mirror of
https://github.com/galaxyproject/galaxy.git
synced 2026-09-24 16:30:27 +08:00
Migrating gff2bed and bed2gff tools from perl to python - tool behavior remains exactly the same.
This commit is contained in:
Greg Von Kuster
@@ -1,84 +0,0 @@
|
||||
#! /usr/bin/perl -w
|
||||
|
||||
# $URL: file://localhost/var/local/svn/repos/elliott/annotations/bed2gff.pl $
|
||||
# $Id: bed2gff.pl 601 2005-12-08 19:35:09Z elliott $
|
||||
|
||||
use strict;
|
||||
use Pod::Usage;
|
||||
use Getopt::Long;
|
||||
|
||||
=head1 NAME
|
||||
|
||||
bed2gff.pl - convert a BED file to a GFF file
|
||||
|
||||
=head1 SYNOPSIS
|
||||
|
||||
bed2gff.pl [--help] []
|
||||
|
||||
=head1 DESCRIPTION
|
||||
|
||||
Converts a BED file into GFF format. Makes the BED <score> column an
|
||||
attribute/value in the last semi-colon delimited field of the GFF file.
|
||||
|
||||
=head1 AUTHOR
|
||||
|
||||
Elliott H. Margulies -- elliott@nhgri.nih.gov
|
||||
initiated 3/10/2005
|
||||
|
||||
=head1 OPTIONS
|
||||
|
||||
=over 8
|
||||
|
||||
=item B<--name>
|
||||
|
||||
feature name for third gff field. This will override the name field in the bed
|
||||
file, if present.
|
||||
|
||||
=item B<--enhanced>
|
||||
|
||||
Will produce enhanced output from a very specific BED6+ input format designed by
|
||||
James Taylor for the ENCODE project.
|
||||
|
||||
=item B<--help>
|
||||
|
||||
Display full documentation.
|
||||
|
||||
=back
|
||||
|
||||
=cut
|
||||
|
||||
my $name;
|
||||
my $enhanced;
|
||||
|
||||
GetOptions('enhanced' => \$enhanced,
|
||||
'name=s' => \$name,
|
||||
'help' => sub { pod2usage( verbose => 2) });
|
||||
|
||||
unless ($ARGV[0]) {
|
||||
pod2usage(1);
|
||||
}
|
||||
my $file = $ARGV[0];
|
||||
open (IN, $file);
|
||||
|
||||
my $localtime = localtime();
|
||||
print "## gff-version 2\n" .
|
||||
'## bed2gff.pl $Rev: 601 $' . "\n\n";
|
||||
# "## Date: $localtime\n" .
|
||||
# '## Input file: ' . $file . "\n\n";
|
||||
|
||||
while (my $line = <IN>) {
|
||||
next if ($line =~ /^\#/ || $line =~ /^track/ || $line =~ /^browser/ || $line =~ /^$/);
|
||||
my @d = split /\s+/, $line;
|
||||
if ($name) {
|
||||
$d[3] = $name;
|
||||
}
|
||||
$d[1]++;
|
||||
$d[4]+=0;
|
||||
print "$d[0]\tbed2gff\t$d[3]\t$d[1]\t$d[2]\t.\t+\t.";
|
||||
if ($enhanced) {
|
||||
print "\tpartition_score \"$d[5]\"; partition_name \"$d[6]\"; partition_frac_overlap \"$d[7]\";\n";
|
||||
} else {
|
||||
print "\tscore \"$d[4]\";\n";
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,46 @@
|
||||
#!/usr/bin/env python2.4
|
||||
# This code exists in 2 places: ~/datatypes/converters and ~/tools/filters
|
||||
import sys
|
||||
|
||||
def __main__():
|
||||
input_name = sys.argv[1]
|
||||
output_name = sys.argv[2]
|
||||
skipped_lines = 0
|
||||
first_skipped_line = 0
|
||||
out = open( output_name, 'w' )
|
||||
out.write( "## gff-version 2\n" )
|
||||
out.write( "## bed_to_gff_converter.py\n\n" )
|
||||
for i, line in enumerate( file( input_name ) ):
|
||||
line = line.rstrip( '\r\n' )
|
||||
if line and not line.startswith( '#' ) and not line.startswith( 'track' ) and not line.startswith( 'browser' ):
|
||||
try:
|
||||
elems = line.split( '\t' )
|
||||
start = str( int( elems[1] ) + 1 )
|
||||
try:
|
||||
feature = elems[3]
|
||||
except:
|
||||
feature = 'feature_%d' % ( i + 1 )
|
||||
try:
|
||||
score = elems[4]
|
||||
except:
|
||||
score = '0'
