miga-base 0.3.0.0 → 0.3.0.1

data/scripts/clade_finding.bash

@@ -26,7 +26,7 @@ ogs.mcl.rb -d . -o miga-project.ani95-clades -t "$CORES" -b \
 rm genome-genome.ani95.rbm
 
 # Propose clade projects
-cat miga-project.ani95-clades | tail -n +2 | tr "," "\\t" | awk 'NF >= 5' \
+tail -n +2 miga-project.ani95-clades | tr "," "\\t" | awk 'NF >= 5' \
   > miga-project.proposed-clades
 
 # Run R code (except in projects type clade)

data/scripts/init.bash

@@ -109,7 +109,7 @@ echo "export PATH=\$MIGA_PATH\$PATH" >> "$HOME/.miga_rc"
 # Check for R packages
 echo "
 Looking for R packages:" >&2
-RLIBS="enveomics.R ape phangorn phytools ggdendro ggplot2 gridExtra cluster dendextend vegan scatterplot3d"
+RLIBS="enveomics.R ape phangorn phytools cluster vegan"
 for lib in $RLIBS ; do
   if ! check_rlib "$lib" ; then
     echo "+ Installing $lib" >&2

data/scripts/miga.bash

@@ -3,7 +3,7 @@ set -e
 #MIGA=${MIGA:-$(cd "$(dirname "$0")/.."; pwd)}
 # shellcheck source=/dev/null
 source "$HOME/.miga_rc"
-export PATH="$MIGA/bin:$PATH"
+export PATH="$MIGA/bin:$MIGA/utils/enveomics/Scripts:$PATH"
 SCRIPT=${SCRIPT:-$(basename "$0" .bash)}
 
 function exists { [[ -e "$1" ]] ; }

data/scripts/mytaxa.bash

@@ -12,82 +12,88 @@ cd "$DIR"
 
 # Initialize
 miga date > "$DATASET.start"
-MT=$(dirname -- "$(which MyTaxa)")
+if [[ "$MIGA_MYTAXA" == "no" ]] ; then
+  echo "This system doesn't currently support MyTaxa." \
+    > "$DATASET.nomytaxa.txt"
+else
+  MT=$(dirname -- "$(which MyTaxa)")
 
-# Check type of dataset
-MULTI=$(miga list_datasets -P "$PROJECT" -D "$DATASET" --multi \
-  | wc -l | awk '{print $1}')
-if [[ "$MULTI" -eq "1" ]] ; then
-  # Check requirements
-  if [[ ! -e "$MT/AllGenomes.faa.dmnd" ]] ; then
-    echo "Cannot locate the database: $MT/AllGenomes.faa.dmnd:" \
-          "no such file or directory" >&2
-    exit 1
-  fi
-  if [[ ! -d "$MT/db" ]] ; then
-    echo "Cannot locate the MyTaxa index: $MT/db:" \
-	  "no such file or directory" >&2
-    exit 1
-  fi
-  if [[ ! -d "$MT/utils" ]] ; then
-    echo "Cannot locate the MyTaxa utilities: $MT/utils:" \
-          "no such file or directory" >&2
-    exit 1
-  fi
-   
-  # Execute search
-  diamond blastp -q "../../../06.cds/$DATASET.faa" -d "$MT/AllGenomes.faa" \
-    -a "$DATASET.daa" -k 5 -p "$CORES" --min-score 60
-  diamond view -a "$DATASET.daa" -o "$DATASET.blast"
+  # Check type of dataset
+  MULTI=$(miga list_datasets -P "$PROJECT" -D "$DATASET" --multi \
+    | wc -l | awk '{print $1}')
+  if [[ "$MULTI" -eq "1" ]] ; then
+    # Check requirements
+    if [[ ! -e "$MT/AllGenomes.faa.dmnd" ]] ; then
+      echo "Cannot locate the database: $MT/AllGenomes.faa.dmnd:" \
+            "no such file or directory" >&2
+      exit 1
+    fi
+    if [[ ! -d "$MT/db" ]] ; then
+      echo "Cannot locate the MyTaxa index: $MT/db:" \
+            "no such file or directory" >&2
+      exit 1
+    fi
+    if [[ ! -d "$MT/utils" ]] ; then
+      echo "Cannot locate the MyTaxa utilities: $MT/utils:" \
+            "no such file or directory" >&2
+      exit 1
+    fi
+     
+    # Execute search
+    diamond blastp -q "../../../06.cds/$DATASET.faa" -d "$MT/AllGenomes.faa" \
+      -a "$DATASET.daa" -k 5 -p "$CORES" --min-score 60
+    diamond view -a "$DATASET.daa" -o "$DATASET.blast"
 
