miga-base 1.2.15.2 → 1.2.15.4

data/utils/enveomics/Pipelines/assembly.pbs/kSelector.R

@@ -1,37 +0,0 @@
-
-# @author: Luis M. Rodriguez-R
-# @update: Nov-29-2012
-
-kSelector <- function(file, lib){
-   red <- rgb(0.6, 0, 0);
-   d <- read.table(file, sep=" ", h=T, fill=T);
-   d <- d[!is.na(d$N50) & !is.na(d$used), ];
-   d$reads <- max(d$reads, na.rm=T)
-   d <- d[order(d$K), ];
-   rownames(d) <- 1:nrow(d);
-   par(mar=c(5,4,4,5)+.1, cex=0.8);
-   barplot(d$reads/1e6, names=d$K, col='white', ylab='Number of reads (in millions)', xlab='K',
-      main=paste('Reads used and N50 by K-mers in the assembly of', lib));
-   barplot(d$used/1e6, col='grey', add=T);
-   par(new=T);
-   plot(1:length(d$K)-0.5, d$N50, col=red, t='b', lty=2, pch=20, cex=1, lwd=1.5,
-      xlim=c(0, length(d$K)), xaxt='n', yaxt='n', xlab='', ylab='');
-   axis(4, col.axis=red);
-   mtext('N50 (bp)', side=4, line=3, col=red);
-   # Suggest best k-mers
-   if(nrow(d) >= 3){
-      x = data.frame(K=d$K, l=(d$N50 - mean(d$N50))/sd(d$N50), u=(d$used - mean(d$used))/sd(d$used));
-      rownames(x) <- rownames(d)
-      d <- cbind(d, sel=FALSE);
-      k_s = c();
-      for(l_star in c(2, 1/2, 1)){
-         k_s_i = x$K[which.max(l_star*x$l + x$u)];
-	 k_s <- c(k_s, k_s_i);
-	 x <- x[x$K!=k_s_i, ];
-	 d$sel[d$K==k_s_i] <- TRUE;
-      }
-      abline(v=as.numeric(rownames(d)[d$sel])-0.5, col='darkgreen', lty=6);
-   }
-   return(d);
-}
-

data/utils/enveomics/Pipelines/assembly.pbs/newbler.pbs

@@ -1,68 +0,0 @@
-#!/bin/bash
-#PBS -l nodes=1:ppn=1
-#PBS -k oe
-
-# Some defaults for the parameters
-BIN454=${BIN454:-"$HOME/454/bin"};
-
-# Check mandatory variables
-if [[ "$LIB" == "" ]]; then
-   echo "Error: LIB is mandatory" >&2
-   exit 1;
-fi
-if [[ "$PDIR" == "" ]]; then
-   echo "Error: PDIR is mandatory" >&2
-   exit 1;
-fi
-if [[ "$KVELVET$KSOAP" == "" ]]; then
-   echo "Error: KVELVET and/or KSOAP are mandatory" >&2
-   exit 1;
-fi
-
-# Prepare input
-KVELVET=$(echo $KVELVET | sed -e 's/:/ /g')
-KSOAP=$(echo $KSOAP | sed -e 's/:/ /g')
-NP=$(cat "$PBS_NODEFILE" | wc -l)
-CWD=$(pwd)
-DIR="$CWD/$LIB.newbler"
-LOG="$DIR.log"
-module load perl/5.14.4
-export PATH=$PATH:$BIN454
-
-# Create project
-echo new > $DIR.proc
-nohup newAssembly $DIR > $LOG
-
-# Prepare Velvet
-if [[ "$KVELVET" != "" ]] ; then
-   echo pre-velvet > $DIR.proc
-   rm $LIB.velvet.tmp1 &>/dev/null
-   for K in $KVELVET ; do
-      perl "$PDIR/FastA.filterN.pl" "$LIB.velvet_$K/contigs.fa" >> $LIB.velvet.tmp1
-   done
-   perl "$PDIR/newbler_preparator.pl" $LIB.velvet.tmp1 $LIB.velvet.tmp2
-   cd $DIR
-   nohup addRun ../$LIB.velvet.tmp2 >> $LOG
-   cd $CWD
-fi ;
-
-# Prepare SOAP
-if [[ "$KSOAP" != "" ]] ; then
-   echo pre-soap > $DIR.proc
-   rm $LIB.soap.tmp1 &>/dev/null
-   for K in $KSOAP ; do
-      cat "$LIB.soap_$K/O.contig" >> $LIB.soap.tmp1
-   done
-   perl "$PDIR/newbler_preparator.pl" $LIB.soap.tmp1 $LIB.soap.tmp2
-   cd $DIR
-   nohup addRun ../$LIB.soap.tmp2 >> $LOG
-   cd $CWD
-fi ;
-
-# Run
-cd $DIR
-echo newbler > $DIR.proc
-nohup runProject -cpu $NP >> $LOG
-cd $CWD
-echo done > $DIR.proc
-