|
||||
# Wouldn't it be better to use the score if it exists rather then hard-coding the '.'?
|
||||
# The same goes for strand, rather than hard-coding the '+'.
|
||||
# I also wonder why each line ends in a semi-colon.
|
||||
# I'm keeping thigs as they were in the original perl code in order to not break workflow.
|
||||
out.write( '%s\tbed2gff\t%s\t%s\t%s\t.\t+\t.\tscore "%s";\n' % ( elems[0], feature, start, elems[2], score ) )
|
||||
except:
|
||||
skipped_lines += 1
|
||||
if not first_skipped_line:
|
||||
first_skipped_line = i + 1
|
||||
else:
|
||||
skipped_lines += 1
|
||||
if not first_skipped_line:
|
||||
first_skipped_line = i + 1
|
||||
out.close()
|
||||
info_msg = "%i lines converted to GFF version 2. " % ( i + 1 - skipped_lines )
|
||||
if skipped_lines > 0:
|
||||
info_msg += "Skipped %d blank/comment/invalid lines starting with line #%d." %( skipped_lines, first_skipped_line )
|
||||
print info_msg
|
||||
|
||||
if __name__ == "__main__": __main__()
|
||||
@@ -1,15 +1,13 @@
|
||||
<tool id="CONVERTER_bed_to_gff_0" name="Convert BED to GFF">
|
||||
<!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
|
||||
<command interpreter="perl">bed2gff.pl $input1 > $output1</command>
|
||||
<!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
|
||||
<!-- Used on the metadata edit page. -->
|
||||
<command interpreter="python2.4">bed_to_gff_converter.py $input1 $output1</command>
|
||||
<inputs>
|
||||
<page>
|
||||
<param format="bed" name="input1" type="data" label="Choose BED file"/>
|
||||
</page>
|
||||
</inputs>
|
||||
<param format="bed" name="input1" type="data" label="Choose BED file"/>
|
||||
</inputs>
|
||||
<outputs>
|
||||
<data format="gff" name="output1"/>
|
||||
</outputs>
|
||||
<help>
|
||||
</help>
|
||||
<!-- <code file="bed_to_gff_converter_code.py"/>-->
|
||||
</tool>
|
||||
|
||||
@@ -1,63 +0,0 @@
|
||||
#! /usr/bin/perl -w
|
||||
|
||||
# $URL: file://localhost/var/local/svn/repos/elliott/annotations/gff2bed.pl $
|
||||
# $Id: gff2bed.pl 600 2005-12-08 18:09:34Z elliott $
|
||||
# Midified by Anton Nekrutenko to print strand as well
|
||||
|
||||
use strict;
|
||||
use Pod::Usage;
|
||||
use Getopt::Long;
|
||||
|
||||
=head1 NAME
|
||||
|
||||
gff2bed.pl - convert GFF to BED files.
|
||||
|
||||
=head1 SYNOPSIS
|
||||
|
||||
gff2bed.pl [--help] [GFF file]
|
||||
|
||||
=head1 DESCRIPTION
|
||||
|
||||
Converts files in GFF format to BED files. In reality, it only looks at the
|
||||
chrom, start, stop, and feature fields of the GFF file and converts to chrom,
|
||||
start, stop, name fields of the BED file. This isn't rocket science.