-  # Prepare MyTaxa input, execute MyTaxa, and generate profiles
-  [[ -e "../../../06.cds/$DATASET.gff2.gz" ]] \
-    && [[ ! -e "../../../06.cds/$DATASET.gff2" ]] \
-    && gunzip "../../../06.cds/$DATASET.gff2.gz"
-  [[ -e "../../../06.cds/$DATASET.gff3.gz" ]] \
-    && [[ ! -e "../../../06.cds/$DATASET.gff3" ]] \
-    && gunzip "../../../06.cds/$DATASET.gff3.gz"
-  if [[ -e "../../../06.cds/$DATASET.gff2" ]] ; then
-    # GFF2
-    perl "$MT/utils/infile_convert.pl" -f gff2 \
-      "../../../06.cds/$DATASET.gff2" "$DATASET.blast" \
-      | sort -k 13 > "$DATASET.mytaxain"
-    "$MT/MyTaxa" "$DATASET.mytaxain" "$DATASET.mytaxa" "0.5"
-    perl "$MT/utils/MyTaxa.distribution.pl" -m "$DATASET.mytaxa" \
-      -g "../../../06.cds/$DATASET.gff2" -f gff2 \
-      -I "$DATASET.mytaxa.innominate" -G "$DATASET.mytaxa.genes" \
-      -K "$DATASET.mytaxa.krona" -u
-  elif [[ -e "../../../06.cds/$DATASET.gff3" ]] ; then
-    # GFF3
-    perl "$MT/utils/infile_convert.pl" -f gff3 \
-      "../../../06.cds/$DATASET.gff3" "$DATASET.blast" | sort -k 13 \
-      > "$DATASET.mytaxain"
-    "$MT/MyTaxa" "$DATASET.mytaxain" "$DATASET.mytaxa" "0.5"
-    perl "$MT/utils/MyTaxa.distribution.pl" -m "$DATASET.mytaxa" \
-      -g "../../../06.cds/$DATASET.gff3" -f gff3 \
-      -I "$DATASET.mytaxa.innominate" -G "$DATASET.mytaxa.genes" \
-      -K "$DATASET.mytaxa.krona" -u
-  else
-    # No GFF
-    perl "$MT/utils/infile_convert.pl" -f no "LOREM_IPSUM" "$DATASET.blast" \
-      | sort -k 13 > "$DATASET.mytaxain"
-    "$MT/MyTaxa" "$DATASET.mytaxain" "$DATASET.mytaxa" "0.5"
-    perl "$MT/utils/MyTaxa.distribution.pl" -m "$DATASET.mytaxa" \
-      -I "$DATASET.mytaxa.innominate" -G "$DATASET.mytaxa.genes" \
-      -K "$DATASET.mytaxa.krona" -u
-  fi
+    # Prepare MyTaxa input, execute MyTaxa, and generate profiles
+    [[ -e "../../../06.cds/$DATASET.gff2.gz" ]] \
+      && [[ ! -e "../../../06.cds/$DATASET.gff2" ]] \
+      && gunzip "../../../06.cds/$DATASET.gff2.gz"
+    [[ -e "../../../06.cds/$DATASET.gff3.gz" ]] \
+      && [[ ! -e "../../../06.cds/$DATASET.gff3" ]] \
+      && gunzip "../../../06.cds/$DATASET.gff3.gz"
+    if [[ -e "../../../06.cds/$DATASET.gff2" ]] ; then
+      # GFF2
+      perl "$MT/utils/infile_convert.pl" -f gff2 \
+        "../../../06.cds/$DATASET.gff2" "$DATASET.blast" \
+        | sort -k 13 > "$DATASET.mytaxain"
+      "$MT/MyTaxa" "$DATASET.mytaxain" "$DATASET.mytaxa" "0.5"
+      perl "$MT/utils/MyTaxa.distribution.pl" -m "$DATASET.mytaxa" \
+        -g "../../../06.cds/$DATASET.gff2" -f gff2 \
+        -I "$DATASET.mytaxa.innominate" -G "$DATASET.mytaxa.genes" \
+        -K "$DATASET.mytaxa.krona" -u
+    elif [[ -e "../../../06.cds/$DATASET.gff3" ]] ; then
+      # GFF3
+      perl "$MT/utils/infile_convert.pl" -f gff3 \
+        "../../../06.cds/$DATASET.gff3" "$DATASET.blast" | sort -k 13 \
+        > "$DATASET.mytaxain"
+      "$MT/MyTaxa" "$DATASET.mytaxain" "$DATASET.mytaxa" "0.5"
+      perl "$MT/utils/MyTaxa.distribution.pl" -m "$DATASET.mytaxa" \
+        -g "../../../06.cds/$DATASET.gff3" -f gff3 \
+        -I "$DATASET.mytaxa.innominate" -G "$DATASET.mytaxa.genes" \
+        -K "$DATASET.mytaxa.krona" -u
+    else
+      # No GFF
+      perl "$MT/utils/infile_convert.pl" -f no "LOREM_IPSUM" "$DATASET.blast" \
+        | sort -k 13 > "$DATASET.mytaxain"
+      "$MT/MyTaxa" "$DATASET.mytaxain" "$DATASET.mytaxa" "0.5"
+      perl "$MT/utils/MyTaxa.distribution.pl" -m "$DATASET.mytaxa" \
+        -I "$DATASET.mytaxa.innominate" -G "$DATASET.mytaxa.genes" \
+        -K "$DATASET.mytaxa.krona" -u
+    fi
+
+    # Execute Krona
+    ktImportText -o "$DATASET.html" -n biota "$DATASET.mytaxa.krona,$DATASET"
 
