I've noticed that when you drag & drop a file into OS X Terminal and any part of the pathway contains a space (for example in a folder name) it substitutes this for a \
This then leads to an error in opening files in my script:
use strict;
use warnings;
use File::Basename;
my $in;
my $filename = $ARGV[0];
unless ($filename){
print "\n\nPlease drag and drop a FASTA/FA or plain-text file containing your sequence into the prompt window and hit ENTER. Alternatively, manually specify the file-pathway:\n";
$filename = <STDIN>;
chomp $filename;
}
open($in, $filename) or die "Failed to open $in: $!";
my $DNA = read_fasta($in);
my $len = length($DNA);
print "\nFASTA/Sequence Length is: $len bp \n";
print "\nPlease enter restriction sites (degeneracy characters permitted) seperated by a single space: ";
my $sites=<STDIN>;
chomp $sites;
my #pats = split ' ', $sites;
for (#pats) {
s/K/[GT]/g;
s/M/[AC]/g;
s/Y/[CT]/g;
s/S/[CG]/g;
s/W/[AT]/g;
s/B/[CGT]/g;
s/V/[ACG]/g;
s/H/[ACT]/g;
s/D/[AGT]/g;
s/X/[AGCT]/g;
s/R/[AG]/g;
s/N/[AGCT]/g;
}
for (#pats) {
my $m = () = $DNA =~ /$_/gi;
print "\nTotal DNA matches to $_ are: $m \n";
}
my $DIR = dirname($filename);
my $name = basename($filename);
(my $extrem = $name) =~ s/\.[^.]+$//;
open my $out, ">$DIR/$extrem $sites.txt";
my $pat=join("|",#pats);
my #cutarr = split(/$pat/, $DNA);
for (#cutarr) {
my $len = length($_);
print $out "$len \n";
}
print "\nYour results are located at: $DIR/$extrem $sites.txt\n\n";
close($out);
close($in);
#Subfunction - Reading formatted FASTA/FA files
sub read_fasta {
my ($fh) = #_;
my $sequence;
while (<$fh>) {
unless (/^>/) {
chomp;
$sequence .= $_;
}
}
return $sequence;
}
It will open files if the pathway contains no spaces. Is there a better way I can go about opening the file to avoid this occurring?
Try to remove backslashes from your file name,
$filename =~ tr|\\||d;
open(my $in, $filename) or die $!;
Related
I am opening a directory and processing each file. A sample file looks like this when opened:
>AAAAA
TTTTTTTTTTTAAAAATTTTTTTTTT
>BBBBB
TTTTTTTTTTTTTTTTTTBBBBBTTT
>CCCCC
TTTTTTTTTTTTTTTTCCCCCTTTTT
For the above sample file, I am trying to make them look like this:
>TAAAAAT
AAAAA
>TBBBBBT
BBBBB
>TCCCCCT
CCCCC
I need to find the "header" in next line sequence, take flanks on either side of the match, and then flip them. I want to print each file's worth of contents to another separate file.
Here is my code so far. It runs without errors, but doesn't generate any output. My guess is this is probably related to the nested if statements. I have never worked with those before.
#!/usr/bin/perl
use strict;
use warnings;
my ($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;
Apologies if this is a bit long winded, bu i really appreciate an answer here as i am having difficulty getting this to work.
Building on from this question here, i have this script that works on a csv file(orig.csv) and provides a csv file that i want(format.csv). What I want is to make this more generic and accept any number of '.csv' files and provide a 'output_csv' for each inputed file. Can anyone help?
#!/usr/bin/perl
use strict;
use warnings;
open my $orig_fh, '<', 'orig.csv' or die $!;
open my $format_fh, '>', 'format.csv' or die $!;
print $format_fh scalar <$orig_fh>; # Copy header line
my %data;
my #labels;
while (<$orig_fh>) {
chomp;
my #fields = split /,/, $_, -1;
my ($label, $max_val) = #fields[1,12];
if ( exists $data{$label} ) {
my $prev_max_val = $data{$label}[12] || 0;
$data{$label} = \#fields if $max_val and $max_val > $prev_max_val;
}
else {
$data{$label} = \#fields;
push #labels, $label;
}
}
for my $label (#labels) {
print $format_fh join(',', #{ $data{$label} }), "\n";
}
i was hoping to use this script from here but am having great difficulty putting the 2 together:
#!/usr/bin/perl
use strict;
use warnings;
#If you want to open a new output file for every input file
#Do it in your loop, not here.
#my $outfile = "KAC.pdb";
#open( my $fh, '>>', $outfile );
opendir( DIR, "/data/tmp" ) or die "$!";
my #files = readdir(DIR);
closedir DIR;
foreach my $file (#files) {
open( FH, "/data/tmp/$file" ) or die "$!";
my $outfile = "output_$file"; #Add a prefix (anything, doesn't have to say 'output')
open(my $fh, '>', $outfile);
while (<FH>) {
my ($line) = $_;
chomp($line);
if ( $line =~ m/KAC 50/ ) {
print $fh $_;
}
}
close($fh);
}
the script reads all the files in the directory and finds the line with this string 'KAC 50' and then appends that line to an output_$file for that inputfile. so there will be 1 output_$file for every inputfile that is read
issues with this script that I have noted and was looking to fix:
- it reads the '.' and '..' files in the directory and produces a
'output_.' and 'output_..' file
- it will also do the same with this script file.
