Changeset 199

Timestamp:

04/10/09 12:00:34 (8 months ago)

Author:

bmoore

Message:

updates to ID mapping scripts and reformatted README for printer and screen

Files:

• README (modified) (2 diffs)
• bin/maker_map_ids (modified) (3 diffs)
• bin/map_fasta_ids (modified) (2 diffs)
• bin/map_gff_ids (modified) (7 diffs)

README

@@ -1 +1 @@
-***MAKER Documentation***
-
-
+
+
-INSTALLATION INSTUCTIONS FOR MAKER
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-You must also install one of the following:
-
-
+
+
-        or
-
+
+
- 
-You might want to also install these optional external programs:
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-Notes:
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-This will create a directory called maker with 5 sub directories:
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
-
-Now you can run MAKER!!
-
-
+
+
+
+
+
+
+
+
-
-Control files:
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-for tcsh:
@@ -89 +134 @@
-export AUGUSTUS_CONFIG_PATH=where_augustus_is_installed/config
-
-
-
+
+
-MPI MAKER INSTALL
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-Example: (This will run MAKER on 3 nodes or processors)
-
-
-
-
-
-Please see the documentation of the MPI environment you use for 
-
-
-
+
+
+
+
+
+
+
+
-MAKER USAGE STATEMENT
-
-Usage:
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-Options:
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-RUNNING MAKER WITH EXAMPLE DATA
-
-
+
+
-2) Type maker -CTL to generate generic maker control files
-
+
+
+
+
-4) Then try the following command from your temporary directory:
-
-
+
+
-
-MAKER will create at least the following files/directories:
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-WARNING:
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-DATASTORE
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-CONFIG FILE EDITING
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-Here an example of a section of the maker_exe.ctl file:
-
+
-#-----Location of Executables Used by Maker/Evaluator
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-#-----Ab-initio Gene Prediction Algorithms
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
-Here an example of a section of the maker_bopts.ctl file:
-====================================
-
-#-----BLAST and Exonerate statistics thresholds
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-Here an example of a section of the maker_opts.ctl file:
-
+
-#-----Genome (Required for De-Novo Annotations)
-
+
+
-
-#-----Re-annotation Options
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-#-----EST Evidence (you must provide a value for at least one)
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-GFF3 Passthrough
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-ADDING UTRs for GBROWSE
-
-
+
+
+
+
-
-maker2zff.pl <directory>
-
-
-
-
-
-
+
+
+
+
+
+
+
+
-APOLLO
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
-HMM BUILDING (based on snap documentation)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

bin/maker_map_ids

@@ -11 +11 @@
-Synopsis:
-
-
+--prefix PYU1_ --justify 6 
-
-Description:
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-";
-
-
-
-
+
+
+
+
+
-                              );
-
-
+
+
-
-
-
-
+
+
-
-
+
+
+
+
-my %counter;
-
+
+
-while (<$IN>) {
-
-        if (/\#\#sequence-region\s+(\S+)\s+(\d+)\s+(\d+)/) {
-                my ($contig_id, $start, $end) = ($1, $2, $3);
-                $contig_length{$contig_id} = ($end - $start);
-                next;
-        }
-
-        last if /^\#\#FASTA/;
@@ -48 +70 @@
-            $phase, $attrb_text) = split /\t/, $_;
-
+        # Here we explicity limit the mapping to genes and mRNAs
-        if ($type =~ /^(gene|mRNA)$/) {
-                my ($id) = $attrb_text =~ /ID=(.*?);/;
-parent
+id
-        }
-}
-
-
-
+
+
+
+
-        for my $start (sort {$b <=> $a} keys %{$contig}) {
-                for my $id (keys %{$contig->{$start}}) {
-                        my $type  = $contig->{$start}{$id};
+                        #Here we create gene and mRNA abbreviation.
-                        my $abrv  = $type eq 'gene' ? 'G' : 'T';
-                        my $count = sprintf '%06s', ++$counter{$type};
@@ -67 +92 @@
-        }
-}
-
-__END__
-
-
-
-                    my @attrb_list = split /\s*;\s*/, $attrbs_text;
-                    my %attrbs;
-                    for my $attrb_pair (@attrb_list) {
-                            my ($tag, $value_text) = split /\s*=\s*/, $attrb_pair;
-                            my @values = split /\s*, \s*/, $value_text;
-                            push @{$attrbs{$tag}} = @values;
-                    }
-                    
-
-                            
-                    }
-            }
-
-#-----------------------------------------------------------------------------
-#-------------------------------- SUBROUTINES --------------------------------
-#-----------------------------------------------------------------------------
+sub parse_sort_order {
-
-
+
-
+        my %sort_order;
+
+        if ($sort_order_file) {
+                open(my $IN, '<', $sort_order_file) or die "Can't open $sort_order_file\n$!\n";
+                my %sort_order = (<$IN>);
+                close $IN;
+        }
+        elsif (`grep -P '\#\#sequence-region' $gff_file`) {
+                open(my $IN, '<', $gff_file) or die "Can't open $gff_file\n$!\n";
+                my $flag;
+                while (my $line = <$IN>) {
+                        if ($line =~ /\#\#sequence-region\s+(\S+)\s+(\d+)\s+(\d+)/) {
+                                $flag++;
+                                my ($contig_id, $start, $end) = ($1, $2, $3);
+                                $sort_order{$contig_id} = ($end - $start);
+                        }
+                        last if $flag;
+                }
+                close $IN;
+        }
+        else {
+                open(my $IN, '<', $gff_file) or die "Can't open $gff_file\n$!\n";
+
+                while (<$IN>) {
+                        my @fields = split /\t/, $_;
+                        next unless @fields == 9;
+                        my $seq = $fields[0];
+                        $sort_order{$seq}++;
+                }
+        }
+        return \%sort_order;
-}
-
+
+
+
+
+
+