|
||||
|
||||
=head1 AUTHOR
|
||||
|
||||
Elliott H. Margulies -- elliott@nhgri.nih.gov
|
||||
initiated on 03/14/2005
|
||||
|
||||
=head1 OPTIONS
|
||||
|
||||
=over 8
|
||||
|
||||
=item B<--help>
|
||||
|
||||
Display full documentation.
|
||||
|
||||
=back
|
||||
|
||||
=cut
|
||||
|
||||
GetOptions('help' => sub { pod2usage( verbose => 2) });
|
||||
|
||||
unless ($ARGV[0]) {
|
||||
pod2usage(1);
|
||||
}
|
||||
|
||||
open (IN, $ARGV[0]);
|
||||
|
||||
while (my $line = <IN>) {
|
||||
next if ($line =~ /^\#/ || $line =~ /^$/);
|
||||
my @data = split /\t/, $line;
|
||||
my $chrom = $data[0];
|
||||
my $start = $data[3];
|
||||
my $stop = $data[4];
|
||||
my $name = $data[2];
|
||||
my $strand = $data[6];
|
||||
$strand = "+" if $strand eq ".";
|
||||
$start--;
|
||||
print "$chrom\t$start\t$stop\t$name\t0\t$strand\n";
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,36 @@
|
||||
#!/usr/bin/env python2.4
|
||||
import sys
|
||||
|
||||
def __main__():
|
||||
input_name = sys.argv[1]
|
||||
output_name = sys.argv[2]
|
||||
skipped_lines = 0
|
||||
first_skipped_line = 0
|
||||
out = open( output_name, 'w' )
|
||||
for i, line in enumerate( file( input_name ) ):
|
||||
line = line.rstrip( '\r\n' )
|
||||
if line and not line.startswith( '#' ):
|
||||
try:
|
||||
elems = line.split( '\t' )
|
||||
start = str( int( elems[3] ) - 1 )
|
||||
strand = elems[6]
|
||||
if strand not in ['+', '-']:
|
||||
strand = '+'
|
||||
# GFF format: chrom source, name, chromStart, chromEnd, score, strand
|
||||
# Bed format: chrom, chromStart, chromEnd, name, score, strand
|
||||
out.write( "%s\t%s\t%s\t%s\t0\t%s\n" %( elems[0], start, elems[4], elems[2], strand ) )
|
||||
except:
|
||||
skipped_lines += 1
|
||||
if not first_skipped_line:
|
||||
first_skipped_line = i + 1
|
||||
else:
|
||||
skipped_lines += 1
|
||||
if not first_skipped_line:
|
||||
first_skipped_line = i + 1
|
||||
out.close()
|
||||
info_msg = "%i lines converted to BED. " % ( i + 1 - skipped_lines )
|
||||
if skipped_lines > 0:
|
||||
info_msg += "Skipped %d blank/comment/invalid lines starting with line #%d." %( skipped_lines, first_skipped_line )
|
||||
print info_msg
|
||||
|
||||
if __name__ == "__main__": __main__()
|
||||
@@ -1,15 +1,13 @@
|
||||
<tool id="CONVERTER_gff_to_bed_0" name="Convert GFF to BED">
|
||||
<!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
|
||||
<command interpreter="perl">gff2bed.pl $input1 > $output1</command>
|
||||
<!-- <description>__NOT_USED_CURRENTLY_FOR_CONVERTERS__</description> -->
|
||||
<!-- Used on the metadata edit page. -->
|
||||
<command interpreter="python2.4">gff_to_bed_converter.py $input1 $output1</command>
|
||||
<inputs>
|
||||
<page>
|
||||
<param format="gff" name="input1" type="data" label="Choose GFF file"/>
|
||||
</page>
|
||||
</inputs>
|
||||
<param format="gff" name="input1" type="data" label="Choose GFF file"/>
