App-Anchr

 view release on metacpan or  search on metacpan

doc/gage_b.md  view on Meta::CPAN

```bash
BASE_NAME=Bcer
cd ${HOME}/data/anchr/${BASE_NAME}

mkdir -p 2_illumina
cd 2_illumina

aria2c -x 9 -s 3 -c http://ccb.jhu.edu/gage_b/datasets/B_cereus_MiSeq.tar.gz

# NOT gzipped tar
tar xvf B_cereus_MiSeq.tar.gz raw/frag_1__cov100x.fastq
tar xvf B_cereus_MiSeq.tar.gz raw/frag_2__cov100x.fastq

cat raw/frag_1__cov100x.fastq \
    | pigz -p 8 -c \
    > R1.fq.gz
cat raw/frag_2__cov100x.fastq \
    | pigz -p 8 -c \
    > R2.fq.gz

rm -fr raw
```

* GAGE-B assemblies

```bash
BASE_NAME=Bcer

doc/masurca.md  view on Meta::CPAN

JF_SIZE = 50000000
END

EOF

# Illumina PE, Short Jump and Sanger4
mkdir -p rhodobacter_PE_SJ_Sanger4
cp sr_config.txt rhodobacter_PE_SJ_Sanger4/
cat <<EOF >> rhodobacter_PE_SJ_Sanger4/sr_config.txt
DATA
PE=  pe 180 20 /home/wangq/data/test/rhodobacter/PE/frag_1.fastq /home/wangq/data/test/rhodobacter/PE/frag_2.fastq
JUMP= sj 3600 200  /home/wangq/data/test/rhodobacter/SJ/short_1.fastq  /home/wangq/data/test/rhodobacter/SJ/short_2.fastq
OTHER=/home/wangq/data/test/rhodobacter/Sanger/rhodobacter_sphaeroides_2_4_1.4x.frg
END

EOF

# Illumina PE, Short Jump and Sanger
mkdir -p rhodobacter_PE_SJ_Sanger
cp sr_config.txt rhodobacter_PE_SJ_Sanger/
cat <<EOF >> rhodobacter_PE_SJ_Sanger/sr_config.txt
DATA
PE=  pe 180 20 /home/wangq/data/test/rhodobacter/PE/frag_1.fastq /home/wangq/data/test/rhodobacter/PE/frag_2.fastq
JUMP= sj 3600 200  /home/wangq/data/test/rhodobacter/SJ/short_1.fastq  /home/wangq/data/test/rhodobacter/SJ/short_2.fastq
OTHER=/home/wangq/data/test/rhodobacter/Sanger/rhodobacter_sphaeroides_2_4_1.1x.frg
END

EOF

# Illumina PE and Short Jump
mkdir -p rhodobacter_PE_SJ
cp sr_config.txt rhodobacter_PE_SJ/
cat <<EOF >> rhodobacter_PE_SJ/sr_config.txt
DATA
PE=  pe 180 20 /home/wangq/data/test/rhodobacter/PE/frag_1.fastq /home/wangq/data/test/rhodobacter/PE/frag_2.fastq
JUMP= sj 3600 200  /home/wangq/data/test/rhodobacter/SJ/short_1.fastq  /home/wangq/data/test/rhodobacter/SJ/short_2.fastq
END

EOF

# Illumina PE, and Sanger4
mkdir -p rhodobacter_PE_Sanger4
cp sr_config.txt rhodobacter_PE_Sanger4/
cat <<EOF >> rhodobacter_PE_Sanger4/sr_config.txt
DATA
PE=  pe 180 20 /home/wangq/data/test/rhodobacter/PE/frag_1.fastq /home/wangq/data/test/rhodobacter/PE/frag_2.fastq
OTHER=/home/wangq/data/test/rhodobacter/Sanger/rhodobacter_sphaeroides_2_4_1.4x.frg
END

EOF

# Illumina PE, and Sanger
mkdir -p rhodobacter_PE_Sanger
cp sr_config.txt rhodobacter_PE_Sanger/
cat <<EOF >> rhodobacter_PE_Sanger/sr_config.txt
DATA
PE=  pe 180 20 /home/wangq/data/test/rhodobacter/PE/frag_1.fastq /home/wangq/data/test/rhodobacter/PE/frag_2.fastq
OTHER=/home/wangq/data/test/rhodobacter/Sanger/rhodobacter_sphaeroides_2_4_1.1x.frg
END

EOF

# Illumina PE
mkdir -p rhodobacter_PE_Sanger
cp sr_config.txt rhodobacter_PE_Sanger/
cat <<EOF >> rhodobacter_PE_Sanger/sr_config.txt
DATA
PE=  pe 180 20 /home/wangq/data/test/rhodobacter/PE/frag_1.fastq /home/wangq/data/test/rhodobacter/PE/frag_2.fastq
END

EOF

# Run
cd ~/data/test

for d in rhodobacter_PE_SJ_Sanger4 rhodobacter_PE_SJ_Sanger rhodobacter_PE_SJ rhodobacter_PE_Sanger4 rhodobacter_PE_Sanger rhodobacter_PE rhodobacter_superreads;
do
    echo "==> ${d}"

doc/masurca.md  view on Meta::CPAN

    bash assemble.sh
    popd > /dev/null
done
```