data/utils/enveomics/Pipelines/assembly.pbs/newbler_preparator.pl

@@ -1,49 +0,0 @@
-#!/usr/bin/perl
-
-
-my ($in, $out) = @ARGV;
-($in and $out) or die "
-Usage: $0 input.fa output.fa
-";
-
-open IN, "<", $in  or die "Cannot read file: $in: $!\n";
-open OUT,">", $out or die "Cannot create file: $out: $!\n";
-
-%reads=();
-@reads=();
-while(<IN>){
-  chomp;
-  if(/^\>/){
-	$tag=$_;
-	$reads{$tag}='';
-	push(@reads,$tag);
-  }else{
-	$reads{$tag}.=$_;
-  }
-}
-close(IN);
-
-for(0..$#reads){
-  $tag=$reads[$_];
-  $read=$reads{$tag};
-  $l=length $read;
-  if($l<100){
-	next;
-  }else{
-	if($l<1500){
-	  print OUT "$tag\n$read\n";
-	}else{
-	  $r=int($l/1500)+1;
-	  $start=0;
-	  $i=1;
-	  while($start<$l-100){
-		$tag_new=$tag.':r'.$i;
-		$i++;
-		$read_new=substr($read,$start,1500);
-		$start+=200;
-		print OUT "$tag_new\n$read_new\n";
-	  }
-	}
-  }
-}
-close(OUT);

data/utils/enveomics/Pipelines/assembly.pbs/soap.pbs

@@ -1,80 +0,0 @@
-#!/bin/bash
-#PBS -k oe
-
-# Some defaults for the parameters
-INSLEN=${INSLEN:-300};
-USECOUPLED=${USECOUPLED:-yes}
-USESINGLE=${USESINGLE:-no}
-CLEANUP=${CLEANUP:-yes}
-
-# Check mandatory variables
-if [[ "$LIB" == "" ]]; then
-   echo "Error: LIB is mandatory" >&2
-   exit 1;
-fi
-if [[ "$PDIR" == "" ]]; then
-   echo "Error: PDIR is mandatory" >&2
-   exit 1;
-fi
-if [[ "$DATA" == "" ]]; then
-   echo "Error: DATA is mandatory" >&2
-   exit 1;
-fi
-
-# Prepare input
-module load perl/5.14.4
-KMER=$PBS_ARRAYID
-DIR="$LIB.soap_$KMER"
-if [[ "$USECOUPLED" == "yes" ]]; then
-   MAXRDLEN=${MAXRDLEN:-$(perl $PDIR/FastA.length.pl "$DATA/$LIB.CoupledReads.fa" | head -n 200000 | awk '{if($2>MAX) MAX=$2} END{print MAX}')}
-elif [[ "$USESINGLE" == "yes" ]]; then
-   MAXRDLEN=${MAXRDLEN:-$(perl $PDIR/FastA.length.pl "$DATA/$LIB.SingleReads.fa" | head -n 200000 | awk '{if($2>MAX) MAX=$2} END{print MAX}')}
-else
-   echo "$0: Error: Nothing to do, neither USECOUPLED nor USESINGLE set to yes." >&2
-   exit 2
-fi
-NP=$(cat "$PBS_NODEFILE" | wc -l)
-
-# Config
-module load SOAP/denovo2/r240
-echo config > $DIR.proc
-echo "max_rd_len=$MAXRDLEN
-[LIB]
-reverse_seq=0
-asm_flag=3
-rank=1" > $DIR.config
-if [[ "$USECOUPLED" == "yes" ]]; then
-   echo "avg_ins=$INSLEN
-p=$DATA/$LIB.CoupledReads.fa" >> $DIR.config
-fi
-if [[ "$USESINGLE" == "yes" ]]; then
-   echo "f=$DATA/$LIB.SingleReads.fa" >> $DIR.config
-fi
-
-
-# Run
-echo pre > $DIR.proc
-if [[ -d $DIR ]] ; then rm -R $DIR ; fi
-mkdir $DIR
-echo soap > $DIR.proc
-SOAPdenovo-63mer all -s $DIR.config -p $NP -K $KMER -o $DIR/O &> $DIR.log
-if [[ -d $DIR ]] ; then
-   if [[ -s $DIR/O.contig ]] ; then
-      if [[ "$CLEANUP" != "no" ]] ; then
-	 echo cleanup > $DIR.proc
-	 rm $DIR/*edge
-	 rm $DIR/*vertex
-	 rm $DIR/*Arc*
-	 rm $DIR/*Graph*
-	 rm $DIR/*readInGap*
-      fi
-      echo done > $DIR.proc
-   else
-      echo "$0: Error: File $DIR/O.contig doesn't exist, something went wrong" >&2
-      exit 1
-   fi
-else
-   echo "$0: Error: Directory $DIR doesn't exist, something went wrong" >&2
-   exit 1
-fi
-

