheck source=scripts/miga.bash
-source "$MIGA/scripts/miga.bash" || exit 1
+. "$MIGA/scripts/miga.bash" || exit 1
 DIR="$PROJECT/data/90.stats"
 [[ -d "$DIR" ]] || mkdir -p "$DIR"
 cd "$DIR"

data/scripts/subclades.bash

@@ -2,10 +2,8 @@
 # Available variables: $PROJECT, $RUNTYPE, $MIGA, $CORES
 set -e
 SCRIPT="subclades"
-echo "MiGA: $MIGA"
-echo "Project: $PROJECT"
 # shellcheck source=scripts/miga.bash
-source "$MIGA/scripts/miga.bash" || exit 1
+. "$MIGA/scripts/miga.bash" || exit 1
 cd "$PROJECT/data/10.clades/02.ani"
 
 # Initialize

data/scripts/taxonomy.bash

@@ -2,10 +2,8 @@
 # Available variables: $PROJECT, $RUNTYPE, $MIGA, $CORES, $DATASET
 set -e
 SCRIPT="taxonomy"
-echo "MiGA: $MIGA"
-echo "Project: $PROJECT"
 # shellcheck source=scripts/miga.bash
-source "$MIGA/scripts/miga.bash" || exit 1
+. "$MIGA/scripts/miga.bash" || exit 1
 DIR="$PROJECT/data/09.distances/05.taxonomy"
 [[ -d "$DIR" ]] || mkdir -p "$DIR"
 cd "$DIR"

data/scripts/trimmed_fasta.bash

@@ -2,10 +2,8 @@
 # Available variables: $PROJECT, $RUNTYPE, $MIGA, $CORES, $DATASET
 set -e
 SCRIPT="trimmed_fasta"
-echo "MiGA: $MIGA"
-echo "Project: $PROJECT"
 # shellcheck source=scripts/miga.bash
-source "$MIGA/scripts/miga.bash" || exit 1
+. "$MIGA/scripts/miga.bash" || exit 1
 cd "$PROJECT/data/04.trimmed_fasta"
 
 b=$DATASET

data/scripts/trimmed_reads.bash

@@ -2,10 +2,8 @@
 # Available variables: $PROJECT, $RUNTYPE, $MIGA, $CORES, $DATASET
 set -e
 SCRIPT="trimmed_reads"
-echo "MiGA: $MIGA"
-echo "Project: $PROJECT"
 # shellcheck source=scripts/miga.bash
-source "$MIGA/scripts/miga.bash" || exit 1
+. "$MIGA/scripts/miga.bash" || exit 1
 cd "$PROJECT/data/02.trimmed_reads"
 
 b=$DATASET

data/test/daemon_test.rb

@@ -40,10 +40,10 @@ class DaemonTest < Test::Unit::TestCase
     out = capture_stdout do
       d.check_datasets
     end
-    assert(out.string =~ /Queueing #{ds.name}:trimmed_reads/)
+    assert(out.string =~ /Queueing #{ds.name}:d/)
     assert_equal(1, d.jobs_to_run.size)
-    assert_equal("project1:trimmed_reads:ds1", d.jobs_to_run.first[:cmd])
-    assert_equal(d.jobs_to_run.first, d.get_job(:trimmed_reads, ds))
+    assert_equal("project1:d:ds1", d.jobs_to_run.first[:cmd])
+    assert_equal(d.jobs_to_run.first, d.get_job(:d, ds))
   end
 
   def test_in_loop

data/utils/distance/runner.rb

@@ -35,7 +35,7 @@ class MiGA::DistanceRunner
     elsif !opts[:run_taxonomy] and dataset.metadata[:db_project]
       ref_path = dataset.metadata[:db_project]
       if project.metadata[:db_proj_dir]
-        ref_path = File.expand_path(project.metadata[:db_proj_dir], ref_path)
+        ref_path = File.expand_path(ref_path, project.metadata[:db_proj_dir])
       end
       @ref_project = MiGA::Project.load(ref_path)
       raise "Cannot load reference project: #{ref_path}" if @ref_project.nil?

data/utils/enveomics/Docs/recplot2.md

@@ -117,11 +117,22 @@ library(enveomics.R)
 load('my-recplot.rdata')
 ```
 
-### Average and median sequencing depth
+### Centrality measures of sequencing depth
 
