I have a file which has lines like this:
1 107275 447049 scaffold1443 465 341154 -
There are several lines which starts with one, after that a blank line separates and start lines with 2 and so on.
I want to separate these lines to different files based on their number.
I wrote this script but it prints in every file only the first line.
#!/usr/bin/perl
#script for choosing chromosome
use strict;
my $filename= $ARGV[0];
open(FILE, $filename);
while (my $line = <FILE>) {
my #data = split('\t', $line);
my $length = #data;
#print $length;
my $num = $data[0];
if ($length == 6) {
open(my $fh, '>', $num);
print $fh $line;
}
$num = $num + 1;
}
please, i need your help!
use >> to open file for appending to end of it as > always truncates desired file to zero bytes,
use strict;
my $filename = $ARGV[0];
open(my $FILE, "<", $filename) or die $!;
while (my $line = <$FILE>) {
my #data = split('\t', $line);
my $length = #data;
#print $length;
my $num = $data[0];
if ($length == 6) {
open(my $fh, '>>', $num);
print $fh $line;
}
$num = $num + 1;
}
If I understand your question correctly, then paragraph mode might be useful. This breaks a record on two or more new-lines, instead of just one:
#ARGV or die "Supply a filename\n";
my $filename= $ARGV[0];
local $/ = ""; # Set paragraph mode
open(my $file, $filename) or die "Unable to open '$filename' for read: $!";
while (my $lines = <$file>) {
my $num = (split("\t", $lines))[0];
open(my $fh, '>', $num) or die "Unable to open '$num' for write: $!";
print $fh $lines;
close $fh;
}
close $file;
Related
I am opening a directory and processing each file. A sample file looks like this when opened:
>AAAAA
TTTTTTTTTTTAAAAATTTTTTTTTT
>BBBBB
TTTTTTTTTTTTTTTTTTBBBBBTTT
>CCCCC
TTTTTTTTTTTTTTTTCCCCCTTTTT
For the above sample file, I am trying to make them look like this:
>TAAAAAT
AAAAA
>TBBBBBT
BBBBB
>TCCCCCT
CCCCC
I need to find the "header" in next line sequence, take flanks on either side of the match, and then flip them. I want to print each file's worth of contents to another separate file.
Here is my code so far. It runs without errors, but doesn't generate any output. My guess is this is probably related to the nested if statements. I have never worked with those before.
#!/usr/bin/perl
use strict;
use warnings;
my ($directory) = #ARGV;
my $dir = "$directory";
my #ArrayofFiles = glob "$dir/*";
my $count = 0;
open(OUT, ">", "/path/to/output_$count.txt") or die $!;
foreach my $file(#ArrayofFiles){
open(my $fastas, $file) or die $!;
while (my $line = <$fastas>){
$count++;
if ($line =~ m/(^>)([a-z]{5})/i){
my $header = $2;
if ($line !~ /^>/){
my $sequence .= $line;
if ($sequence =~ m/(([a-z]{1})($header)([a-z]{1}))/i){
my $matchplusflanks = $1;
print OUT ">", $matchplusflanks, "\n", $header, "\n";
}
}
}
}
}
How can I fix this code? Thanks.
Try this
foreach my $file(#ArrayofFiles)
{
open my $fh," <", $file or die"error opening $!\n";
while(my $head=<$fh>)
{
chomp $head;
$head=~s/>//;
my $next_line = <$fh>;
my($extract) = $next_line =~m/(.$head.)/;
print ">$extract\n$head\n";
}
}
There are several mistakes in your code but the main problem is:
if ($line =~ m/(^>)([a-z]{5})/i) {
my $header = $2;
if ($line !~ /^>/) {
# here you write to the output file
Because the same line can't start and not start with > at the same time, your output files are never written. The second if statement always fails and its block is never executed.
open(OUT, ">", "/path/to/output_$count.txt") or die $!; and $count++ are misplaced. Since you want to produce an output file (with a new name) for each input file, you need to put them in the foreach block, not outside or in the while loop.
Example:
#!/usr/bin/perl
use strict;
use warnings;
my ($dir) = #ARGV;
my #files = glob "$dir/*";
my $count;
my $format = ">%s\n%s\n";
foreach my $file (#files) {
open my $fhi, '<', $file
or die "Can't open file '$file': $!";
$count++;
my $output_path = "/path/to/output_$count.txt";
open my $fho, '>', $output_path
or die "Can't open file '$output_path': $!";
my ($header, $seq);
while(<$fhi>) {
chomp;
if (/^>([a-z]{5})/i) {
if ($seq) { printf $fho $format, $seq =~ /([a-z]$header[a-z])/i, $header; }
($header, $seq) = ($1, '');
} else { $seq .= $_; }
}
if ($seq) { printf $fho $format, $seq =~ /([a-z]$header[a-z])/i, $header; }
}
close $fhi;
close $fho;
sorry if it seems obvious but Im pretty new at Perl and programming and I've been working over a week and can't get it done.