-  # Execute Krona
-  ktImportText -o "$DATASET.html" -n biota "$DATASET.mytaxa.krona,$DATASET"
+    # Gzip and cleanup
+    [[ -e "../../../06.cds/$DATASET.gff2" ]] \
+      && gzip -9 -f "../../../06.cds/$DATASET.gff2"
+    [[ -e "../../../06.cds/$DATASET.gff3" ]] \
+      && gzip -9 -f "../../../06.cds/$DATASET.gff3"
+    gzip -9 -f "$DATASET.mytaxain"
+    gzip -9 -f "$DATASET.blast"
+    rm "$DATASET.daa"
+  fi
 
-  # Gzip and cleanup
-  [[ -e "../../../06.cds/$DATASET.gff2" ]] \
-    && gzip -9 -f "../../../06.cds/$DATASET.gff2"
-  [[ -e "../../../06.cds/$DATASET.gff3" ]] \
-    && gzip -9 -f "../../../06.cds/$DATASET.gff3"
-  gzip -9 -f "$DATASET.mytaxain"
-  gzip -9 -f "$DATASET.blast"
-  rm "$DATASET.daa"
 fi
 
 # Finalize

data/scripts/mytaxa_scan.bash

@@ -12,76 +12,81 @@ cd "$DIR"
 
 # Initialize
 miga date > "$DATASET.start"
-MT=$(dirname -- "$(which MyTaxa)")
-TMPDIR=$(mktemp -d /tmp/MiGA.XXXXXXXXXXXX)
-trap "rm -rf '$TMPDIR'; exit" SIGHUP SIGINT SIGTERM
+if [[ "$MIGA_MYTAXA" == "no" ]] ; then
+  echo "This system doesn't currently support MyTaxa." \
+    > "$DATASET.nomytaxa.txt"
+else
+  MT=$(dirname -- "$(which MyTaxa)")
+  TMPDIR=$(mktemp -d /tmp/MiGA.XXXXXXXXXXXX)
+  trap "rm -rf '$TMPDIR'; exit" SIGHUP SIGINT SIGTERM
 