I was also trying to make it dynamic by getting this script to work in any directory it is run in by adding this code:
use Cwd qw();
my $path = Cwd::cwd();
print "$path\n";
and
opendir( DIR, $path ) or die "$!"; # open the current directory
open( FH, "$path/$file" ) or die "$!"; #open the file
**EDIT::I have tried combining the versions but am getting errors.Advise greatly appreciated*
UserName#wabcl13 ~/Perl
$ perl formatfile_QforStackOverflow.pl
Parentheses missing around "my" list at formatfile_QforStackOverflow.pl line 13.
source dir -> /home/UserName/Perl
Can't use string ("/home/UserName/Perl/format_or"...) as a symbol ref while "strict refs" in use at formatfile_QforStackOverflow.pl line 28.
combined code::
use strict;
use warnings;
use autodie; # this is used for the multiple files part...
#START::Getting current working directory
use Cwd qw();
my $source_dir = Cwd::cwd();
#END::Getting current working directory
print "source dir -> $source_dir\n";
my $output_prefix = 'format_';
opendir my $dh, $source_dir; #Changing this to work on current directory; changing back
for my $file (readdir($dh)) {
next if $file !~ /\.csv$/;
next if $file =~ /^\Q$output_prefix\E/;
my $orig_file = "$source_dir/$file";
my $format_file = "$source_dir/$output_prefix$file";
# .... old processing code here ...
## Start:: This part works on one file edited for this script ##
#open my $orig_fh, '<', 'orig.csv' or die $!; #line 14 and 15 above already do this!!
#open my $format_fh, '>', 'format.csv' or die $!;
#print $format_fh scalar <$orig_fh>; # Copy header line #orig needs changeing
print $format_file scalar <$orig_file>; # Copy header line
my %data;
my #labels;
#while (<$orig_fh>) { #orig needs changing
while (<$orig_file>) {
chomp;
my #fields = split /,/, $_, -1;
my ($label, $max_val) = #fields[1,12];
if ( exists $data{$label} ) {
my $prev_max_val = $data{$label}[12] || 0;
$data{$label} = \#fields if $max_val and $max_val > $prev_max_val;
}
else {
$data{$label} = \#fields;
push #labels, $label;
}
}
for my $label (#labels) {
#print $format_fh join(',', #{ $data{$label} }), "\n"; #orig needs changing
print $format_file join(',', #{ $data{$label} }), "\n";
}
## END:: This part works on one file edited for this script ##
}
How do you plan on inputting the list of files to process and their preferred output destination? Maybe just have a fixed directory that you want to process all the cvs files, and prefix the result.
#!/usr/bin/perl
use strict;
use warnings;
use autodie;
my $source_dir = '/some/dir/with/cvs/files';
my $output_prefix = 'format_';
opendir my $dh, $source_dir;
for my $file (readdir($dh)) {
next if $file !~ /\.csv$/;
next if $file =~ /^\Q$output_prefix\E/;
my $orig_file = "$source_dir/$file";
my $format_file = "$source_dir/$output_prefix$file";
.... old processing code here ...
}
Alternatively, you could just have an output directory instead of prefixing the files. Either way, this should get you on your way.
I am having trouble with getting my perl script to work. The issue might be related to the reading of the Extract file line by line within the while loop, any help would be appreciated. There are two files
Bad file that contains a list of bad IDs (100s of IDs)
2
3
Extract that contains a delimited data with the ID in field 1 (millions of rows)
1|data|data|data
2|data|data|data
2|data|data|data
2|data|data|data
3|data|data|data
4|data|data|data
5|data|data|data
I am trying to remove all the rows from the large extract file where the IDs match. There can be multiple rows where the ID matches. The extract is sorted.
#use strict;
#use warnning;
$SourceFile = $ARGV[0];
$ToRemove = $ARGV[1];
$FieldNum = $ARGV[2];
$NewFile = $ARGV[3];
$LargeRecords = $ARGV[4];
open(INFILE, $SourceFile) or die "Can't open source file: $SourceFile \n";
open(REMOVE, $ToRemove) or die "Can't open toRemove file: $ToRemove \n";
open(OutGood, "> $NewFile") or die "Can't open good output file \n";
open(OutLarge, "> $LargeRecords") or die "Can't open Large Records output file \n";
#Read in the list of bad IDs into array
#array = <REMOVE>;
#Loop through each bad record
foreach (#array)
{
$badID = $_;
#read the extract line by line
while(<INFILE>)
{
#take the line and split it into
#fields = split /\|/, $_;
my $extractID = $fields[$FieldNum];
#print "Here's what we got: $badID and $extractID\n";
while($extractID == $badID)
{
#Write out bad large records
print OutLarge join '|', #fields;
#Get the next line in the extract file
#fields = split /\|/, <INFILE>;
my $extractID = $fields[$FieldNum];
$found = 1; #true
#print " We got a match!!";
#remove item after it has been found
my $input_remove = $badID;
#array = grep {!/$input_remove/} #array;
}
print OutGood join '|', #fields;
}
}
Try this:
$ perl -F'|' -nae 'BEGIN {while(<>){chomp; $bad{$_}++;last if eof;}} print unless $bad{$F[0]};' bad good
First, you are lucky: The number of bad IDs is small. That means, you can read the list of bad IDs once, stick them in a hash table without running into any difficulty with memory usage. Once you have them in a hash, you just read the big data file line by line, skipping output for bad IDs.
