Batch Creator Script - Revision history

Siegele at 04:16, 19 June 2013

2013-06-19T04:16:21Z

← Older revision		Revision as of 04:16, 19 June 2013
Line 47:		Line 47:
	#		#
	# QUESTIONS		# QUESTIONS
	# Contact me at amandasupak@~~tamu~~.~~edu~~		# Contact me at amandasupak@gmail.com
	#		#
	# ----------------------------------------------------------------------------------		# ----------------------------------------------------------------------------------

127.0.0.1: Edited by wikibot

2011-07-01T02:17:21Z

Edited by wikibot

← Older revision		Revision as of 02:17, 1 July 2011
Line 63:		Line 63:
	"g\|gse_number=s" => \$gse_number		"g\|gse_number=s" => \$gse_number
	);		);
	die "needs a template file\n" unless $template_file;		die "needs a template file
	die "neeeds a data file\n" unless $data_file;		" unless $template_file;
	die "needs a GSE number!\n" unless $gse_number;		die "neeeds a data file
			" unless $data_file;
			die "needs a GSE number!
			" unless $gse_number;

	# Read template into a scalar (to ignore line endings)		# Read template into a scalar (to ignore line endings)
Line 76:		Line 79:

	# Remove Excel style line endings (window's endings)		# Remove Excel style line endings (window's endings)
	$template_content =~ s!\r!\n!g;		$template_content =~ s!\r!
	@template_lines = split /\n/, $template_content;		!g;
			@template_lines = split /
			/, $template_content;

	#Print to the screen that the data is being processed		#Print to the screen that the data is being processed
	print "~~\nProcessing~~...\n";		print "
			Processing...
			";

	#Strips "GSE" from "GSE#####" when typed in the promt "-g"		#Strips "GSE" from "GSE#####" when typed in the promt "-g"
	$gse_number=~ s/GSE(\d+)/$1/;		$gse_number=~ s/GSE(\d+)/$1/;
	print "$gse_number\n";		print "$gse_number
			";

	# split the template into columns, only on the second line (the first is the headings)		# split the template into columns, only on the second line (the first is the headings)
Line 93:		Line 101:

	#Put the headers from the template into the output file		#Put the headers from the template into the output file
	print OUTPUT $template_lines[0] . "\n";		print OUTPUT $template_lines[0] . "
			";

	# Read the data file into a scalar		# Read the data file into a scalar
Line 102:		Line 111:
	close DATA;		close DATA;
	}		}
	$data_content =~ s!\r!\n!g;		$data_content =~ s!\r!
	my @data_lines = split /\n/, $data_content;		!g;
			my @data_lines = split /
			/, $data_content;

	my @data;		my @data;
Line 166:		Line 177:
	}		}
	else {		else {
	print STDERR "Please check the experiment description (Column R). It must include a description of the experiment before the <c-anno> tag.\n";		print STDERR "Please check the experiment description (Column R). It must include a description of the experiment before the <c-anno> tag.
			";
	}		}

Line 184:		Line 196:
	my $date = getColumn(16);		my $date = getColumn(16);
	if ( $date !~ /^(?:19\|20)\d\d-(?:0[1-9]\|1[012])-(?:0[1-9]\|[12][0-9]\|3[01])$/ ) { # match a date like YYYY-MM-DD		if ( $date !~ /^(?:19\|20)\d\d-(?:0[1-9]\|1[012])-(?:0[1-9]\|[12][0-9]\|3[01])$/ ) { # match a date like YYYY-MM-DD
	print STDERR "Date in the wrong format! Please use YYYY-MM-DD format.\n";		print STDERR "Date in the wrong format! Please use YYYY-MM-DD format.
			";
	$date = '';		$date = '';
	}		}
Line 203:		Line 216:
	# now we have @fields_to_print, make into scalar and print to the screen		# now we have @fields_to_print, make into scalar and print to the screen
	my $x = join("\t", @fields_to_print);		my $x = join("\t", @fields_to_print);
	print OUTPUT $x . "\n";		print OUTPUT $x . "
	print "$fields_to_print[6]\n";		";
			print "$fields_to_print[6]
			";


	#for (my $j=0, $c=scalar(@fields_to_print); $j<=$c; $j++) {		#for (my $j=0, $c=scalar(@fields_to_print); $j<=$c; $j++) {
	# printf("%d,\t%s,\t%s,\t%s\n",$j, $data[$j], $template[$j], $fields_to_print[$j] );		# printf("%d,\t%s,\t%s,\t%s
			",$j, $data[$j], $template[$j], $fields_to_print[$j] );
	#}		#}
	#die();		#die();
Line 222:		Line 238:

	if ( !$data[$column_index] && !$template[$column_index] ) {		if ( !$data[$column_index] && !$template[$column_index] ) {
	print STDERR "Column " . $column_index . " doesn't have any values in data or template!\n";		print STDERR "Column " . $column_index . " doesn't have any values in data or template!
			";
	return;		return;
	}		}
Line 232:		Line 249:

	my $r = $i -1;		my $r = $i -1;
	print "Created $r row(s)\n";		print "Created $r row(s)
			";