My idea is simple. I've got a .csv where I've got the names in the first column, a number from -1 to 1 in the second and a position on the third. Then another file where I have got the names (line starts with >) and the info with 80 characters per line.
What I want to do is keep the name lines of the first file and grab the 'position' given from -20 to +60. But I cannot get it to work and I've got to the point where don't know where to follow.
use strict; #read file line by line
use warnings;
my $outputfile = "Output1.txt";
my $filename = "InputP.txt";
my $inputfasta = "Inputfasta.txt";
open my $fh, '<', $filename or die "Couldn't open '$filename'";
open my $fh2, '>', $outputfile or die "Couldn't create '$outputfile'";
open my $fh3, '<', $inputfasta or die "Couldn't open '$inputfasta'";
my $Psequence = 0;
my $seqname = 0;
while (my $line = <$fh>) {
chomp $line;
my $length = index ($line, ",");
$seqname = substr ($line, 0, $length);
my $length2 = index ($line, ",", $length);
my $score = substr ($line, $length +1, $length2);
my $length3 = index ($line, ",", $length2);
my $position = substr ($line, $length2 +1, $length3);
#print $fh2 "$seqname"."\t"."$score"."\t"."$position"."\n"; }
my $Rlength2 = index ($score, ",");
my $Rscore = substr ($score, 0, $Rlength2);
#print "$Rscore"."\n";}
while (my $linea = <$fh3>){ #same order.
chomp $linea;
if ($linea=~/^>(.+)/) {
print $fh3 "\n"."$linea"."\n"; }
else { $linea =~ /^\s*(.*)\s*$/;
chomp $linea;
print $fh3 "$linea". "\n"; }
}
if ($Rscore >= 0.5){
$Psequence = substr ($linea, -20, 81);
print "$seqname"."\n"."$Psequence";}
}
Please, learn to indent the code correctly. Then the error will be more obvious:
while (my $linea = <$fh3>){ #same order.
chomp $linea;
if ($linea =~ /^>(.+)/) {
print $fh3 "\n$linea\n";
} else {
# Commented out as it does nothing.
# $linea =~ /^\s*(.*)\s*$/;
# chomp $linea;
print $fh3 "$linea\n";
}
}
if ($Rscore >= 0.5){
$Psequence = substr $linea, -20, 81;
print "$seqname\n$Psequence";
}
$linea exists only in the while loop, but you try to use it in the following paragraph, too. The variable disappears when the loop ends.
Create a hash from the CSV where the key is the name and the value is the position.
use Text::CSV_XS qw( );
my %pos_by_name;
{
open(my $fh, '<', $input_qfn)
or die("Can't open $input_qfn: $!\n");
my $csv = Text::CSV_XS->new({ auto_diag => 1, binary => 1 });
while (my $row = $csv_in->getline($fh)) {
$pos_by_name{ $row->[0] } = $row->[2];
}
}
Then, it's just a question of extracting the names from the other file, and using the hash to find the associated position.
open(my $fh, '<', $fasta_qfn)
or die("Can't open $fasta_qfn: $!\n");
while (<$fh>) {
chomp;
my ($name) = /^>(.*)/
or next;
my $pos = $pos_by_name{$name};
if (!defined($pos)) {
die("Can't find position for $name\n");
}
... Do something with $name and $pos ...
}
This is what I have so far, but the code is only showing contents of column 1. I'm not sure how to compute columns. I am really new to programming, so this may be an easy question.
my $filename = "Q5.txt";
open(my $fh, "<", $filename) or die "Could not open '$filename'\n";
while (my $line = <$fh>) {
$count++;
#line = $line;
for (#line) {
...