-# Check type of dataset
-NOMULTI=$(miga list_datasets -P "$PROJECT" -D "$DATASET" --no-multi \
-  | wc -l | awk '{print $1}')
-if [[ "$NOMULTI" -eq "1" ]] ; then
-  # Check requirements
-  if [[ ! -e "$MT/AllGenomes.faa.dmnd" ]] ; then
-    echo "Cannot locate the database: $MT/AllGenomes.faa.dmnd:" \
-          "no such file or directory" >&2
-    exit 1
-  fi
-  if [[ ! -d "$MT/db" ]] ; then
-    echo "Cannot locate the MyTaxa index: $MT/db:" \
-          "no such file or directory" >&2
-    exit 1
-  fi
-  if [[ ! -d "$MT/utils" ]] ; then
-    echo "Cannot locate the MyTaxa utilities: $MT/utils:" \
-          "no such file or directory" >&2
-    exit 1
-  fi
-   
-  if [[ ! -s "$DATASET.mytaxa" ]] ; then
-    # Execute search
-    if [[ ! -s "$DATASET.blast" ]] ; then
-      diamond blastp -q "../../../06.cds/$DATASET.faa" \
-        -d "$MT/AllGenomes.faa" -k 5 -p "$CORES" --min-score 60 \
-        -a "$DATASET.daa" -t "$TMPDIR"
-      diamond view -a "$DATASET.daa" -o "$DATASET.blast" -t "$TMPDIR"
+  # Check type of dataset
+  NOMULTI=$(miga list_datasets -P "$PROJECT" -D "$DATASET" --no-multi \
+    | wc -l | awk '{print $1}')
+  if [[ "$NOMULTI" -eq "1" ]] ; then
+    # Check requirements
+    if [[ ! -e "$MT/AllGenomes.faa.dmnd" ]] ; then
+      echo "Cannot locate the database: $MT/AllGenomes.faa.dmnd:" \
+            "no such file or directory" >&2
+      exit 1
+    fi
+    if [[ ! -d "$MT/db" ]] ; then
+      echo "Cannot locate the MyTaxa index: $MT/db:" \
+            "no such file or directory" >&2
+      exit 1
+    fi
+    if [[ ! -d "$MT/utils" ]] ; then
+      echo "Cannot locate the MyTaxa utilities: $MT/utils:" \
+            "no such file or directory" >&2
+      exit 1
     fi
+     
+    if [[ ! -s "$DATASET.mytaxa" ]] ; then
+      # Execute search
+      if [[ ! -s "$DATASET.blast" ]] ; then
+        diamond blastp -q "../../../06.cds/$DATASET.faa" \
+          -d "$MT/AllGenomes.faa" -k 5 -p "$CORES" --min-score 60 \
+          -a "$DATASET.daa" -t "$TMPDIR"
+        diamond view -a "$DATASET.daa" -o "$DATASET.blast" -t "$TMPDIR"
+      fi
 
-    # Prepare MyTaxa input, execute MyTaxa, and generate profiles
-    perl "$MT/utils/infile_convert.pl" -f no "LOREM_IPSUM" "$DATASET.blast" \
-      | sort -k 13 > "$DATASET.mytaxain"
-    "$MT/MyTaxa" "$DATASET.mytaxain" "$DATASET.mytaxa" "0.5"
-  fi
-  ruby "$MIGA/utils/mytaxa_scan.rb" "../../../06.cds/$DATASET.faa" \
-        "$DATASET.mytaxa" "$DATASET.wintax"
-  echo "
-  source('$MIGA/utils/mytaxa_scan.R');
-  pdf('$DATASET.pdf', 12, 7);
-  mytaxa.scan('$DATASET.wintax');
-  dev.off();
-  " | R --vanilla
+      # Prepare MyTaxa input, execute MyTaxa, and generate profiles
+      perl "$MT/utils/infile_convert.pl" -f no "LOREM_IPSUM" "$DATASET.blast" \
+        | sort -k 13 > "$DATASET.mytaxain"
+      "$MT/MyTaxa" "$DATASET.mytaxain" "$DATASET.mytaxa" "0.5"
+    fi
+    ruby "$MIGA/utils/mytaxa_scan.rb" "../../../06.cds/$DATASET.faa" \
+          "$DATASET.mytaxa" "$DATASET.wintax"
+    echo "
+    source('$MIGA/utils/mytaxa_scan.R');
+    pdf('$DATASET.pdf', 12, 7);
+    mytaxa.scan('$DATASET.wintax');
+    dev.off();
+    " | R --vanilla
+
+    # Extract genes from flagged regions
+    [[ -d "$DATASET.reg" ]] || mkdir "$DATASET.reg"
+    if [[ -e "$DATASET.wintax.regions" ]] ; then
+      i=0
+      for win in $(cat "$DATASET.wintax.regions") ; do
+        let i=$i+1
+        awk "NR==$win" "$DATASET.wintax.genes" | tr "\\t" "\\n" \
+          > "$DATASET.reg/$i.ids"
+        FastA.filter.pl -q "$DATASET.reg/$i.ids" \
+          "../../../06.cds/$DATASET.faa" > "$DATASET.reg/$i.faa"
+      done
+    fi
 