bin/map_fasta_ids

@@ -32 +32 @@
-die $usage unless $map_file && $fasta_file;
-
+# Read the map file and build a map hash;
-open (my $MAP, '<', $map_file) or die "Can't open $map_file for reading\n$!\n";
-my %map;
@@ -37 +38 @@
-close $MAP;
-
+# Open the fasta file for input unlink it to avoid clobbering it and open the 
+# same file for output.
-open (my $IN, '<', $fasta_file) or die "Can't open $fasta_file for reading\n$!\n";
-unlink($fasta_file);
-open(my $OUT, '>', $fasta_file) or die "Can't open $fasta_file for writing\n$!\n";
-
+# Just do it!
-while (<$IN>) {
-        if  (/^>/) {

bin/map_gff_ids

@@ -16 +16 @@
-
-This script takes a id map file and changes the name of the
-
-
-
-
-
-
-
-
+
+
+
+
-
-";
@@ -35 +31 @@
-die $usage unless $map_file && $gff_file;
-
+# Read map file and create a map hash
-open (my $MAP, '<', $map_file) or die "Can't open $map_file for reading\n$!\n";
-my %map;
@@ -40 +37 @@
-close $MAP;
-
+# Open $gff_file for reading, unlink it to avoid clobbering it and then open
+# the same file for writing.  This allows in-place editing.
-open (my $IN, '<', $gff_file) or die "Can't open $gff_file for reading\n$!\n";
-unlink($gff_file);
-open(my $OUT, '>', $gff_file) or die "Can't open $gff_file for writing\n$!\n";
+
+# Set the order in which attributes will appear in the attribute text.
+# Attributes not listed here will be sorted alphabetically.
+my %order = (ID     => 1,
+             Parent => 2,
+             Name   => 3,
+             Alias  => 4,
+            );
-
-my $fasta_start;
@@ -50 +57 @@
-        my ($seq, $source, $type, $start, $end, $score,
-            $strand, $phase, $attrb_text) = split /\t/, $line;
-
-
-
-
-
+
+
+
+
+
+
-                chomp $attrb_text;
-
-
-
-
-
-
-
+
+
+
-                my $alias;
-                my @ids;
-                if ($type eq 'mRNA' || $type eq 'gene') {
-                        $alias = $attrb{ID}[0] if $type =~ /^(gene|mRNA)$/;
-                }
+
+                # Collect all IDs that should be mapped for this feature
+                # (the values of Parent and ID tags)
+                my @ids;
-                push @ids, @{$attrb{Parent}} if $attrb{Parent};
-                push @ids, @{$attrb{ID}}     if $attrb{ID};
+
+                # Keep only the IDs that are in the mapping file.
-                my @map_ids;
-                map {push @map_ids, $_ if $map{$_}}  @ids;
+
+                # If there is nothing to map, print the line and go to
+                # the next feature.
-                if (! @map_ids) {
-                        print $OUT $line;
-                        next LINE;
-                };
+
+                # Map old_name to new_name for each tag value...
-                for my $tag (keys %attrb) {
-                        for my $value (@{$attrb{$tag}}) {
-                                for my $id (@map_ids) {
-
+
+
-                                        next unless ($value eq $id || $value =~ /$id:/);
-                                        $value =~ s/$id/$map{$id}/;
@@ -85 +100 @@
-                        }
-                }
+                # Now that we're done mapping, add the alias to the attributes
+                # if we have one.
-                $attrb{Alias} = [$alias] if $alias;
-
-
-
-
-
+
+
+
-                map {$order{$_} ||= 99} keys %attrb;
+
+                # Create new attribute text.
-                my $new_attrb_text;
-                for my $tag (sort {$order{$a} <=> $order{$b} || $a cmp $b} keys %attrb) {
@@ -98 +115 @@
-                }
-                $new_attrb_text .= "\n";
+
+                # Create a new $line.
-                $line = join "\t", ($seq,
-                                 $source,
@@ -111 +130 @@
-        print $OUT $line;
-}
+#-----------------------------------------------------------------------------
+#-------------------------- Subroutines --------------------------------------
+#-----------------------------------------------------------------------------
+sub parse_attributes {
+        my $attrb_text = shift;
+
+        my %attrb;
+        my @attrb_list = split /\s*;\s*/, $attrb_text;
+        for my $attrb_pair (@attrb_list) {
+                my ($tag, $value_text) = split /\s*=\s*/, $attrb_pair;
+                my @values = split /\s*,\s*/, $value_text;
+                $attrb{$tag} = \@values;
+        }
+        return %attrb;
+}