data/utils/enveomics/Pipelines/assembly.pbs/stats.pbs

@@ -1,57 +0,0 @@
-#!/bin/bash
-#PBS -q iw-shared-6
-#PBS -l nodes=1:ppn=1
-#PBS -l mem=1gb
-#PBS -l walltime=3:00:00
-#PBS -k oe
-
-# Check mandatory variables
-if [[ "$LIB" == "" ]]; then
-   echo "Error: LIB is mandatory" >&2
-   exit 1;
-fi
-if [[ "$PDIR" == "" ]]; then
-   echo "Error: PDIR is mandatory" >&2
-   exit 1;
-fi
-
-# Run
-module load perl/5.14.4
-echo "K N50 used reads " > $LIB.velvet.n50
-echo "K N50 used reads " > $LIB.soap.n50
-for ID in $(seq 10 31); do
-   let KMER=$ID*2+1
-   DIRV="$LIB.velvet_$KMER"
-   DIRS="$LIB.soap_$KMER"
-   echo $KMER > $LIB.velvet.n50.$KMER
-   echo $KMER > $LIB.soap.n50.$KMER
-   # N50 (>=500)
-   perl "$PDIR/FastA.N50.pl" "$DIRV/contigs.fa" 500 | grep '^N50' | sed -e 's/.*: //' >> $LIB.velvet.n50.$KMER
-   perl "$PDIR/FastA.N50.pl" "$DIRS/O.contig" 500 | grep '^N50' | sed -e 's/.*: //' >> $LIB.soap.n50.$KMER
-   # Used and Total reads
-   tail -n 1 $DIRV/Log | sed -e 's/.* using \\([0-9]*\\)\\/\\([0-9]*\\) reads.*/\\1\\n\\2/' >> $LIB.velvet.n50.$KMER
-   if [ -e "$DIRS/O.readOnContig" ] ; then
-      cat "$DIRS/O.readOnContig" | grep -vc '^read' >> $LIB.soap.n50.$KMER
-   elif [ -e "$DIRS/O.readOnContig.gz" ] ; then
-      zcat "$DIRS/O.readOnContig.gz" | grep -vc '^read' >> $LIB.soap.n50.$KMER
-   else
-      echo 0 >> $LIB.soap.n50.$KMER
-   fi
-   head -n 1 $DIRS/O.peGrads | awk '{print $3}' >> $LIB.soap.n50.$KMER
-   # Join
-   (cat $LIB.velvet.n50.$KMER | tr "\\n" " "; echo) >> $LIB.velvet.n50
-   rm $LIB.velvet.n50.$KMER
-   (cat $LIB.soap.n50.$KMER | tr "\\n" " "; echo) >> $LIB.soap.n50
-   rm $LIB.soap.n50.$KMER
-done
-
-# Create plot
-module load R/3.1.2
-echo "
-source('$PDIR/kSelector.R');
-pdf('$LIB.n50.pdf', 13, 7);
-kSelector('$LIB.velvet.n50', '$LIB (Velvet)');
-kSelector('$LIB.soap.n50', '$LIB (SOAP)');
-dev.off();
-" | R --vanilla -q
-

