App-Fasops
view release on metacpan or search on metacpan
{
"abstract" : "operating blocked fasta files",
"author" : [
"Qiang Wang <wang-q@outlook.com>"
],
"dynamic_config" : 0,
"generated_by" : "Minilla/v3.1.5",
"license" : [
"perl_5"
],
"meta-spec" : {
"url" : "http://search.cpan.org/perldoc?CPAN::Meta::Spec",
---
abstract: 'operating blocked fasta files'
author:
- 'Qiang Wang <wang-q@outlook.com>'
build_requires:
Spreadsheet::XLSX: '0.15'
Test::More: '0.88'
Test::Number::Delta: '1.06'
configure_requires:
Module::Build::Tiny: '0.035'
dynamic_config: 0
generated_by: 'Minilla/v3.1.5, CPAN::Meta::Converter version 2.150010'
[](https://travis-ci.org/wang-q/App-Fasops) [](https://codecov.io/github/wang-q/App-Fas...
# NAME
App::Fasops - operating blocked fasta files
# SYNOPSIS
fasops <command> [-?h] [long options...]
-? -h --help show help
Available commands:
commands: list the application's commands
help: display a command's help screen
axt2fas: convert axt to blocked fasta
check: check genome locations in (blocked) fasta headers
concat: concatenate sequence pieces in blocked fasta files
consensus: create consensus from blocked fasta file
covers: scan blocked fasta files and output covers on chromosomes
join: join multiple blocked fasta files by common target
links: scan blocked fasta files and output bi/multi-lateral range links
maf2fas: convert maf to blocked fasta
mergecsv: merge csv files based on @fields
names: scan blocked fasta files and output all species names
refine: realign blocked fasta file with external programs
replace: replace headers from a blocked fasta
separate: separate blocked fasta files by species
slice: extract alignment slices from a blocked fasta
split: split blocked fasta files to per-alignment files
stat: basic statistics on alignments
subset: extract a subset of species from a blocked fasta
xlsx: paint substitutions and indels to an excel file
See `fasops commands` for usage information.
# AUTHOR
Qiang Wang <wang-q@outlook.com>
# COPYRIGHT AND LICENSE
lib/App/Fasops.pm view on Meta::CPAN
use strict;
use warnings;
use App::Cmd::Setup -app;
1;
__END__
=head1 NAME
App::Fasops - operating blocked fasta files
=head1 SYNOPSIS
fasops <command> [-?h] [long options...]
-? -h --help show help
Available commands:
commands: list the application's commands
help: display a command's help screen
axt2fas: convert axt to blocked fasta
check: check genome locations in (blocked) fasta headers
concat: concatenate sequence pieces in blocked fasta files
consensus: create consensus from blocked fasta file
covers: scan blocked fasta files and output covers on chromosomes
join: join multiple blocked fasta files by common target
links: scan blocked fasta files and output bi/multi-lateral range links
maf2fas: convert maf to blocked fasta
mergecsv: merge csv files based on @fields
names: scan blocked fasta files and output all species names
refine: realign blocked fasta file with external programs
replace: replace headers from a blocked fasta
separate: separate blocked fasta files by species
slice: extract alignment slices from a blocked fasta
split: split blocked fasta files to per-alignment files
stat: basic statistics on alignments
subset: extract a subset of species from a blocked fasta
xlsx: paint substitutions and indels to an excel file
See C<fasops commands> for usage information.