-  # Extract genes from flagged regions
-  [[ -d "$DATASET.reg" ]] || mkdir "$DATASET.reg"
-  if [[ -e "$DATASET.wintax.regions" ]] ; then
-    i=0
-    for win in $(cat "$DATASET.wintax.regions") ; do
-      let i=$i+1
-      awk "NR==$win" "$DATASET.wintax.genes" | tr "\\t" "\\n" \
-        > "$DATASET.reg/$i.ids"
-      FastA.filter.pl -q "$DATASET.reg/$i.ids" \
-        "../../../06.cds/$DATASET.faa" > "$DATASET.reg/$i.faa"
-    done
+    # Clean
+    [[ -e "$DATASET.daa" ]] && rm "$DATASET.daa"
+    [[ -s "$DATASET.blast" && ! -s "$DATASET.blast.gz" ]] \
+      && gzip -9 -f "$DATASET.blast"
+    [[ -s "$DATASET.mytaxain" && ! -s "$DATASET.mytaxain.gz" ]] \
+      && gzip -9 -f "$DATASET.mytaxain"
   fi
 
-  # Clean
-  [[ -e "$DATASET.daa" ]] && rm "$DATASET.daa"
-  [[ -s "$DATASET.blast" && ! -s "$DATASET.blast.gz" ]] \
-    && gzip -9 -f "$DATASET.blast"
-  [[ -s "$DATASET.mytaxain" && ! -s "$DATASET.mytaxain.gz" ]] \
-    && gzip -9 -f "$DATASET.mytaxain"
 fi
 
 # Finalize
-rm -R "$TMPDIR"
 miga date > "$DATASET.done"
 miga add_result -P "$PROJECT" -D "$DATASET" -r "$SCRIPT"

data/scripts/ogs.bash

@@ -37,7 +37,7 @@ 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 $MIGA/utils/core-pan-plot.R \
+Rscript "$MIGA/utils/core-pan-plot.R" \
   miga-project.core-pan.tsv miga-project.core-pan.pdf
 
 # Finalize

data/scripts/trimmed_fasta.bash

@@ -21,13 +21,14 @@ for sis in 1 2 ; do
 done
 
 # FastQ -> FastA
-FastQ.toFastA.awk < "../02.trimmed_reads/$b.1.clipped.fastq" > "$b.1.fasta"
+FQ2A="$MIGA/utils/enveomics/Scripts/FastQ.toFastA.awk"
+awk -f "$FQ2A" < "../02.trimmed_reads/$b.1.clipped.fastq" > "$b.1.fasta"
 if [[ -e "../02.trimmed_reads/$b.2.clipped.fastq" ]] ; then
-  FastQ.toFastA.awk < "../02.trimmed_reads/$b.2.clipped.fastq" > "$b.2.fasta"
+  awk -f "$FQ2A" < "../02.trimmed_reads/$b.2.clipped.fastq" > "$b.2.fasta"
   FastA.interpose.pl "$b.CoupledReads.fa" "$b".[12].fasta
   gzip -9 -f "$b.2.fasta"
   gzip -9 -f "$b.1.fasta"
-  FastQ.toFastA.awk < "../02.trimmed_reads/$b".[12].clipped.single.fastq \
+  awk -f "$FQ2A" < "../02.trimmed_reads/$b".[12].clipped.single.fastq \
     > "$b.SingleReads.fa"
   gzip -9 -f "$b.SingleReads.fa"
 else

