make_shrimp_workflow

#!/usr/bin/perl -w

if($#ARGV!=3) {
	print "Use: $0 <query.csfasta> <genome.fasta> <output.txt> <seqs-per-split>\n";
	exit(1);
}

$queryfile = $ARGV[0];
$genomefile = $ARGV[1];
$outputfile = $ARGV[2];
$seqspersplit = $ARGV[3];

$nseqs = 0;

open FILE, "$queryfile" or die;
while(<FILE>) {
	if($_ =~ /^\>.*/) { $nseqs++; }

}
close FILE;

$nsplits = int(1 + $nseqs / $seqspersplit);

print "# Workflow generated by \"$0 @ARGV\"\n";
print "# $queryfile has $nseqs sequences\n";
print "# splitting into $nsplits files of $seqspersplit each\n";
print "\n";

$inputlist = "$queryfile.0";
$outputlist = "output.0";

for($i=1;$i<$nsplits;$i++) {
	$outputlist = "$outputlist output.$i";
	$inputlist  = "$inputlist $queryfile.$i";
}

print "OPTIONS=-M fast -M 50bp\n";
print "\n";

print "$inputlist: $queryfile\n";
print "\tLOCAL ./split_fasta $seqspersplit $queryfile\n\n";

for($i=0;$i<$nsplits;$i++) {
	print "output.$i: $queryfile.$i $genomefile rmapper-cs\n";
	print "\t./rmapper-cs \$OPTIONS $queryfile.$i $genomefile > output.$i\n\n";
}

print "$outputfile: $outputlist\n";
print "\tLOCAL cat $outputlist > $outputfile\n";