data/utils/enveomics/Pipelines/assembly.pbs/velvet.pbs

@@ -1,63 +0,0 @@
-#!/bin/bash
-#PBS -l nodes=1:ppn=1
-#PBS -k oe
-
-# Some defaults for the parameters
-FORMAT=${FORMAT:-fasta};
-INSLEN=${INSLEN:-300};
-USECOUPLED=${USECOUPLED:-yes};
-USESINGLE=${USESINGLE:-no};
-CLEANUP=${CLEANUP:-yes}
-
-# Check mandatory variables
-if [[ "$LIB" == "" ]]; then
-   echo "Error: LIB is mandatory" >&2
-   exit 1;
-fi
-if [[ "$PDIR" == "" ]]; then
-   echo "Error: PDIR is mandatory" >&2
-   exit 1;
-fi
-if [[ "$DATA" == "" ]]; then
-   echo "Error: DATA is mandatory" >&2
-   exit 1;
-fi
-
-# Prepare input
-KMER=$PBS_ARRAYID
-CWD=$(pwd)
-DIR="$CWD/$LIB.velvet_$KMER"
-
-# Run
-module load velvet/1.2.10
-echo velveth > $DIR.proc
-CMD="velveth_101_omp $DIR $KMER -$FORMAT"
-if [[ "$USECOUPLED" == "yes" ]]; then
-   CMD="$CMD -shortPaired $DATA/$LIB.CoupledReads.fa"
-fi
-if [[ "$USESINGLE" == "yes" ]]; then
-   CMD="$CMD -short $DATA/$LIB.SingleReads.fa"
-fi
-if [[ "$VELVETH_EXTRA" != "" ]]; then
-   CMD="$CMD $VELVETH_EXTRA"
-fi
-$CMD &> $DIR.hlog
-echo velvetg > $DIR.proc
-velvetg_101_omp "$DIR" -exp_cov auto -cov_cutoff auto -ins_length "$INSLEN" $VELVETG_EXTRA &> $DIR.glog
-if [[ -d $DIR ]] ; then
-   if [[ -s $DIR/contigs.fa ]] ; then
-      if [[ "$CLEANUP" != "no" ]] ; then
-	 echo cleanup > $DIR.proc
-	 rm $DIR/Sequences
-	 rm $DIR/Roadmaps
-	 rm $DIR/*Graph*
-      fi
-      echo done > $DIR.proc
-   else
-      echo "$0: Error: File $DIR/contigs.fa doesn't exist, something went wrong" >&2
-      exit 1
-   fi
-else
-   echo "$0: Error: Directory $DIR doesn't exist, something went wrong" >&2
-   exit 1
-fi

data/utils/enveomics/Pipelines/blast.pbs/01.pbs.bash

@@ -1,38 +0,0 @@
-# blast.pbs pipeline
-# Step 01 : Initialize input files
-
-# 00. Read configuration
-cd $SCRATCH ;
-TASK="dry" ;
-source "$PDIR/RUNME.bash" ;
-echo "$PBS_JOBID" > "$SCRATCH/success/01.00" ;
-
-if [[ ! -e "$SCRATCH/success/01.01" ]] ; then
-   # 01. BEGIN
-   REGISTER_JOB "01" "01" "Custom BEGIN function" \
-      && BEGIN \
-      || exit 1 ;
-   touch "$SCRATCH/success/01.01" ;
-fi
-
-if [[ ! -e "$SCRATCH/success/01.02" ]] ; then
-   # 02. Split
-   [[ -d "$SCRATCH/tmp/split" ]] && rm -R "$SCRATCH/tmp/split" ;
-   REGISTER_JOB "01" "02" "Splitting query files" \
-      && mkdir "$SCRATCH/tmp/split" \
-      && perl "$PDIR/FastA.split.pl" "$INPUT" "$SCRATCH/tmp/split/$PROJ" "$MAX_JOBS" \
-      || exit 1 ;
-   touch "$SCRATCH/success/01.02" ;
-fi ;
-
-if [[ ! -e "$SCRATCH/success/01.03" ]] ; then
-   # 03. Finalize
-   REGISTER_JOB "01" "03" "Finalizing input preparation" \
-      && mv "$SCRATCH/tmp/split" "$SCRATCH/tmp/in" \
-      || exit 1 ;
-   touch "$SCRATCH/success/01.03" ;
-fi ;
-
-[[ -d "$SCRATCH/tmp/out" ]] || ( mkdir "$SCRATCH/tmp/out" || exit 1 ) ;
-JOB_DONE "01" ;
-