}
}
print $line[0];
Something like this should suit you
use strict;
use warnings;
use autodie;
my $filename = 'Q5.txt';
my ($n, #totals);
open my $fh, '<', $filename;
while (<$fh>) {
my #fields = split;
$totals[$_] += $fields[$_] for 0 .. $#fields;
++$n;
}
$_ /= $n for #totals;
print "#totals\n";
I'm trying to count the number of 'N's in a FASTA file which is:
>Header
AGGTTGGNNNTNNGNNTNGN
>Header2
AGNNNNNNNGNNGNNGNNGN
so in the end I want to get the count of number of 'N's and each header is a read so I want to make a histogram so I would at the end output something like this:
# of N's # of Reads
0 300
1 240
etc...
so there are 300 sequences or reads that have 0 number of 'N's
use strict;
use warnings;
my $file = shift;
my $output_file = shift;
my $line;
my $sequence;
my $length;
my $char_N_count = 0;
my #array;
my $count = 0;
if (!defined ($output_file)) {
die "USAGE: Input FASTA file\n";
}
open (IFH, "$file") or die "Cannot open input file$!\n";
open (OFH, ">$output_file") or die "Cannot open output file $!\n";
while($line = <IFH>) {
chomp $line;
next if $line =~ /^>/;
$sequence = $line;
#array = split ('', $sequence);
foreach my $element (#array) {
if ($element eq 'N') {
$char_N_count++;
}
}
print "$char_N_count\n";
}
Try this. I changed a few things like using scalar file handles. There are many ways to do this in Perl, so some people will have other ideas. In this case I used an array which may have gaps in it - another option is to store results in a hash and key by the count.
Edit: Just realised I'm not using $output_file, because I have no idea what you want to do with it :) Just change the 'print' at the end to 'print $out_fh' if your intent is to write to it.
use strict;
use warnings;
my $file = shift;
my $output_file = shift;
if (!defined ($output_file)) {
die "USAGE: $0 <input_file> <output_file>\n";
}
open (my $in_fh, '<', $file) or die "Cannot open input file '$file': $!\n";
open (my $out_fh, '>', $output_file) or die "Cannot open output file '$output_file': $!\n";
my #results = ();
while (my $line = <$in_fh>) {
next if $line =~ /^>/;
my $num_n = ($line =~ tr/N//);
$results[$num_n]++;
}
print "# of N's\t# of Reads\n";
for (my $i = 0; $i < scalar(#results) ; $i++) {
unless (defined($results[$i])) {
$results[$i] = 0;
# another option is to 'next' if you don't want to show the zero totals
}
print "$i\t\t$results[$i]\n";
}
close($in_fh);
close($out_fh);
exit;
I have a file that looks like
NAME|JOHN|TOKYO|JPN
AGE|32|M
INFO|SINGLE|PROFESSIONAL|IT
NAME|MARK|MANILA|PH
AGE|37|M
INFO|MARRIED|PROFESSIONAL|BPO
NAME|SAMANTHA|SYDNEY|AUS
AGE|37|F
INFO|MARRIED|PROFESSIONAL|OFFSHORE
NAME|LUKE|TOKYO|JPN
AGE|27|M
INFO|SINGLE|PROFESSIONAL|IT
I want to separate the records by country. I have stored each line into array variable #fields
my #fields = split(/\|/, $_ );
making $fields[3] as my basis for sorting it. I wanted it to separate into 2 output text files
OUTPUT TEXT FILE 1:
NAME|JOHN|TOKYO|JPN
AGE|32|M
INFO|SINGLE|PROFESSIONAL|IT
NAME|LUKE|TOKYO|JPN
AGE|27|M
INFO|SINGLE|PROFESSIONAL|IT
OUTPUT TEXT FILE 2
NAME|MARK|MANILA|PH
AGE|37|M
INFO|MARRIED|PROFESSIONAL|BPO
NAME|SAMANTHA|SYDNEY|AUS
AGE|37|F
INFO|MARRIED|PROFESSIONAL|OFFSHORE
Putting all that is from JPN to output text 1 & non-JPN country to output text file 2
here's the code that what trying to work out
use strict;
use warnings;
use Data::Dumper;
use Carp qw(croak);
my #fields;
my $tmp_var;
my $count;
;
my ($line, $i);
my $filename = 'data.txt';
open(my $input_fh, '<', $filename ) or croak "Can't open $filename: $!";
open(OUTPUTA, ">", 'JPN.txt') or die "wsl_reformat.pl: could not open $ARGV[0]";
open(OUTPUTB, ">", 'Non-JPN.txt') or die "wsl_reformat.pl: could not open $ARGV[0]";
my $fh;
while (<$input_fh>) {
chomp;
my #fields = split /\|/;
if ($fields[0] eq 'NAME') {
for ($i=1; $i < #fields; $i++) {
if ($fields[3] eq 'JPN') {
$fh = $_;
print OUTPUTA $fh;
}
else {
$fh = $_;
print OUTPUTB $fh;
}
}
}
}
close(OUTPUTA);
close(OUTPUTB)
Still has no luck on it :(
Here is the way I think ikegami was saying, but I've never tried this before (although it gave the correct results).
