App-Egaz

 view release on metacpan or  search on metacpan

lib/App/Egaz/Command/blastlink.pm  view on Meta::CPAN

sub abstract {
    return 'link sequences by blastn';
}

sub opt_spec {
    return (
        [ "outfile|o=s",  "Output filename. [stdout] for screen", { default => "stdout" }, ],
        [ "coverage|c=f", "coverage of identical matches",        { default => 0.9 }, ],
        [ "batch=i",      "batch size of blast records",          { default => 500000 }, ],
        [ "parallel|p=i", "number of threads",                    { default => 2 }, ],
        [ "verbose|v",    "verbose mode", ],
        { show_defaults => 1, }
    );
}

sub usage_desc {
    return "egaz blastlink [options] <infile>";
}

sub description {

lib/App/Egaz/Command/blastmatch.pm  view on Meta::CPAN

sub abstract {
    return 'matched positions by blastn in genome sequences';
}

sub opt_spec {
    return (
        [ "outfile|o=s",  "Output filename. [stdout] for screen", { default => "stdout" }, ],
        [ "perchr",       "one (fake) runlist per chromosome", ],
        [ "coverage|c=f", "coverage of identical matches",        { default => 0.9 }, ],
        [ "batch=i",      "batch size of blast records",          { default => 500000 }, ],
        [ "parallel|p=i", "number of threads",                    { default => 2 }, ],
        [ "verbose|v",    "verbose mode", ],
        { show_defaults => 1, }
    );
}

sub usage_desc {
    return "egaz blastmatch [options] <infile>";
}

sub description {

lib/App/Egaz/Command/blastn.pm  view on Meta::CPAN

sub opt_spec {
    return (
        [ "outfile|o=s", "Output filename. [stdout] for screen", { default => "stdout" }, ],
        [ "evalue=f",    "expectation value (E) threshold",      { default => 0.01 }, ],
        [ "wordsize=i",  "length of best perfect match",         { default => 40 }, ],
        [   "outfmt=s", "out format",
            { default => "7 qseqid sseqid qstart qend sstart send qlen slen nident" },
        ],
        [ "tmp=s", "user defined tempdir", ],
        [ "parallel|p=i", "number of threads", { default => 2 }, ],
        [ "verbose|v",    "verbose mode", ],
        { show_defaults => 1, }
    );
}

sub usage_desc {
    return "egaz blastn [options] <infile> <genome.fa>";
}

sub description {

lib/App/Egaz/Command/blastn.pm  view on Meta::CPAN

        }
    }

    {    # blastn
        my $cmd
            = sprintf "blastn -task megablast"
            . " -max_target_seqs 20 -culling_limit 20"    # reduce size of reports
            . " -dust no -soft_masking false"             # disable dust and soft masking
            . " -evalue $opt->{evalue} -word_size $opt->{wordsize}"
            . " -outfmt '$opt->{outfmt}'"
            . " -num_threads $opt->{parallel} -db $basename -query $infiles[0]"
            . " -out $basename.blast";

        my $blastn_usage = `blastn -h`;
        if ( $blastn_usage =~ /\-max_hsps int/ ) {
            $cmd .= " -max_hsps 10";                      # Nucleotide-Nucleotide BLAST 2.6.0+
        }
        elsif ( $blastn_usage =~ /\-max_hsps_per_subject int/ ) {
            $cmd .= " -max_hsps_per_subject 10";          # Nucleotide-Nucleotide BLAST 2.2.28+
        }

lib/App/Egaz/Command/lastz.pm  view on Meta::CPAN

        [ "E=i",          "Scoring: gap-extension penalty", ],
        [ "Q=s",          "Scoring: matrix file", ],
        [ "C=i",          "Aligning: chain option", ],
        [ "T=i",          "Aligning: words option", ],
        [ "M=i",          "Aligning: mask any base in seq1 hit this many times", ],
        [ "K=i",          "Dropping hsp: threshold for MSPs for the first pass", ],
        [ "L=i",          "Dropping hsp: threshold for gapped alignments for the second pass", ],
        [ "H=i",          "Dropping hsp: threshold to be interpolated between alignments", ],
        [ "Y=i",          "Dropping hsp: X-drop parameter for gapped extension", ],
        [ "Z=i",          "Speedup: increment between successive words", ],
        [ "parallel|p=i", "number of threads", { default => 2 }, ],
        [ "verbose|v",    "verbose mode", ],
        { show_defaults => 1, }
    );
}