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

@@ -0,0 +1,66 @@
+#!/bin/bash
+
+# @author  Luis M. Rodriguez-R
+# @license Artistic-2.0
+
+set -e # <- So it stops if there is an error
+function exists { [[ -e "$1" ]] ; } # <- To test *any* of many files
+
+OUT=$1		# <- Output file
+[[ -n "$1" ]] && shift
+SEQS=("$@")	# <- list of all genomes
+THR=2		# <- Number or threads
+DEF_DIST=0.9	# <- Default distance when AAI cannot be reliably estimated
+
+# This is just the help message
+if [[ $# -lt 2 ]] ; then
+echo "
+Use case: Building AAI matrices from a collection of genomes.
+
+IMPORTANT
+This script is functional, but it's mainly intended for illustrative purposes.
+Please take a look at the code first.
+
+Usage:
+$0 <output.txt> <genomes...>
+
+<output.txt>	The output AAI list, in tab-delimited form containing the
+		following columns: (1) Sequence A, (2) Sequence B, (3)
+		AAI, (4) AAI-SD, (5) Proteins used, (6) Number of proteins in
+		the smallest genome, (7) Percentage of the genome shared.
+<genomes...>	The list of files containing the genomes (at least 2).
+
+" >&2
+exit
+fi
+
+# 00. Create environment
+export PATH=$(dirname "$0")/../Scripts:$PATH
+
+# 01. Calculate AAI
+echo "[01/03] Calculating AAI"
+for i in "${SEQS[@]}" ; do
+  for j in "${SEQS[@]}" ; do
+    echo -n " o $i vs $j: "
+    AAI=$(aai.rb -1 "$i" -2 "$j" -S "$OUT.db" -t "$THR" \
+      --no-save-rbm --auto --quiet)
+    echo ${AAI:-Below detection}
+    [[ "$i" == "$j" ]] && break
+  done
+done
+
+# 02. Extract matrix
+echo "[02/03] Extracting list"
+echo -e "SeqA\tSeqB\tAAI\tSD\tN\tOmega\tFrx" > "$OUT"
+echo "select seq1, seq2, aai, sd, n, omega, (100.0*n/omega) from aai;" \
+  | sqlite3 "$OUT.db" | tr '|' '\t' >> "$OUT"
+
+# 03. Make it a distance matrix.
+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=$DEF_DIST, max.sim=100);
+write.table(as.matrix(aai.d), '$OUT.dist',
+  quote=FALSE, col.names=NA, row.names=TRUE, sep='\\t')
+" | R --vanilla >/dev/null

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

@@ -0,0 +1,66 @@
+#!/bin/bash
+
+# @author  Luis M. Rodriguez-R
+# @license Artistic-2.0
+
+set -e # <- So it stops if there is an error
+function exists { [[ -e "$1" ]] ; } # <- To test *any* of many files
+
+OUT=$1		# <- Output file
+[[ -n "$1" ]] && shift
+SEQS=("$@")	# <- list of all genomes
+THR=2		# <- Number or threads
+DEF_DIST=0.9	# <- Default distance when ANI cannot be reliably estimated
+
+# This is just the help message
+if [[ $# -lt 2 ]] ; then
+echo "
+Use case: Building ANI matrices from a collection of genomes.
+
+IMPORTANT
+This script is functional, but it's mainly intended for illustrative purposes.
+Please take a look at the code first.
+
+Usage:
+$0 <output.txt> <genomes...>
+
+<output.txt>	The output ANI list, in tab-delimited form containing the
+		following columns: (1) Sequence A, (2) Sequence B, (3)
+		ANI, (4) ANI-SD, (5) Fragments used, (6) Maximum number
+		of fragments, (7) Percentage of the genome shared.
+<genomes...>	The list of files containing the genomes (at least 2).
+
+" >&2
+exit
+fi
+
+# 00. Create environment
+export PATH=$(dirname "$0")/../Scripts:$PATH
+
+# 01. Calculate ANI
+echo "[01/03] Calculating ANI"
+for i in "${SEQS[@]}" ; do
+  for j in "${SEQS[@]}" ; do
+    echo -n " o $i vs $j: "
+    ANI=$(ani.rb -1 "$i" -2 "$j" -S "$OUT.db" -t "$THR" \
+      --no-save-rbm --no-save-regions --auto --quiet)
+    echo ${ANI:-Below detection}
+    [[ "$i" == "$j" ]] && break
+  done
+done
+
+# 02. Extract matrix
+echo "[02/03] Extracting list"
+echo -e "SeqA\tSeqB\tANI\tSD\tN\tOmega\tFrx" > "$OUT"
+echo "select seq1, seq2, ani, sd, n, omega, (100.0*n/omega) from ani;" \
+  | sqlite3 "$OUT.db" | tr '|' '\t' >> "$OUT"
+
+# 03. Make it a distance matrix.
+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=$DEF_DIST, max.sim=100);
+write.table(as.matrix(ani.d), '$OUT.dist',
+  quote=FALSE, col.names=NA, row.names=TRUE, sep='\\t')
+" | R --vanilla >/dev/null