data/utils/enveomics/Pipelines/blast.pbs/02.pbs.bash

@@ -1,73 +0,0 @@
-# blast.pbs pipeline
-# Step 02 : Run BLAST
-
-# Read configuration
-cd $SCRATCH ;
-TASK="dry" ;
-source "$PDIR/RUNME.bash" ;
-
-# 00. Initial vars
-ID_N=$PBS_ARRAYID
-[[ "$ID_N" == "" ]] && exit 1 ;
-[[ -e "$SCRATCH/success/02.$ID_N" ]] && exit 0 ;
-IN="$SCRATCH/tmp/in/$PROJ.$ID_N.fa" ;
-OUT="$SCRATCH/tmp/out/$PROJ.blast.$ID_N" ;
-FINAL_OUT="$SCRATCH/results/$PROJ.$ID_N.blast" ;
-if [[ -e "$SCRATCH/success/02.$ID_N.00" ]] ; then
-   pre_job=$(cat "$SCRATCH/success/02.$ID_N.00") ;
-   state=$(qstat -f "$pre_job" 2>/dev/null | grep job_state | sed -e 's/.*= //')
-   if [[ "$state" == "R" ]] ; then
-      echo "Warning: This task is already being executed by $pre_job. Aborting." >&2 ;
-      exit 0 ;
-   elif [[ "$state" == "" ]] ; then
-      echo "Warning: This task was initialized by $pre_job, but it's currently not running. Superseding." >&2 ;
-   fi ;
-fi
-echo "$PBS_JOBID" > "$SCRATCH/success/02.$ID_N.00" ;
-
-# 01. Before BLAST
-if [[ ! -e "$SCRATCH/success/02.$ID_N.01" ]] ; then
-   BEFORE_BLAST "$IN" "$OUT" || exit 1 ;
-   touch "$SCRATCH/success/02.$ID_N.01" ;
-fi ;
-
-# 02. Run BLAST
-if [[ ! -e "$SCRATCH/success/02.$ID_N.02" ]] ; then
-   # Recover previous runs, if any
-   if [[ -s "$OUT" ]] ; then
-      perl "$PDIR/BlastTab.recover_job.pl" "$IN" "$OUT" \
-	 || exit 1 ;
-   fi ;
-   # Run BLAST
-   RUN_BLAST "$IN" "$OUT" \
-      && mv "$OUT" "$OUT-z" \
-      || exit 1 ;
-   touch "$SCRATCH/success/02.$ID_N.02" ;
-fi ;
-
-# 03. Collect BLAST parts
-if [[ ! -e "$SCRATCH/success/02.$ID_N.03" ]] ; then
-   if [[ -e "$OUT" ]] ; then
-      echo "Warning: The file $OUT pre-exists, but the BLAST collection was incomplete." >&2 ;
-      echo "  I'm assuming that it corresponds to the first part of the result, but you should check manually." >&2 ;
-      echo "  The last lines are:" >&2 ;
-      tail -n 3 "$OUT" >&2 ;
-   else
-      touch "$OUT" || exit 1 ;
-   fi ;
-   for i in $(ls $OUT-*) ; do
-      cat "$i" >> "$OUT" ;
-      rm "$i" || exit 1 ;
-   done ;
-   mv "$OUT" "$FINAL_OUT"
-   touch "$SCRATCH/success/02.$ID_N.03" ;
-fi ;
-
-# 04. After BLAST
-if [[ ! -e "$SCRATCH/success/02.$ID_N.04" ]] ; then
-   AFTER_BLAST "$IN" "$FINAL_OUT" || exit 1 ;
-   touch "$SCRATCH/success/02.$ID_N.04" ;
-fi ;
-
-touch "$SCRATCH/success/02.$ID_N" ;
-