sub usage_desc {
    return "egaz lastz [options] <path/target> <path/query>";
}

sub description {

lib/App/Egaz/Command/lpcnam.pm  view on Meta::CPAN

}

sub opt_spec {
    return (
        [ "outdir|o=s", "Output directory", ],
        [ "lineargap=s",  "axtChain linearGap, loose or medium", { default => "loose" }, ],
        [ "minscore=i",   "minimum score for axtChain",          { default => 1000 }, ],
        [ "tname|t=s",    "target name", ],
        [ "qname|q=s",    "query name", ],
        [ "syn",          "create .synNet.maf instead of .net.maf", ],
        [ "parallel|p=i", "number of threads",                   { default => 2 }, ],
        [ "verbose|v",    "verbose mode", ],
        { show_defaults => 1, }
    );
}

sub usage_desc {
    return "egaz lpcnam [options] <path/target> <path/query> <path/lav>";
}

sub description {

lib/App/Egaz/Command/multiz.pm  view on Meta::CPAN

sub abstract {
    return 'multiz step by step';
}

sub opt_spec {
    return (
        [ "outdir|o=s", "Output directory", ],
        [ "tree=s",     "a rooted newick tree", ],
        [ "target=s",   "target name, this command can automatically pick one", ],
        [ "keeptmp",    "keep intermediate files", ],
        [ "parallel|p=i", "number of threads", { default => 2 }, ],
        { show_defaults => 1, }
    );
}

sub usage_desc {
    return "egaz multiz [options] <maf dir> [more dirs]";
}

sub description {
    my $desc;

lib/App/Egaz/Command/raxml.pm  view on Meta::CPAN

    return 'raxml wrapper to construct phylogenetic trees';
}

sub opt_spec {
    return (
        [ "outfile|o=s",   "Output filename. [stdout] for screen", { default => "stdout" }, ],
        [ "outgroup=s",    "the name of outgroup if exists", ],
        [ "seed|s=i",      "specify a random number seed", ],
        [ "bootstrap|b=i", "the number of alternative runs",       { default => 100 }, ],
        [ "tmp=s",         "user defined tempdir", ],
        [ "parallel|p=i",  "number of threads",                    { default => 2 }, ],
        [ "verbose|v",     "verbose mode", ],
        { show_defaults => 1, }
    );
}

sub usage_desc {
    return "egaz raxml [options] <infile> [more infiles]";
}

sub description {

lib/App/Egaz/Command/repeatmasker.pm  view on Meta::CPAN

    return 'RepeatMasker wrapper';
}

sub opt_spec {
    return (
        [ "outdir|o=s",   "Output directory",  { default => "." }, ],
        [ "species=s",    "the species or clade of the input sequence", ],
        [ "opt=s",        "other options be passed to RepeatMasker", ],
        [ "gff",          "create .rm.gff by rmOutToGFF3.pl", ],
        [ "tmp=s",        "user defined tempdir", ],
        [ "parallel|p=i", "number of threads", { default => 2 }, ],
        [ "verbose|v",    "verbose mode", ],
        { show_defaults => 1, }
    );
}

sub usage_desc {
    return "egaz repeatmasker [options] <infile> [more infiles]";
}

sub description {

lib/App/Egaz/Command/template.pm  view on Meta::CPAN

                    [ "self"  => "self genome alignments, paralogs" ],
                    [ "prep"  => "prepare sequences" ],
                ],
            }
        ],
        [],
        [ "outdir|o=s",   "Output directory", { default => "." }, ],
        [ "queue=s",      "QUEUE_NAME",       { default => "mpi" }, ],
        [ "separate",     "separate each Target-Query groups", ],
        [ "tmp=s",        "user defined tempdir", ],
        [ "parallel|p=i", "number of threads", { default => 2 }, ],
        [ "verbose|v",    "verbose mode", ],
        [],
        [ "length=i",  "minimal length of alignment fragments", { default => 1000 }, ],
        [ "partition", "use partitioned sequences if available", ],
        [ "msa=s",     "aligning program for refine alignments", { default => "mafft" }, ],
        [ "taxon=s",   "taxon.csv for this project", ],
        [ "aligndb",   "create aligndb scripts", ],
        [],
        [ "multiname=s", "naming multiply alignment", ],
        [ "outgroup=s",  "the name of outgroup", ],

lib/App/Egaz/Common.pm  view on Meta::CPAN

    # -b    compute forward and reverse complement matches
    # -F    force 4 column output format regardless of the number of reference sequence inputs
    # -n    match only the characters a, c, g, or t
    #
    # sparsemem only
    # -k    sampled suffix positions (one by default)
    my $template;
    my $exe;
    if ( IPC::Cmd::can_run('sparsemem') ) {
        $exe      = 'sparsemem';
        $template = "%s -maxmatch -F -l %d -b -n -k 4 -threads 4 %s %s > %s";
    }
    else {
        $exe      = 'mummer';
        $template = "%s -maxmatch -F -l %d -b -n %s %s > %s";
    }

    my $cmd = sprintf $template, $exe, $length, $genome, $query, $result->stringify;
    system $cmd;
}