|
||||
</inputs>
|
||||
<outputs>
|
||||
<data format="bed" name="output1"/>
|
||||
</outputs>
|
||||
<help>
|
||||
</help>
|
||||
<!-- <code file="gff_to_bed_converter_code.py"/>-->
|
||||
</tool>
|
||||
|
||||
@@ -1,84 +0,0 @@
|
||||
#! /usr/bin/perl -w
|
||||
|
||||
# $URL: file://localhost/var/local/svn/repos/elliott/annotations/bed2gff.pl $
|
||||
# $Id: bed2gff.pl 601 2005-12-08 19:35:09Z elliott $
|
||||
|
||||
use strict;
|
||||
use Pod::Usage;
|
||||
use Getopt::Long;
|
||||
|
||||
=head1 NAME
|
||||
|
||||
bed2gff.pl - convert a BED file to a GFF file
|
||||
|
||||
=head1 SYNOPSIS
|
||||
|
||||
bed2gff.pl [--help] []
|
||||
|
||||
=head1 DESCRIPTION
|
||||
|
||||
Converts a BED file into GFF format. Makes the BED <score> column an
|
||||
attribute/value in the last semi-colon delimited field of the GFF file.
|
||||
|
||||
=head1 AUTHOR
|
||||
|
||||
Elliott H. Margulies -- elliott@nhgri.nih.gov
|
||||
initiated 3/10/2005
|
||||
|
||||
=head1 OPTIONS
|
||||
|
||||
=over 8
|
||||
|
||||
=item B<--name>
|
||||
|
||||
feature name for third gff field. This will override the name field in the bed
|
||||
file, if present.
|
||||
|
||||
=item B<--enhanced>
|
||||
|
||||
Will produce enhanced output from a very specific BED6+ input format designed by
|
||||
James Taylor for the ENCODE project.
|
||||
|
||||
=item B<--help>
|
||||
|
||||
Display full documentation.
|
||||
|
||||
=back
|
||||
|
||||
=cut
|
||||
|
||||
my $name;
|
||||
my $enhanced;
|
||||
|
||||
GetOptions('enhanced' => \$enhanced,
|
||||
'name=s' => \$name,
|
||||
'help' => sub { pod2usage( verbose => 2) });
|
||||
|
||||
unless ($ARGV[0]) {
|
||||
pod2usage(1);
|
||||
}
|
||||
my $file = $ARGV[0];
|
||||
open (IN, $file);
|
||||
|
||||
my $localtime = localtime();
|
||||
print "## gff-version 2\n" .
|
||||
'## bed2gff.pl $Rev: 601 $' . "\n\n";
|
||||
# "## Date: $localtime\n" .
|
||||
# '## Input file: ' . $file . "\n\n";
|
||||
|
||||
while (my $line = <IN>) {
|
||||
next if ($line =~ /^\#/ || $line =~ /^track/ || $line =~ /^browser/ || $line =~ /^$/);
|
||||
my @d = split /\s+/, $line;
|
||||
if ($name) {
|
||||
$d[3] = $name;
|
||||
}
|
||||
$d[1]++;
|
||||
$d[4]+=0;
|
||||
print "$d[0]\tbed2gff\t$d[3]\t$d[1]\t$d[2]\t.\t+\t.";
|
||||
if ($enhanced) {
|
||||
print "\tpartition_score \"$d[5]\"; partition_name \"$d[6]\"; partition_frac_overlap \"$d[7]\";\n";
|
||||
} else {
|
||||
print "\tscore \"$d[4]\";\n";
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
<tool id="bed2gff1" name="BED-to-GFF">
|
||||
<description>converter</description>
|
||||
<command interpreter="perl">bed2gff.pl $input > $out_file1</command>
|
||||
<command interpreter="python2.4">bed_to_gff_converter.py $input $out_file1</command>
|
||||
<inputs>
|
||||
<param format="bed" name="input" type="data" label="Convert this query"/>
|
||||
</inputs>
|
||||
@@ -10,7 +10,7 @@
|
||||
<tests>