 ```R
 mean(enve.recplot2.seqdepth(rp)) # <- Average
 median(enve.recplot2.seqdepth(rp)) # <- Median
+enve.truncate(enve.recplot2.seqdepth(rp)) # <- 95% Central Truncated Mean
+enve.truncate(enve.recplot2.seqdepth(rp), 0.9) # <- 90% Central Truncated Mean
+```
+
+The functions above only use hits with identity above the cutoff for "in-group" (by default: 95%).
+In order to estimate the sequencing depth with a different identity cutoff, modify the cutoff first:
+
+```R
+rp98 <- enve.recplot2.changeCutoff(rp, 98) # <- Change to ≥98%
+mean(enve.recplot2.seqdepth(rp98)) # <- Average (for the new object)
+median(enve.recplot2.seqdepth(rp98)) # <- Median (for the new object)
 ```
 
 ### Average and median sequencing depth excluding zero-coverage windows
@@ -189,7 +200,7 @@ p <- plot(rp, use.peaks=peaks, layout=4) # <- Remove `layout=4` for the full plo
 dev.off()
 ```
 
-The key function here is `enve.recplo2.findPeaks`. This function has several parameters, depending on
+The key function here is `enve.recplot2.findPeaks`. This function has several parameters, depending on
 the method used. To see all supported methods, use `?enve.recplot2.findPeaks`. To see all the options
 of the default method (`'emauto'`) use `?enve.recplot2.findPeaks.emauto`.
 

data/utils/enveomics/Examples/aai-matrix.bash

@@ -59,8 +59,8 @@ echo "select seq1, seq2, aai, sd, n, omega, (100.0*n/omega) from aai;" \
 echo "[03/03] Generating distance matrix"
 echo "
 source('$(dirname $0)/../enveomics.R/R/df2dist.R');
-a <- read.table('$OUT', sep='\\t', h=TRUE, as.is=T);
-aai.d <- enve.df2dist(a, default.d=$DEF_DIST, max.sim=100);
+a <- read.table('$OUT', sep = '\\t', header = TRUE, as.is = TRUE, quote = '');
+aai.d <- enve.df2dist(a, default.d = $DEF_DIST, max.sim = 100);
 write.table(as.matrix(aai.d), '$OUT.dist',
-  quote=FALSE, col.names=NA, row.names=TRUE, sep='\\t')
+  quote = FALSE, col.names = NA, row.names = TRUE, sep = '\\t')
 " | R --vanilla >/dev/null

data/utils/enveomics/Examples/ani-matrix.bash

@@ -59,8 +59,8 @@ echo "select seq1, seq2, ani, sd, n, omega, (100.0*n/omega) from ani;" \
 echo "[03/03] Generating distance matrix"
 echo "
 source('$(dirname $0)/../enveomics.R/R/df2dist.R');
-a <- read.table('$OUT', sep='\\t', h=TRUE, as.is=T);
-ani.d <- enve.df2dist(a, default.d=$DEF_DIST, max.sim=100);
+a <- read.table('$OUT', sep = '\\t', header = TRUE, as.is = TRUE, quote = '');
+ani.d <- enve.df2dist(a, default.d = $DEF_DIST, max.sim = 100);
 write.table(as.matrix(ani.d), '$OUT.dist',
-  quote=FALSE, col.names=NA, row.names=TRUE, sep='\\t')
+  quote = FALSE, col.names = NA, row.names = TRUE, sep = '\\t')
 " | R --vanilla >/dev/null

data/utils/enveomics/Makefile

@@ -7,7 +7,7 @@ include globals.mk
 
 TEST=Tests
 enveomics_r=enveomics.R
-enveomics_r_v=enveomics.R_1.3
+enveomics_r_v=enveomics.R_$(shell grep '^Version: ' enveomics.R/DESCRIPTION | perl -pe 's/.*: //')
 .PHONY: test install install-scripts install-r uninstall install-deps
 
 test: $(enveomics_r_v).tar.gz
@@ -41,7 +41,7 @@ uninstall:
 	-$(R) CMD REMOVE $(enveomics_r)
 
