view release on metacpan or  search on metacpan

bin/RNAmotifAnalysis  view on Meta::CPAN

            stock2fasta     => 'selex_stock2fasta.pl',
        };
        $config->{Flags_for} = {
            RNAalifold => '-r -cv 0.6 -nc 10 -p -d2 -noLP -color -aln',
            mafft      => '--preservecase --clustalout',
        };
        $config->write($config_filename);
        warn "\nNo configuration file found. Creating new configuration file '$config_filename'\n";
        warn external_dependecnies();
        warn <<"MSG";

        If you have problems, you may need to ensure that each executable
        listed in '$config_filename' is located in a directory that is found
        in your PATH environment variable.\n";
MSG
    }
    $config = Config::Tiny->read($config_filename);
    return $config;
}

sub create_batch_files {
    my $config      = shift;
    my $num_cpus    = shift;
    my $run_scripts = shift;

    # Get all the file names to be processed
    my @fasta_filenames = glob '*_top.fasta';

    # Reduce number of cpus if there are fewer files
    $num_cpus = min(scalar @fasta_filenames, $num_cpus);

    # Create a batch of commands for each CPU to work on
    my @workload = map { $EMPTY_STRING } 1 .. $num_cpus;
    my $add_work = __add_work(
        {
            workload_aref => \@workload,
            num_cpus      => $num_cpus,
            config        => $config,
        }
    );
    $add_work->($_) for @fasta_filenames;

    # Execute the commands for each CPU
    for my $batch_num ( 1 .. $num_cpus ){

        # name script file for each batch
        my $batch_filename = "batch_$batch_num";

        # Create a directory for each batch
        system("mkdir $batch_filename.dir");

        # Move into batch directory
        chdir "$batch_filename.dir";

        # Write batch instruction to script file
        open( my $fh, '>', $batch_filename);
        print {$fh} $workload[ $batch_num - 1];
        close $fh;

        # Make script file executable
        system("chmod u+x $batch_filename");

        # Run the script, if desired
        if($run_scripts){
            system("./$batch_filename &");
        }

        # Return to directory about batch directory
        chdir '..';
    }
    return;
}

sub __add_work {
    my %opt = %{ shift() };
    my $workload_aref       = $opt{workload_aref} || croak "'workload_aref' required";
    my $num_cpus            = $opt{num_cpus}      || croak "'num_cpus' required";
    my $config              = $opt{config}        || croak "'config' required";
    my $work_index          = 0;
    my @filenames_to_rename = _filenames_to_rename();

    my $MAFFT_cmd      = "$config->{executables}{mafft} $config->{Flags_for}{mafft}";
    my $RNAalifold_cmd = "$config->{executables}{RNAalifold} $config->{Flags_for}{RNAalifold}";
    return sub {
        my $fasta_filename = shift;
        my %file           = file_name_hash($fasta_filename);

        # Don't allow accidentally creating new keys
        lock_keys %file;

        # Cycle through the sets number of work orders
        if ( $work_index >= $num_cpus ) {
            $work_index = 0;
        }

        $workload_aref->[$work_index] .= join(
            "\n",

            # Pull fasta file into current directory
            "mv ../$file{fasta} .",

            # Do alignment of sequences against each other
            "$MAFFT_cmd $file{fasta} > $file{aligned}",

            # Calculate the secondary structure
            "$RNAalifold_cmd < $file{aligned} > $file{sec_struct}",

            # Rename resulting files
            ( map { "mv $_ $file{$_}" } @filenames_to_rename ),

            # Convert secondary structure file to Stockholm format
            "$config->{executables}{CreateStockholm} $file{aligned} $file{sec_struct} > $file{stock}",

            # Determine covariance model
            "$config->{executables}{cmbuild} $file{covar_model} $file{stock}",

        ) . "\n";

        # Increment work index
        $work_index++;

bin/RNAmotifAnalysis  view on Meta::CPAN

=head1 INSTALLATION

    These installation instructions assume being able to open and use a
    terminal window on Linux.

    (0) Some systems need several dependencies installed ahead of time.

        You may be able to skip this step. However, if subsequent steps don't
        work, then be sure that some basic libraries are installed, as shown
        below (or ask a system administrator to take care of it). For the
        applicable distribution, open a terminal and then type the commands as
        indicated:

        For RedHat or CentOS 5.x systems (tested on CentOS 5.5)

                sudo yum install gcc

        For RedHat or CentOS 6.x systems (tested on "Minimal Desktop" CentOS 6.0)

                sudo yum install gcc
                sudo yum install perl-devel

        For Ubuntu systems (tested on Ubuntu 12-04 LTS)

                sudo apt-get install curl

        For Debian 5.x systems:

                sudo apt-get install gcc
                sudo apt-get install make

    (1) Install the non-Perl dependencies:
        (Versions shown are those that we've tested. Please contact us if
        newer versions do not work.)

        Infernal            1.0.2    (http://infernal.janelia.org/)
        MAFFT               6.849b   (http://mafft.cbrc.jp/alignment/software/)
        RNA Vienna package  1.8.4    (http://www.tbi.univie.ac.at/~ivo/RNA/)

        After installing these, make sure all of the foloowing executables are
        in directories within your PATH:

            cmbuild
            cmcalibrate
            cmsearch
            cmalign
            mafft
            RNAalifold

    (2) Use a CPAN client to install Bio::App::SELEX::RNAmotifAnalysis.

        Here we demonstrate the use of cpanminus to install it to a local Perl module directory. These instructions assume absolutely no experience with cpanminus.

              1. Download cpanminus

                    curl -LOk http://xrl.us/cpanm


              2. Make it executable

                    chmod u+x cpanm


              3. Make a local lib/perl5 directory (if it doesn't already exist)

                    mkdir -p ~/lib/perl5


              4. Add relevant directories to your PERL5LIB and PATH environment
                 variables by adding the following text to your ~/.bashrc
                 file:


                    # Set PERL5LIB if it doesn't already exist
                    : ${PERL5LIB:=~/lib/perl5}

                    # Prepend to PERL5LIB if directory not already found in PERL5LIB
                    if ! echo $PERL5LIB | egrep -q "(^|:)~/perl5/lib/perl5($|:)"; then
                        export PERL5LIB=~/lib/perl5:$PERL5LIB;
                    fi

                    # Prepend to PATH if directory not already found in PATH
                    if ! echo $PATH | egrep -q "(^|:)~/perl5/bin($|:)"; then
                        export PATH=~/bin:$PATH;
                    fi


              5. Update environment variables immediately

                    source ~/.bashrc


              6. Install Module::Build

                    ./cpanm Module::Build


              7. Install Text::LevenshteinXS (even if you already have it installed elsewhere)

                    ./cpanm Text::LevenshteinXS


              8. Install Bio::App::SELEX::RNAmotifAnalysis

                    ./cpanm Bio::App::SELEX::RNAmotifAnalysis


    Please contact the author if, after consulting this documentation and
    searching Google with error messages, you still encounter difficulties
    during the installation process.

=head1 INCOMPATIBILITIES

    Windows:     lacks necessary *nix utilities
    SGI:         problems with compiled dependency Text::LevenshteinXS
    Sun/Solaris: problems with compiled dependency Text::LevenshteinXS
    BSD:         problems with compiled dependency Text::LevenshteinXS

=head1 BUGS AND LIMITATIONS

     There are no known bugs in this module.