### Rhodobacter sphaeroides with `anchr superreads`

```bash
# gzip original fastq
mkdir -p ~/data/test/rhodobacter/PEgz
gzip -c ~/data/test/rhodobacter/PE/frag_1.fastq > ~/data/test/rhodobacter/PEgz/frag_1.fq.gz
gzip -c ~/data/test/rhodobacter/PE/frag_2.fastq > ~/data/test/rhodobacter/PEgz/frag_2.fq.gz

mkdir -p ~/data/test/rhodobacter_superreads
cd ~/data/test/rhodobacter_superreads

perl ~/Scripts/sra/superreads.pl \
    ~/data/test/rhodobacter/PEgz/frag_1.fq.gz \
    ~/data/test/rhodobacter/PEgz/frag_2.fq.gz \
    -s 180 -d 20

```

### 结果比较

```bash
cd ~/data/test/

printf "| %s | %s | %s | %s | %s | %s | %s | %s |\n" \

lib/App/Anchr/Command/break.pm  view on Meta::CPAN

    {
        $tempdir->child("break.fasta")->remove;
        for my $serial ( sort { $a <=> $b } keys %{$region_of} ) {

            #@type AlignDB::IntSpan
            my $region = $region_of->{$serial};

            for my $set ( $region->sets ) {
                my $cmd;
                $cmd .= "DBshow -U $fn_dazz $serial";
                $cmd .= " | faops frag -l 0 stdin @{[$set->min]} @{[$set->max]} stdout";
                $cmd .= " >> break.fasta";
                App::Anchr::Common::exec_cmd( $cmd, { verbose => $opt->{verbose}, } );
            }
        }

        if ( !$tempdir->child("break.fasta")->is_file ) {
            Carp::croak "Failed: create break.fasta\n";
        }

        YAML::Syck::DumpFile(

lib/App/Anchr/Command/cover.pm  view on Meta::CPAN

    #
    #                #@type AlignDB::IntSpan
    #                my $region = $covered_of->{$serial}{ $opt->{coverage} };
    #
    #                for my $set ( $region->sets ) {
    #                    next if $set->size < $opt->{len};
    #
    #                    my $cmd;
    #                    $cmd .= "DBshow -U $basename $serial";
    #                    $cmd .= " | faops replace -l 0 stdin first.replace.tsv stdout";
    #                    $cmd .= " | faops frag -l 0 stdin @{[$set->min]} @{[$set->max]} stdout";
    #                    $cmd .= " >> covered.fasta";
    #                    App::Anchr::Common::exec_cmd( $cmd, { verbose => $opt->{verbose}, } );
    #                }
    #            }
    #        }
    #
    #        if ( !$tempdir->child("covered.fasta")->is_file ) {
    #            Carp::croak "Failed: create covered.fasta\n";
    #        }
    #    }

lib/App/Anchr/Command/quorum.pm  view on Meta::CPAN

use autodie;

use App::Anchr -command;
use App::Anchr::Common;

use constant abstract => "Run quorum to discard bad reads";

sub opt_spec {
    return (
        [ "outfile|o=s", "output filename, [stdout] for screen", { default => "quorum.sh" }, ],
        [ 'size|s=i',    'fragment size',                        { default => 300, }, ],
        [ 'std|d=i',     'fragment size standard deviation',     { default => 30, }, ],
        [ 'jf=i',        'jellyfish hash size',                  { default => 500_000_000, }, ],
        [ 'estsize=s',   'estimated genome size',                { default => "auto", }, ],
        [   "adapter|a=s", "adapter file",
            { default => File::ShareDir::dist_file( 'App-Anchr', 'adapter.jf' ) },
        ],
        [ 'parallel|p=i', 'number of threads', { default => 8, }, ],
        { show_defaults => 1, }
    );
}