 $(enveomics_r_v).tar.gz: install-deps
-	-rm -r $(enveomics_r).tar.gz
+	rm -f $(enveomics_r_v).tar.gz
 	./build_enveomics_r.bash
 	$(R) CMD build $(enveomics_r)/
 	$(MAKE) install-r

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

@@ -99,6 +99,7 @@
         "files using <map.bls> as prefix with extensions .rec (for the",
         "recruitment plot) and .lim (for the limits of the different sequences",
         "in <seq.fa>)."],
+      "see_also": ["BlastTab.recplot2.R", "GFF.catsbj.pl"],
       "help_arg": "-h",
       "options": [
          {
@@ -119,8 +120,8 @@
            "opt": "-s",
            "name": "Subset",
            "description": ["The FastA provided is to be treated as a subset of",
-             "the subject. By default, it expects all the subjects to be",
-             "present in the BLAST."]
+             "the subject. By default, it expects all the BLAST subjects to be",
+             "present in the FastA."]
          },
          {
            "opt": "-q",
@@ -623,7 +624,8 @@
         { "r_package": "optparse" },
         { "r_package": "enveomics.R" }
       ],
-      "see_also": [ "RecPlot2.compareIdentities.R" ],
+      "see_also": ["BlastTab.catsbj.pl", "GFF.catsbj.pl",
+        "RecPlot2.compareIdentities.R"],
       "options": [
         {
           "opt": "--prefix",
@@ -637,7 +639,13 @@
           "opt": "--pos-breaks",
           "arg": "integer",
           "default": 1000,
-          "description": ["Breaks in the positions histogram."]
+          "description": "Breaks in the positions histogram."
+        },
+        {
+          "opt": "--pos-breaks-tsv",
+          "arg": "in_file",
+          "description": ["File with (absolute) coordinates of breaks in the",
+            "position histogram."]
         },
         {
           "opt": "--id-breaks",

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

@@ -216,6 +216,50 @@
         }
       ]
     },
+    {
+      "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",
@@ -298,6 +342,49 @@
         }
       ]
     },
+    {
+      "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."
+        },
+        {
+          "name": "Output file",
+          "opt": "--out",
+          "arg": "out_file",
+          "mandatory": true,
+          "description": "Output FastA file."
+        },
+        {
+          "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.",
@@ -432,6 +519,7 @@
       "task": "FastA.subsample.pl",
       "description": "Subsamples a set of sequences.",
       "help_arg": "-h",
+      "see_also": "FastA.sample.rb",
       "options": [
         {
           "name": "Fraction",
@@ -548,6 +636,53 @@
         }
       ]
     },
+    {
+      "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",

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

@@ -743,6 +743,55 @@
           "description": "Verbously display warnings."
         }
       ]
+    },
+    {
+      "task": "GFF.catsbj.pl",
+      "description": ["Generates a list of coordinates from a GFF table",
+        "concatenating the subject sequences."],
+      "help_arg": "-h",
+      "see_also": ["BlastTab.recplot2.R", "BlastTab.catsbj.pl"],
+      "options": [
+        {
+          "name": "Lim file",
+          "opt": "-L",
+          "arg": "out_file",
+          "description": ["An output file with the absolute coordinates of the",
+            "concatenated contigs. This is identical to the .lim file",
+            "generated by BlastTab.catsbj.pl."]
+        },
+        {
+          "name": "Inter-feature gaps",
+          "opt": "-i",
+          "description": ["Preserve exact coordinates and include",
+            "inter-feature windows as separate bins. By default, the",
+            "coordinates are set in the midpoint between features when",
+            "non-contiguous."]
+        },
+        {
+          "name": "Subset",
+          "opt": "-s",
+          "description": ["The FastA provided is to be treated as a subset of",
+            "the subject. By default, it expects all the contigs to be present",
+            "in the BLAST."]
+        },
+        {
+          "name": "Quiet",
+          "opt": "-q",
+          "description": "Run quietly."
+        },
+        {
+          "name": "Subject sequences",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Subject sequences (contigs) in FastA format."
+        },
+        {
+          "name": "Features",
+          "arg": "in_file",
+          "mandatory": true,
+          "description": "Features to map in GFF."
+        }
+      ]
     }
   ]
 }