	__END__		__END__

Amandasupak at 21:31, 7 September 2010

2010-09-07T21:31:53Z

← Older revision		Revision as of 21:31, 7 September 2010
Line 1:		Line 1:

	<perl>		<perl>
	#!/usr/bin/perl -w		#!/usr/bin/perl -w
Line 79:		Line 78:
	$template_content =~ s!\r!\n!g;		$template_content =~ s!\r!\n!g;
	@template_lines = split /\n/, $template_content;		@template_lines = split /\n/, $template_content;

			#Print to the screen that the data is being processed
			print "\nProcessing...\n";

			#Strips "GSE" from "GSE#####" when typed in the promt "-g"
			$gse_number=~ s/GSE(\d+)/$1/;
			print "$gse_number\n";

	# split the template into columns, only on the second line (the first is the headings)		# split the template into columns, only on the second line (the first is the headings)
Line 195:		Line 201:
	$fields_to_print[20] = getColumn(20);		$fields_to_print[20] = getColumn(20);

	# now we have @fields_to_print, make into scalar and print		# now we have @fields_to_print, make into scalar and print to the screen
	my $x = join("\t", @fields_to_print);		my $x = join("\t", @fields_to_print);
	print OUTPUT $x . "\n";		print OUTPUT $x . "\n";
Line 226:		Line 232:

	my $r = $i -1;		my $r = $i -1;
	print "Created $r ~~rows~~\n";		print "Created $r row(s)\n";

	__END__		__END__
Line 237:		Line 243:
	Column H is taken from template unless specified by user (.EXP files)		Column H is taken from template unless specified by user (.EXP files)
	Column L is taken from text of Column R before "<c-anno>"		Column L is taken from text of Column R before "<c-anno>"
	Column M is taken from Column L		Column M is taken from Column L</perl>
	</perl>

Amandasupak: Created page with ' #!/usr/bin/perl -w # ---------------------------------------------------------------------------------- # # 2010-06-11 Version 1.0 # # INTRODUCTION: # This code t...'

2010-06-11T18:46:59Z

Created page with ' <perl> #!/usr/bin/perl -w # ---------------------------------------------------------------------------------- # # 2010-06-11 Version 1.0 # # INTRODUCTION: # This code t...'

New page

<perl>
#!/usr/bin/perl -w

# ----------------------------------------------------------------------------------
#
# 2010-06-11 Version 1.0
#
# INTRODUCTION:
# This code takes a template and merges it with a data file to create a batch
# files for loading microarray data into SMD [smd.stanford.edu]. The purpose
# is to automate the process of making annotations by having this script fill
# in fields that are always the same.
#
# >>Template File Construction:
# This file should include 2 rows of data with the first being the headers from
# "Result_Set_Name" to "PROBE_SET_ALGORITHM". The second row should data in any
# column that includes information that will never change for that template
# type. If you have multipule array types that you are loading you can make
# different templates.
#
# >>Data File Construction:
# This file should contain at least 2 rows (one for the headers and the other
# for the row of data that was annotated), but can be as many rows as you want.
#
# >>Note about files types:
# You can make the template and data file in excel, but they must be saved as
# a tab-delimited text file if you want them to work properly with this code.
# The resulting batch file will be named GSE####_batch.txt (where the #### will
# be replaced with the GSE number you give the command line).
#
# HOW THE CODE WORKS:
# This code will first look at your data file and see if the cells are filled.
# If they are not, it will check the template. If neither are present this code
# will throw an error telling you which column is missing data. Because the data
# file has priority over the template, you can overwrite sany template options
# without changing the template itself. However if you find yourself overwriting
# many of the template options it would be best to make an new template.
#
# >>Assumptions in this code
# This code assumes that Column C, O, and S are blank and do not read from the
# template or data files.
#
# >>Rules
# Listed at the bottom of this code is quick glance at what rules this code
# follows. As a rule of thumb fill in Columns D, K, N, P, T, and U for the template
# and Columns E, F, G, Q, and R for the data file.
#
# QUESTIONS
# Contact me at amandasupak@tamu.edu
#
# ----------------------------------------------------------------------------------

#use strict;
use Getopt::Long;
use Data::Dumper;

my ($template_content, $data_file, $gse_number, $result, @template_lines);

$result = GetOptions (
"t|template=s" => \$template_file,
"d|data=s" => \$data_file,
"g|gse_number=s" => \$gse_number
);
die "needs a template file\n" unless $template_file;
die "neeeds a data file\n" unless $data_file;
die "needs a GSE number!\n" unless $gse_number;