#!/usr/bin/env perl
use strict;
use warnings;
# hardwired for convenience
my $bad_id_file = 'bad.txt';
my $data_file = 'data.txt';
my $bad_ids = read_bad_ids($bad_id_file);
remove_data_with_bad_ids($data_file, $bad_ids);
sub remove_data_with_bad_ids {
my $file = shift;
my $bad = shift;
open my $in, '<', $file
or die "Cannot open '$file': $!";
while (my $line = <$in>) {
if (my ($id) = extract_id(\$line)) {
exists $bad->{ $id } or print $line;
}
}
close $in
or die "Cannot close '$file': $!";
return;
}
sub read_bad_ids {
my $file = shift;
open my $in, '<', $file
or die "Cannot open '$file': $!";
my %bad;
while (my $line = <$in>) {
if (my ($id) = extract_id(\$line)) {
$bad{ $id } = undef;
}
}
close $in
or die "Cannot close '$file': $!";
return \%bad;
}
sub extract_id {
my $string_ref = shift;
if (my ($id) = ($$string_ref =~ m{\A ([0-9]+) }x)) {
return $id;
}
return;
}
I'd use a hash as follows:
use warnings;
use strict;
my #bad = qw(2 3);
my %bad;
$bad{$_} = 1 foreach #bad;
my #file = qw (1|data|data|data 2|data|data|data 2|data|data|data 2|data|data|data 3|data|data|data 4|data|data|data 5|data|data|data);
my %hash;
foreach (#file){
my #split = split(/\|/);
$hash{$split[0]} = $_;
}
foreach (sort keys %hash){
print "$hash{$_}\n" unless exists $bad{$_};
}
Which gives:
1|data|data|data
4|data|data|data
5|data|data|data
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'm trying to print a character from a file each time I get a char as input.
My problem is that it prints the whole line. I know it's a logic problem, I just can't figure out how to fix it.
use Term::ReadKey;
$inputFile = "input.txt";
open IN, $inputFile or die "I can't open the file :$ \n";
ReadMode("cbreak");
while (<IN>) {
$line = <IN>;
$char = ReadKey();
foreach $i (split //, $line) {
print "$i" if ($char == 0);
}
}
Move the ReadKey call into the foreach loop.
use strictures;
use autodie qw(:all);
use Term::ReadKey qw(ReadKey ReadMode);
my $inputFile = 'input.txt';
open my $in, '<', $inputFile;
ReadMode('cbreak');
while (my $line = <$in>) {
foreach my $i (split //, $line) {
my $char = ReadKey;
print $i;
}
}
END { ReadMode('restore') }
Your original code has 3 problems:
You only read the character once (outside the for loop)
You read 1 line from input file when testing while (<IN>) { (LOSING that line!) and then another in $line = <IN>; - therefore, only read even #d lines in your logic
print "$i" prints 1 line with no newline, therefore, you don't see characters separated
My scrip reads all the files in a directory, puts then in a list, chooses a random file from the given list.
After that, each time it gets an input char from the user, it prints a char from the file.
#!C:\perl\perl\bin\perl
use Term::ReadKey qw(ReadKey ReadMode);
use autodie qw(:all);
use IO::Handle qw();
use Fatal qw( open );
STDOUT->autoflush(1);
my $directory = "codes"; #directory's name
opendir (DIR, $directory) or die "I can't open the directory $directory :$ \n"; #open the dir
my #allFiles; #array of all the files
while (my $file = readdir(DIR)) { #read each file from the directory
next if ($file =~ m/^\./); #exclude it if it starts with '.'
push(#allFiles, $file); #add file to the array
}
closedir(DIR); #close the input directory
my $filesNr = scalar(grep {defined $_} #allFiles); #get the size of the files array
my $randomNr = int(rand($filesNr)); #generate a random number in the given range (size of array)
$file = #allFiles[$randomNr]; #get the file at given index
open IN, $file or die "I can't open the file :$ \n"; #read the given file
ReadMode('cbreak'); #don't print the user's input
while (my $line = <IN>) { #read each line from file
foreach my $i (split //, $line) { #split the line in characters (including \n & \t)
print "$i" if ReadKey(); #if keys are pressed, print the inexed char
}
}
END {
ReadMode('restore') #deactivate 'cbreak' read mode
}