#!/usr/bin/perl
use strict;
use warnings;
open my $jpn_fh, ">", 'o33.txt' or die $!;
open my $other_fh, ">", 'o44.txt' or die $!;
my $fh;
while (<DATA>) {
if (/^NAME/) {
if (/JPN$/) {
$fh = $jpn_fh;
}
else {
$fh = $other_fh;
}
}
print $fh $_;
}
close $jpn_fh or die $!;
close $other_fh or die $!;
__DATA__
NAME|JOHN|TOKYO|JPN
AGE|32|M
INFO|SINGLE|PROFESSIONAL|IT
NAME|MARK|MANILA|PH
AGE|37|M
INFO|MARRIED|PROFESSIONAL|BPO
NAME|SAMANTHA|SYDNEY|AUS
AGE|37|F
INFO|MARRIED|PROFESSIONAL|OFFSHORE
NAME|LUKE|TOKYO|JPN
AGE|27|M
INFO|SINGLE|PROFESSIONAL|IT
You didn't say what you needed help with, so I'm assuming it's coming up with an algorithm. Here's a good one:
Open the file to read.
Open the file for the JPN entries.
Open the file for the non-JPN entries.
While not eof,
Read a line.
Parse the line.
If it's the first line of a record,
If the person's country is JPN,
Set current file handle to the file handle for JPN entries.
Else,
Set current file handle to the file handle for non-JPN entries.
Print the line to the current file handle.
my $jpn_qfn = '...';
my $other_qfn = '...';
open(my $jpn_fh, '>', $jpn_qfn)
or die("Can't create $jpn_qfn: $!\n");
open(my $other_fh, '>', $other_qfn)
or die("Can't create $other_qfn: $!\n");
my $fh;
while (<>) {
chomp;
my #fields = split /\|/;
if ($fields[0] eq 'NAME') {
$fh = $fields[3] eq 'JPN' ? $jpn_fh : $other_fh;
}
say $fh $_;
}
#!/usr/bin/env perl
use 5.012;
use autodie;
use strict;
use warnings;
# store per country output filehandles
my %output;
# since this is just an example, read from __DATA__ section
while (my $line = <DATA>) {
# split the fields
my #cells = split /[|]/, $line;
# if first field is NAME, this is a new record
if ($cells[0] eq 'NAME') {
# get the country code, strip trailing whitespace
(my $country = $cells[3]) =~ s/\s+\z//;
# if we haven't created and output file for this
# country, yet, do so
unless (defined $output{$country}) {
open my $fh, '>', "$country.out";
$output{$country} = $fh;
}
my $out = $output{$country};
# output this and the next two lines to
# country specific output file
print $out $line, scalar <DATA>, scalar <DATA>;
}
}
close $_ for values %output;
__DATA__
NAME|JOHN|TOKYO|JPN
AGE|32|M
INFO|SINGLE|PROFESSIONAL|IT
NAME|MARK|MANILA|PH
AGE|37|M
INFO|MARRIED|PROFESSIONAL|BPO
NAME|SAMANTHA|SYDNEY|AUS
AGE|37|F
INFO|MARRIED|PROFESSIONAL|OFFSHORE
NAME|LUKE|TOKYO|JPN
AGE|27|M
INFO|SINGLE|PROFESSIONAL|IT
Thanks for your Help heaps
I was able to solved this problem in perl,
many thanks
#!/usr/local/bin/perl
use strict;
use warnings;
use Data::Dumper;
use Carp qw(croak);
my #fields;
my $tmp_var;
my ($rec_type, $country);
my $filename = 'data.txt';
open (my $input_fh, '<', $filename ) or croak "Can't open $filename: $!";
open my $OUTPUTA, ">", 'o33.txt' or die $!;
open my $OUTPUTB, ">", 'o44.txt' or die $!;
my $Combline;
while (<$input_fh>) {
$_ = _trim($_);
#fields = split (/\|/, $_);
$rec_type = $fields[0];
$country = $fields[3];
if ($rec_type eq 'NAME') {
if ($country eq 'JPN') {
*Combline = $OUTPUTA;
}
else {
*Combline = $OUTPUTB;
}
}
print Combline;
}
close $OUTPUTA or die $!;
close $OUTPUTB or die $!;
sub _trim {
my $word = shift;
if ( $word ) {
$word =~ s/\s*\|/\|/g; #remove trailing spaces
$word =~ s/"//g; #remove double quotes
}
return $word;
}