data/utils/enveomics/Pipelines/blast.pbs/03.pbs.bash

@@ -1,21 +0,0 @@
-# blast.pbs pipeline
-# Step 03 : Finalize
-
-# Read configuration
-cd $SCRATCH ;
-TASK="dry" ;
-source "$PDIR/RUNME.bash" ;
-PREFIX="$SCRATCH/results/$PROJ" ;
-OUT="$SCRATCH/$PROJ.blast" ;
-echo "$PBS_JOBID" > "$SCRATCH/success/02.00" ;
-
-# 01. END
-if [[ ! -e "$SCRATCH/success/03.01" ]] ; then
-   REGISTER_JOB "03" "01" "Custom END function" \
-      && END "$PREFIX" "$OUT" \
-      || exit 1 ;
-   touch "$SCRATCH/success/03.01" ;
-fi ;
-
-JOB_DONE "03" ;
-

data/utils/enveomics/Pipelines/blast.pbs/BlastTab.recover_job.pl

@@ -1,72 +0,0 @@
-#!/usr/bin/perl
-
-use warnings;
-use strict;
-use File::Copy;
-
-my($fasta, $blast) = @ARGV;
-
-($fasta and $blast) or die "
-.USAGE:
-   $0 query.fa blast.txt
-
-   query.fa	Query sequences in FastA format.
-   blast.txt	Incomplete BLAST output in tabular format.
-
-";
-
-print "Fixing $blast:\n";
-my $blast_res;
-for(my $i=0; 1; $i++){
-   $blast_res = "$blast-$i";
-   last unless -e $blast_res;
-}
-open BLAST, "<", $blast or die "Cannot read the file: $blast: $!\n";
-open TMP, ">", "$blast-tmp" or die "Cannot create the file: $blast-tmp: $!\n";
-my $last="";
-my $last_id="";
-my $before = "";
-while(my $ln=<BLAST>){
-   chomp $ln;
-   last unless $ln =~ m/(.+?)\t/;
-   my $id = $1;
-   if($id eq $last_id){
-      $last.= $ln."\n";
-   }else{
-      print TMP $last if $last;
-      $before = $last_id;
-      $last = $ln."\n";
-      $last_id = $id;
-   }
-}
-close BLAST;
-close TMP;
-
-move "$blast-tmp", $blast_res or die "Cannot move file $blast-tmp into $blast_res: $!\n";
-unlink $blast or die "Cannot delete file: $blast: $!\n";
-
-unless($before eq ""){
-   print "[$before] ";
-   $before = ">$before";
-   
-   open FASTA, "<", $fasta or die "Cannot read file: $fasta: $!\n";
-   open TMP, ">", "$fasta-tmp" or die "Cannot create file: $fasta-tmp: $!\n";
-   my $print = 0;
-   my $at = 0;
-   my $i = 0;
-   while(my $ln=<FASTA>){
-      $i++;
-      $print = 1 if $at and $ln =~ /^>/;
-      print TMP $ln if $print;
-      $ln =~ s/\s+.*//;
-      chomp $ln;
-      $at = $i if $ln eq $before;
-   }
-   close TMP;
-   close FASTA;
-   printf 'recovered at %.2f%% (%d/%d).'."\n", 100*$at/$i, $at, $i if $i;
-
-   move $fasta, "$fasta.old" or die "Cannot move file $fasta into $fasta.old: $!\n";
-   move "$fasta-tmp", $fasta or die "Cannot move file $fasta-tmp into $fasta: $!\n";
-}
-

