App-Dazz

 view release on metacpan or  search on metacpan

doc/dazzler.md  view on Meta::CPAN

faops some -l 0 renamed.fasta <(DBshow -n myDB 5-10 102 100-101 | sed 's/^>//') stdout

```

## daligner

`HPC.daligner`

* local alignments involving at least `-l` base pairs (default 1000)
* An average correlation rate of `-e` (default 70%) set to 80%
* The default number of threads is 4, set by `-T` option (power of 2)
* Set the `-t` parameter which suppresses the use of any *k*-mer that occurs more than *t* times in
  either the subject or target block.
* Let the program automatically select a value of *t* that meets a given memory usage limit
  specified (in Gb) by the `-M` parameter
* one or more interval tracks specified with the `-m` option (m for mask)

### Create jobs by `HPC.daligner` and execute it

Three .las (`myDB.[1-3].las`) files are generated then concatenated to `myDB.las`.

lib/App/Dazz/Command/contained.pm  view on Meta::CPAN

use constant abstract => "discard contained unitigs";

sub opt_spec {
    return (
        [ "outfile|o=s", "output filename, [stdout] for screen", ],
        [ "len|l=i",      "minimal length of overlaps",   { default => 500 }, ],
        [ "idt|i=f",      "minimal identity of overlaps", { default => 0.98 }, ],
        [ "proportion=f", "nearly contained proportion",  { default => 0.98 }, ],
        [ "prefix=s",     "prefix of names",              { default => "infile" }, ],
        [ "tmp=s",        "user defined tempdir", ],
        [ "parallel|p=i", "number of threads",            { default => 8 }, ],
        [ "verbose|v",    "verbose mode", ],
        { show_defaults => 1, }
    );
}

sub usage_desc {
    return "dazz contained [options] <infile> [more infiles]";
}

sub description {

lib/App/Dazz/Command/group.pm  view on Meta::CPAN

sub opt_spec {
    return (
        [ "dir|d=s", "output directory", ],
        [ "range|r=s",    "ranges of anchors",            { required => 1 }, ],
        [ "coverage|c=i", "minimal coverage",             { default  => 2 }, ],
        [ "max=i",        "max distance",                 { default  => 5000 }, ],
        [ "len|l=i",      "minimal length of overlaps",   { default  => 1000 }, ],
        [ "idt|i=f",      "minimal identity of overlaps", { default  => 0.85 }, ],
        [ "keep",         "don't remove multi-matched reads", ],
        [ 'oa=s',         'overlaps between anchors', ],
        [ "parallel|p=i", "number of threads",            { default  => 4 }, ],
        [ "verbose|v",    "verbose mode", ],
        [ "png",          "write a png file via graphviz", ],
        { show_defaults => 1, }
    );
}


# 三代 reads 里有一个常见的错误, 即单一 ZMW 里的测序结果中, 接头序列部分的测序结果出现了较多的错误,
# 因此并没有将接头序列去除干净, 形成的 subreads 里含有多份基因组上同一片段, 它们之间以接头序列为间隔.
#

lib/App/Dazz/Command/merge.pm  view on Meta::CPAN

use App::Dazz::Common;

use constant abstract => "merge overlapped unitigs";

sub opt_spec {
    return (
        [ "outfile|o=s", "output filename, [stdout] for screen", ],
        [ "len|l=i",      "minimal length of overlaps",   { default => 1000 }, ],
        [ "idt|i=f",      "minimal identity of overlaps", { default => 0.98 }, ],
        [ "tmp=s",        "user defined tempdir", ],
        [ "parallel|p=i", "number of threads",            { default => 8 }, ],
        [ "verbose|v",    "verbose mode", ],
        [ "png",          "write a png file via graphviz", ],
        { show_defaults => 1, }
    );
}

sub usage_desc {
    return "dazz merge [options] <infile>";
}

lib/App/Dazz/Command/orient.pm  view on Meta::CPAN

use constant abstract => "orient overlapped sequences to the same strand";

sub opt_spec {
    return (
        [ "outfile|o=s",  "output filename, [stdout] for screen", ],
        [ "restrict|r=s", "limit to known pairs", ],
        [ "len|l=i",      "minimal length of overlaps",   { default => 1000 }, ],
        [ "idt|i=f",      "minimal identity of overlaps", { default => 0.85 }, ],
        [ "tmp=s",        "user defined tempdir", ],
        [ "parallel|p=i", "number of threads",            { default => 4 }, ],
        [ "verbose|v",    "verbose mode", ],
        { show_defaults => 1, }
    );
}

sub usage_desc {
    return "dazz orient [options] <infiles>";
}

sub description {

lib/App/Dazz/Command/overlap.pm  view on Meta::CPAN

use constant abstract => "detect overlaps by daligner";

sub opt_spec {
    return (
        [ "outfile|o=s",  "output filename, [stdout] for screen", ],
        [ "len|l=i",      "minimal length of overlaps",   { default => 500 }, ],
        [ "idt|i=f",      "minimal identity of overlaps", { default => 0.7 }, ],
        [ "serial",       "serials instead of original names in the output file", ],
        [ "all",          "all overlaps instead of proper overlaps", ],
        [ "tmp=s",        "user defined tempdir", ],
        [ "parallel|p=i", "number of threads", { default => 8 }, ],
        [ "verbose|v",    "verbose mode", ],
        { show_defaults => 1, }
    );
}

sub usage_desc {
    return "dazz overlap [options] <infiles>";
}

sub description {

lib/App/Dazz/Command/overlap2.pm  view on Meta::CPAN

sub opt_spec {
    return (
        [ "dir|d=s",      "working directory",     { default => "." }, ],
        [ "p1=s",         "prefix of first file",  { default => "anchor" }, ],
        [ "p2=s",         "prefix of second file", { default => "long" }, ],
        [ "pd=s",         "prefix of result files", ],
        [ "block|b=i",    "block size in Mbp",            { default => 20 }, ],
        [ "len|l=i",      "minimal length of overlaps",   { default => 1000 }, ],
        [ "idt|i=f",      "minimal identity of overlaps", { default => 0.8 }, ],
        [ "all",          "all overlaps instead of proper overlaps", ],
        [ "parallel|p=i", "number of threads", { default => 8 }, ],
        [ "verbose|v",    "verbose mode", ],
        { show_defaults => 1, }
    );
}

sub usage_desc {
    return "dazz overlap2 [options] <infile1> <infile2>";
}

sub description {