|
||||
<test>
|
||||
<param name="input" value="1.bed"/>
|
||||
<output name="out_file1" file="cf-bed2gff.dat"/>
|
||||
<output name="out_file1" file="bed2gff_out.gff"/>
|
||||
</test>
|
||||
</tests>
|
||||
<help>
|
||||
|
||||
@@ -0,0 +1,46 @@
|
||||
#!/usr/bin/env python2.4
|
||||
# This code exists in 2 places: ~/datatypes/converters and ~/tools/filters
|
||||
import sys
|
||||
|
||||
def __main__():
|
||||
input_name = sys.argv[1]
|
||||
output_name = sys.argv[2]
|
||||
skipped_lines = 0
|
||||
first_skipped_line = 0
|
||||
out = open( output_name, 'w' )
|
||||
out.write( "## gff-version 2\n" )
|
||||
out.write( "## bed_to_gff_converter.py\n\n" )
|
||||
for i, line in enumerate( file( input_name ) ):
|
||||
line = line.rstrip( '\r\n' )
|
||||
if line and not line.startswith( '#' ) and not line.startswith( 'track' ) and not line.startswith( 'browser' ):
|
||||
try:
|
||||
elems = line.split( '\t' )
|
||||
start = str( int( elems[1] ) + 1 )
|
||||
try:
|
||||
feature = elems[3]
|
||||
except:
|
||||
feature = 'feature_%d' % ( i + 1 )
|
||||
try:
|
||||
score = elems[4]
|
||||
except:
|
||||
score = '0'
|
||||
# Wouldn't it be better to use the score if it exists rather then hard-coding the '.'?
|
||||
# The same goes for strand, rather than hard-coding the '+'.
|
||||
# I also wonder why each line ends in a semi-colon.
|
||||
# I'm keeping thigs as they were in the original perl code in order to not break workflow.
|
||||
out.write( '%s\tbed2gff\t%s\t%s\t%s\t.\t+\t.\tscore "%s";\n' % ( elems[0], feature, start, elems[2], score ) )
|
||||
except:
|
||||
skipped_lines += 1
|
||||
if not first_skipped_line:
|
||||
first_skipped_line = i + 1
|
||||
else:
|
||||
skipped_lines += 1
|
||||
if not first_skipped_line:
|
||||
first_skipped_line = i + 1
|
||||
out.close()
|
||||
info_msg = "%i lines converted to GFF version 2. " % ( i + 1 - skipped_lines )
|
||||
if skipped_lines > 0:
|
||||
info_msg += "Skipped %d blank/comment/invalid lines starting with line #%d." %( skipped_lines, first_skipped_line )
|
||||
print info_msg
|
||||
|
||||
if __name__ == "__main__": __main__()
|
||||
@@ -1,63 +0,0 @@
|
||||
#! /usr/bin/perl -w
|
||||
|
||||
# $URL: file://localhost/var/local/svn/repos/elliott/annotations/gff2bed.pl $
|
||||
# $Id: gff2bed.pl 600 2005-12-08 18:09:34Z elliott $
|
||||
# Midified by Anton Nekrutenko to print strand as well
|
||||
|
||||
use strict;
|
||||
use Pod::Usage;
|
||||
use Getopt::Long;
|
||||
|
||||
=head1 NAME
|
||||
|
||||
gff2bed.pl - convert GFF to BED files.
|
||||
|
||||
=head1 SYNOPSIS
|
||||
|
||||
gff2bed.pl [--help] [GFF file]
|
||||
|
||||
=head1 DESCRIPTION
|
||||
|
||||
Converts files in GFF format to BED files. In reality, it only looks at the
|
||||
chrom, start, stop, and feature fields of the GFF file and converts to chrom,
|
||||
start, stop, name fields of the BED file. This isn't rocket science.