# Read template into a scalar (to ignore line endings)
{
local $/;
open (TEMPLATE, $template_file) or die "Couldn't open file: $!";
$template_content = <TEMPLATE>;
close TEMPLATE;
}

# Remove Excel style line endings (window's endings)
$template_content =~ s!\r!\n!g;
@template_lines = split /\n/, $template_content;

# split the template into columns, only on the second line (the first is the headings)
my @template = split /\t/, $template_lines[1];

# open a file to print to
open (OUTPUT, '>GSE' . $gse_number . '_batch.txt') or die $!;

#Put the headers from the template into the output file
print OUTPUT $template_lines[0] . "\n";

# Read the data file into a scalar
{
local $/;
open (DATA, $data_file) or die "Couldn't open file: $!";
$data_content = <DATA>;
close DATA;
}
$data_content =~ s!\r!\n!g;
my @data_lines = split /\n/, $data_content;

my @data;

my $i = 0;
foreach (@data_lines) {

if ( $i ==0 ) {
$i++;
next;
}

next if /^\s*$/;

@data = split /\t/, $_;

my @fields_to_print;

# (A) result_set_name
if ($gse_number =~ m/^GSE/i) {
$gse_number =~ s/^GSE//;
}
$fields_to_print[0] = 'GSE' . $gse_number . '_ecolihub';

# (B) result_set_description
$fields_to_print[1] = $fields_to_print[0];

# (C) add_to_exp (blank)
$fields_to_print[2] = "";

# (D) print_name
$fields_to_print[3] = getColumn(3);

# (E) experiment_category
$fields_to_print[4] = getColumn(4);

# (F) experiment_subcategory
$fields_to_print[5] = getColumn(5);

# (G) slide_name
$fields_to_print[6] = getColumn(6);

# (H) exp_file_location
$fields_to_print[7] = getColumn(7);

# (I) cel_file_location
$fields_to_print[8] = $fields_to_print[6] . '.CEL';

# (J) gene_file_location
$fields_to_print[9] = $fields_to_print[6] . '.CEL.chp.txt';

# (K) single_scan_file_location
$fields_to_print[10] = getColumn(10);

# (L) single_channel_description
my $s = getColumn(17);
if ( $s =~ /^"(.*)"$/ ) { # strip off the leading and trailing quotes added by Excel
$s = $1;
}
if ( $s =~ /^(.*)<c-anno>/ ) { # grab off the first part
$fields_to_print[11] = $1;
}
else {
print STDERR "Please check the experiment description (Column R). It must include a description of the experiment before the <c-anno> tag.\n";
}

# (M) experiment_name
$fields_to_print[12] = $fields_to_print[11];

# (N) normalization
$fields_to_print[13] = getColumn(13);

# (O) norm_value
$fields_to_print[14] = '';

# (P) experimenter
$fields_to_print[15] = getColumn(15);

# (Q) date
my $date = getColumn(16);
if ( $date !~ /^(?:19|20)\d\d-(?:0[1-9]|1[012])-(?:0[1-9]|[12][0-9]|3[01])$/ ) { # match a date like YYYY-MM-DD
print STDERR "Date in the wrong format! Please use YYYY-MM-DD format.\n";
$date = '';
}
$fields_to_print[16] = $date;

# (R) experiment_description
$fields_to_print[17] = $s; # from (L)

# (S) collaborative_group
$fields_to_print[18] = "";

# (T) individual_user
$fields_to_print[19] = getColumn(19);

# (U) probe_set_algorithm
$fields_to_print[20] = getColumn(20);

# now we have @fields_to_print, make into scalar and print
my $x = join("\t", @fields_to_print);
print OUTPUT $x . "\n";
print "$fields_to_print[6]\n";

#for (my $j=0, $c=scalar(@fields_to_print); $j<=$c; $j++) {
# printf("%d,\t%s,\t%s,\t%s\n",$j, $data[$j], $template[$j], $fields_to_print[$j] );
#}
#die();

$i++;
}
close DATA;

#Determines if the data file or the template file has priority
sub getColumn {
my $column_index = shift @_;

if ( !$data[$column_index] && !$template[$column_index] ) {
print STDERR "Column " . $column_index . " doesn't have any values in data or template!\n";
return;
}

return ($data[$column_index])
? $data[$column_index]
: $template[$column_index];
}

my $r = $i -1;
print "Created $r rows\n";

__END__

#Rules:
Column A is taken from the template and user input (GSE####)
Column B is (column A)
Column I is (column G + .CEL)
Column J is (column G + .CEL.chp.txt)
Column H is taken from template unless specified by user (.EXP files)
Column L is taken from text of Column R before "<c-anno>"
Column M is taken from Column L
</perl>