=head1 AUTHOR
Qiang Wang <wang-q@outlook.com>
=head1 COPYRIGHT AND LICENSE
lib/App/Fasops/Command/axt2fas.pm view on Meta::CPAN
package App::Fasops::Command::axt2fas;
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'convert axt to blocked fasta';
}
sub opt_spec {
return (
[ "outfile|o=s", "Output filename, [stdout] for screen" ],
[ "length|l=i", "the threshold of alignment length", { default => 1 }, ],
[ "tname|t=s", "target name", { default => "target" }, ],
[ "qname|q=s", "query name", { default => "query" }, ],
[ "size|s=s", "query chr.sizes", ],
{ show_defaults => 1, }
lib/App/Fasops/Command/check.pm view on Meta::CPAN
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'check genome locations in (blocked) fasta headers';
}
sub opt_spec {
return (
[ "outfile|o=s", "Output filename. [stdout] for screen." ],
[ "name|n=s", "Which species to be checked, omit this will check all sequences" ],
{ show_defaults => 1, }
);
}
lib/App/Fasops/Command/concat.pm view on Meta::CPAN
package App::Fasops::Command::concat;
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'concatenate sequence pieces in blocked fasta files';
}
sub opt_spec {
return (
[ "outfile|o=s", "Output filename. [stdout] for screen" ],
[ "total|t=i", "Stop when exceed this length", { default => 10_000_000, }, ],
[ "relaxed", "output relaxed phylip instead of fasta" ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "fasops concat [options] <infile> <name.list>";
}
sub description {
my $desc;
$desc .= ucfirst(abstract) . ".\n";
$desc .= <<'MARKDOWN';
* <infile> is the path to blocked fasta file, .fas.gz is supported
* infile == stdin means reading from STDIN
* <name.list> is a file with a list of names to keep, one per line
* Names in the output file will following the order in <name.list>
MARKDOWN
return $desc;
}
sub validate_args {
lib/App/Fasops/Command/consensus.pm view on Meta::CPAN
use MCE;
use MCE::Flow Sereal => 1;
use MCE::Candy;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'create consensus from blocked fasta file';
}
sub opt_spec {
return (
[ "outfile|o=s", "output filename. [stdout] for screen" ],
[ "outgroup", "has outgroup at the end of blocks", ],
[ "cname", "the name of consensus", { default => "consensus" }, ],
[ "parallel|p=i", "run in parallel mode", { default => 1 }, ],
{ show_defaults => 1, }
);
lib/App/Fasops/Command/consensus.pm view on Meta::CPAN
sub usage_desc {
return "fasops consensus [options] <infile>";
}
sub description {
my $desc;
$desc .= ucfirst(abstract) . ".\n";
$desc .= <<'MARKDOWN';
* <infile> are paths to blocked fasta files, .fas.gz is supported
* infile == stdin means reading from STDIN
* `poa` is used for creating consensus sequences
MARKDOWN
return $desc;
}
sub validate_args {
my ( $self, $opt, $args ) = @_;
lib/App/Fasops/Command/covers.pm view on Meta::CPAN
package App::Fasops::Command::covers;
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::Fasops::Common;
sub abstract {
return 'scan blocked fasta files and output covers on chromosomes';
}
sub opt_spec {
return (
[ "outfile|o=s", "Output filename. [stdout] for screen" ],
[ "name|n=s", "Only output this species" ],
[ "length|l=i", "the threshold of alignment length", { default => 1 } ],
[ "trim|t=i",
"Trim align borders to avoid some overlaps in lastz results",
{ default => 0 }
lib/App/Fasops/Command/create.pm view on Meta::CPAN
package App::Fasops::Command::create;
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'create blocked fasta files from links of ranges';
}
sub opt_spec {
return (
[ "outfile|o=s", "Output filename. [stdout] for screen" ],
[ "genome|g=s", "Reference genome file", { required => 1 }, ],
[ "name|n=s", "Default name for ranges", ],
{ show_defaults => 1, }
);
}
lib/App/Fasops/Command/join.pm view on Meta::CPAN
package App::Fasops::Command::join;
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'join multiple blocked fasta files by common target';
}
sub opt_spec {
return (
[ "outfile|o=s", "Output filename. [stdout] for screen" ],
[ "name|n=s", "According to this species. Default is the first one" ],
{ show_defaults => 1, }
);
}
lib/App/Fasops/Command/links.pm view on Meta::CPAN
package App::Fasops::Command::links;
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'scan blocked fasta files and output bi/multi-lateral range links';
}
sub opt_spec {
return (
[ "outfile|o=s", "Output filename. [stdout] for screen." ],
[ "pair|p", "pairwise links" ],
[ "best|b", "best-to-best pairwise links" ],
{ show_defaults => 1, }
);
}
lib/App/Fasops/Command/maf2fas.pm view on Meta::CPAN
package App::Fasops::Command::maf2fas;
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'convert maf to blocked fasta';
}
sub opt_spec {
return (