|
||||
|
||||
=head1 AUTHOR
|
||||
|
||||
Elliott H. Margulies -- elliott@nhgri.nih.gov
|
||||
initiated on 03/14/2005
|
||||
|
||||
=head1 OPTIONS
|
||||
|
||||
=over 8
|
||||
|
||||
=item B<--help>
|
||||
|
||||
Display full documentation.
|
||||
|
||||
=back
|
||||
|
||||
=cut
|
||||
|
||||
GetOptions('help' => sub { pod2usage( verbose => 2) });
|
||||
|
||||
unless ($ARGV[0]) {
|
||||
pod2usage(1);
|
||||
}
|
||||
|
||||
open (IN, $ARGV[0]);
|
||||
|
||||
while (my $line = <IN>) {
|
||||
next if ($line =~ /^\#/ || $line =~ /^$/);
|
||||
my @data = split /\t/, $line;
|
||||
my $chrom = $data[0];
|
||||
my $start = $data[3];
|
||||
my $stop = $data[4];
|
||||
my $name = $data[2];
|
||||
my $strand = $data[6];
|
||||
$strand = "+" if $strand eq ".";
|
||||
$start--;
|
||||
print "$chrom\t$start\t$stop\t$name\t0\t$strand\n";
|
||||
}
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
<tool id="gff2bed1" name="GFF-to-BED">
|
||||
<description>converter</description>
|
||||
<command interpreter="perl">gff2bed.pl $input > $out_file1</command>
|
||||
<command interpreter="python2.4">gff_to_bed_converter.py $input $out_file1</command>
|
||||
<inputs>
|
||||
<param format="gff" name="input" type="data" label="Convert this query"/>
|
||||
</inputs>
|
||||
@@ -10,7 +10,7 @@
|
||||
<tests>
|
||||
<test>
|
||||
<param name="input" value="5.gff" ftype="gff"/>
|
||||
<output name="out_file1" file="cf-gff2bed.dat"/>
|
||||
<output name="out_file1" file="gff2bed_out.bed"/>
|
||||
</test>
|
||||
</tests>
|
||||
<help>
|
||||
|
||||
@@ -0,0 +1,36 @@
|
||||
#!/usr/bin/env python2.4
|
||||
import sys
|
||||
|
||||
def __main__():
|
||||
input_name = sys.argv[1]
|
||||
output_name = sys.argv[2]
|
||||
skipped_lines = 0
|
||||
first_skipped_line = 0
|
||||
out = open( output_name, 'w' )
|
||||
for i, line in enumerate( file( input_name ) ):
|
||||
line = line.rstrip( '\r\n' )
|
||||
if line and not line.startswith( '#' ):
|
||||
try:
|
||||
elems = line.split( '\t' )
|
||||
start = str( int( elems[3] ) - 1 )
|
||||
strand = elems[6]
|
||||
if strand not in ['+', '-']:
|
||||
strand = '+'
|
||||
# GFF format: chrom source, name, chromStart, chromEnd, score, strand
|
||||
# Bed format: chrom, chromStart, chromEnd, name, score, strand
|
||||
out.write( "%s\t%s\t%s\t%s\t0\t%s\n" %( elems[0], start, elems[4], elems[2], strand ) )
|
||||
except:
|
||||
skipped_lines += 1
|
||||
if not first_skipped_line:
|
||||
first_skipped_line = i + 1
|
||||
else:
|
||||
skipped_lines += 1
|
||||
if not first_skipped_line:
|
||||
first_skipped_line = i + 1
|
||||
out.close()
|
||||
info_msg = "%i lines converted to BED. " % ( i + 1 - skipped_lines )
|
||||
if skipped_lines > 0:
|
||||
info_msg += "Skipped %d blank/comment/invalid lines starting with line #%d." %( skipped_lines, first_skipped_line )
|
||||
print info_msg
|
||||
|
||||
if __name__ == "__main__": __main__()
|
||||
Reference in New Issue
Block a user