data/utils/enveomics/Pipelines/blast.pbs/CONFIG.mock.bash

@@ -1,98 +0,0 @@
-#!/bin/bash
-
-##################### VARIABLES
-# Queue and resources.
-QUEUE="iw-shared-6" ;
-MAX_JOBS=500 ; # Maximum number of concurrent jobs. Never exceed 1990.
-PPN=2 ;
-RAM="9gb" ;
-
-# Paths
-SCRATCH_DIR="$HOME/scratch/pipelines/blast" ; # Where the outputs and temporals will be created
-INPUT="$HOME/data/my-large-file.fasta" ; # Input query file
-DB="$HOME/data/db/nr" ; # Input database
-PROGRAM="blastp" ;
-
-# Pipeline
-MAX_TRIALS=5 ; # Maximum number of automated attempts to re-start a job
-
-##################### FUNCTIONS
-## All the functions below can be edited to suit your particular job.
-## No function can be empty, but you can use a "dummy" function (like true).
-## All functions have access to any of the variables defined above.
-## 
-## The functions are executed in the following order (from left to right):
-##
-##           / -----> BEFORE_BLAST --> RUN_BLAST --> AFTER_BLAST ---\
-##          /              ···            ···            ···         \
-## BEGIN --#--------> BEFORE_BLAST --> RUN_BLAST --> AFTER_BLAST -----#---> END
-##          \              ···            ···            ···         /
-##           \ -----> BEFORE_BLAST --> RUN_BLAST --> AFTER_BLAST ---/
-##
-
-# Function to execute ONLY ONCE at the begining
-function BEGIN {
-   ### Format the database (assuming proteins, check commands):
-   # module load ncbi_blast/2.2.25 || exit 1 ;
-   # makeblastdb -in $HOME/data/some-database.faa -title $DB -dbtype prot || exit 1 ;
-   # module unload ncbi_blast/2.2.25 || exit 1 ;
-   ### Don't do anything:
-   true ;
-}
-
-# Function to execute BEFORE running the BLAST, for each sub-task.
-function BEFORE_BLAST {
-   local IN=$1 # Query file
-   local OUT=$2 # Blast file (to be created)
-   ### Don't do anything:
-   true ;
-}
-
-# Function that executes BLAST, for each sub-task
-function RUN_BLAST {
-   local IN=$1 # Query file
-   local OUT=$2 # Blast file (to be created)
-   ### Run BLAST+ with 13th and 14th columns (query length and subject length):
-   module load ncbi_blast/2.2.28_binary || exit 1 ;
-   $PROGRAM -query $IN -db $DB -out $OUT -num_threads $PPN \
-   	-outfmt "6 qseqid sseqid pident length mismatch gapopen qstart qend sstart send evalue bitscore qlen slen" \
-	|| exit 1 ;
-   module unload ncbi_blast/2.2.28_binary || exit 1 ;
-   ### Run BLAT (nucleotides)
-   # module load blat/rhel6 || exit 1 ;
-   # blat $DB $IN -out=blast8 $OUT || exit 1 ;
-   # module unload blat/rhel6 || exit 1 ;
-   ### Run BLAT (proteins)
-   # module load blat/rhel6 || exit 1 ;
-   # blat $DB $IN -out=blast8 -prot $OUT || exit 1 ;
-   # module unload blat/rhel6 || exit 1 ;
-}
-
-# Function to execute AFTER running the BLAST, for each sub-task
-function AFTER_BLAST {
-   local IN=$1 # Query files
-   local OUT=$2 # Blast files
-   ### Filter by best-match:
-   # sort $OUT | perl $PDIR/../../Scripts/BlastTab.best_hit_sorted.pl > $OUT.bm
-   ### Filter by Bit-score 60:
-   # awk '$12>=60' $OUT > $OUT.bs60
-   ### Filter by corrected identity 95 (only if it has the additional 13th column):
-   # awk '$3*$4/$13 >= 95' $OUT > $OUT.ci95
-   ### Don't do anything:
-   true ;
-}
-
-# Function to execute ONLY ONCE at the end, to concatenate the results
-function END {
-   local PREFIX=$1 # Prefix of all Blast files
-   local OUT=$2 # Single Blast output (to be created).
-   ### Simply concatenate files:
-   # cat $PREFIX.*.blast > $OUT
-   ### Concatenate only the filtered files (if filtering in AFTER_BLAST):
-   # cat $PREFIX.*.blast.bs60 > $OUT
-   ### Sort the BLAST by query (might require considerable RAM):
-   # sort -k 1 $PREFIX.*.blast > $OUT
-   ### Don't do anyhthing:
-   true ;
-}
-

data/utils/enveomics/Pipelines/blast.pbs/FastA.split.pl

@@ -1 +0,0 @@
-../../Scripts/FastA.split.pl