[ "outfile|o=s", "Output filename. [stdout] for screen" ],
[ "length|l=i", "the threshold of alignment length", { default => 1 } ],
{ show_defaults => 1, }
);
}
lib/App/Fasops/Command/names.pm view on Meta::CPAN
package App::Fasops::Command::names;
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::Fasops::Common;
sub abstract {
return 'scan blocked fasta files and output all species names';
}
sub opt_spec {
return (
[ "outfile|o=s", "Output filename. [stdout] for screen" ],
[ "count|c", "Also count name occurrences" ],
{ show_defaults => 1, }
);
}
lib/App/Fasops/Command/refine.pm view on Meta::CPAN
use MCE;
use MCE::Flow Sereal => 1;
use MCE::Candy;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'realign blocked fasta file with external programs';
}
sub opt_spec {
return (
[ "outfile|o=s", "Output filename. [stdout] for screen" ],
[ "outgroup", "Has outgroup at the end of blocks", ],
[ "parallel|p=i", "run in parallel mode", { default => 1 }, ],
[ "msa=s", "Aligning program", { default => "mafft" }, ],
[ "quick",
"Quick mode, only aligning indel adjacent regions. Suitable for multiz outputs",
lib/App/Fasops/Command/refine.pm view on Meta::CPAN
sub description {
my $desc;
$desc .= ucfirst(abstract) . ".\n";
$desc .= <<'MARKDOWN';
* List of msa:
* mafft
* muscle
* clustalw
* none: means skip realigning
* <infile> are paths to blocked fasta files, .fas.gz is supported
* infile == stdin means reading from STDIN
MARKDOWN
return $desc;
}
sub validate_args {
my ( $self, $opt, $args ) = @_;
lib/App/Fasops/Command/replace.pm view on Meta::CPAN
package App::Fasops::Command::replace;
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'replace headers from a blocked fasta';
}
sub opt_spec {
return ( [ "outfile|o=s", "Output filename. [stdout] for screen." ], { show_defaults => 1, } );
}
sub usage_desc {
return "fasops replace [options] <infile> <replace.tsv>";
}
lib/App/Fasops/Command/separate.pm view on Meta::CPAN
package App::Fasops::Command::separate;
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'separate blocked fasta files by species';
}
sub opt_spec {
return (
[ "outdir|o=s", "Output location, [stdout] for screen", { default => '.' } ],
[ "suffix|s=s", "Extensions of output files", { default => '.fasta' } ],
[ "rm|r", "If outdir exists, remove it before operating" ],
[ "rc", "Revcom sequences when chr_strand is '-'" ],
[ "nodash", "Remove dashes ('-') from sequences" ],
{ show_defaults => 1, }
lib/App/Fasops/Command/slice.pm view on Meta::CPAN
package App::Fasops::Command::slice;
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'extract alignment slices from a blocked fasta';
}
sub opt_spec {
return (
[ "outfile|o=s", "Output filename. [stdout] for screen." ],
[ "name|n=s", "According to this species. Default is the first one." ],
[ "length|l=i", "the threshold of alignment length", { default => 1 } ],
{ show_defaults => 1, }
);
}
lib/App/Fasops/Command/split.pm view on Meta::CPAN
package App::Fasops::Command::split;
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'split blocked fasta files to per-alignment files';
}
sub opt_spec {
return (
[ "outdir|o=s", "Output location, [stdout] for screen" ],
[ "rm|r", "if outdir exists, remove it before operating." ],
[ "chr", "split by chromosomes." ],
[ "simple", "only keep names in headers" ],
{ show_defaults => 1, }
);
lib/App/Fasops/Command/split.pm view on Meta::CPAN
sub usage_desc {
return "fasops split [options] <infile> [more infiles]";
}
sub description {
my $desc;
$desc .= ucfirst(abstract) . ".\n";
$desc .= <<'MARKDOWN';
* <infiles> are paths to blocked fasta files, .fas.gz is supported
* infile == stdin means reading from STDIN
MARKDOWN
return $desc;
}
sub validate_args {
my ( $self, $opt, $args ) = @_;
lib/App/Fasops/Command/subset.pm view on Meta::CPAN
package App::Fasops::Command::subset;
use strict;
use warnings;
use autodie;
use App::Fasops -command;
use App::RL::Common;
use App::Fasops::Common;
sub abstract {
return 'extract a subset of species from a blocked fasta';
}
sub opt_spec {
return (
[ "outfile|o=s", "Output filename. [stdout] for screen" ],
[ "first", "Always keep the first species" ],
[ "required", "Skip blocks not containing all the names" ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "fasops subset [options] <infile> <name.list>";
}
sub description {
my $desc;
$desc .= ucfirst(abstract) . ".\n";
$desc .= <<'MARKDOWN';
* <infile> is the path to blocked fasta file, .fas.gz is supported
* infile == stdin means reading from STDIN
* <name.list> is a file with a list of names to keep, one per line
* Names in the output file will following the order in <name.list>
MARKDOWN
return $desc;
}
sub validate_args {
( run in 1.487 second using v1.01-cache-2.11-cpan-49f99fa48dc )