comparison khmer_load_into_counting.xml @ 0:69d52f45c2fa draft

planemo upload

0:69d52f45c2fa

<tool id="khmer_load_into_counting" name="Load Into Counting" version="0.1.5">
    <description>Creates k-mer countgraph using reads</description>
    <requirements>
        <requirement type="package" version="2.1.2">khmer</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        load-into-counting.py
        $advanced.b
        $advanced.small
        -k $advanced.kmer
        -U $advanced.ukmer
        #if str( $advanced.max_mem ) != "0"
            -M $advanced.max_mem
        #end if
        #if str( $advanced.fp_rate ) != "0"
            --fp-rate $advanced.fp_rate
        #end if
        #if str( $advanced.num_table ) != "0"
            -N $advanced.num_table
        #end if
        #if str( $advanced.table_size ) != "0"
            -x $advanced.table_size
        #end if
        hash.ct.gz
        #if str( $data_input.data_selector ) == "paired"       
            $data_input.input1.forward $data_input.input1.reverse
        #end if
        #if str( $data_input.data_selector ) == "single"       
            $data_input.input2
        #end if
    ]]></command>
    <inputs>
        <conditional name="data_input">
            <param name="data_selector" type="select" label="Single or Paired-end Data" help="Select between paired and single end data to add name to dataset">
                <option value="paired">Paired</option>
                <option value="single">Single</option>
            </param>
            <when value="paired">
                <param name="input1" format="data" type="data_collection" collection_type="paired" label="Select a paired collection" help="a paired data"/>
            </when>
            <when value="single">
                <param name="input2" format="data" type="data" label="input" help="Specify dataset with single reads"/>
            </when>
        </conditional>
        <section name="advanced" title="Advanced options" expanded="false">
            <param type="boolean" argument="--small" label="Small count" checked="false" truevalue="--small-count" falsevalue="" help="Reduce memory usage by using a smaller counter for individual kmers. (default: False)"/>
            <param type="boolean" argument="-b" label="big count" checked="True" truevalue="-b" falsevalue="--no-bigcount" help="Reduce memory usage by using a smaller counter for individual kmers. (default: True)"/>
            <param name="thread" type="integer" value="1" label="Threads" help="Number of simultaneous threads to execute (default: 1)" />
            <param name="kmer" type="integer" value="32" label="K-mer" help="K-mer size to use (default: 32)" />
            <param name="ukmer" type="integer" value="0" label="Unique K-mer" help="approximate number of unique kmers in the input set (default: 0)" />
            <param name="num_table" type="integer" value="0" label="Number of tables" help="number of tables to use (default: False)" />
            <param name="table_size" type="integer" value="0" label="Maximum size of table" help="maximum size of tables to use (default: False)" />
            <param name="max_mem" type="integer" value="0" label="Maximum Memory" help="number of tables to use (default: False)" />
            <param name="fp_rate" type="integer" value="0" label="FP rate override" help="Override the automatic FP rate setting for the current script" />
        </section>
    </inputs>
    <outputs>
        <data name="hash_output" label="Hash output" format="data" from_work_dir="hash.ct.gz"/>
    </outputs>
    <help><![CDATA[
|| This is the script load-into-counting.py in khmer.
|| You are running khmer version 2.1.2
|| You are also using screed version 1.0
||
|| If you use this script in a publication, please cite EACH of the following:
||
||   * MR Crusoe et al., 2015. http://dx.doi.org/10.12688/f1000research.6924.1
||   * Q Zhang et al., http://dx.doi.org/10.1371/journal.pone.0101271
||   * A. Döring et al. http://dx.doi.org:80/10.1186/1471-2105-9-11
||
|| Please see http://khmer.readthedocs.io/en/latest/citations.html for details.

usage: load-into-counting.py [--version] [--info] [-h] [-k KSIZE]
                             [-U UNIQUE_KMERS] [--fp-rate FP_RATE]
                             [-M MAX_MEMORY_USAGE] [--small-count]
                             [-T THREADS] [-b] [-s FORMAT] [-f] [-q]
                             output_countgraph_filename
                             input_sequence_filename
                             [input_sequence_filename ...]

Build a k-mer countgraph from the given sequences.

positional arguments:
  output_countgraph_filename
                        The name of the file to write the k-mer countgraph to.
  input_sequence_filename
                        The names of one or more FAST[AQ] input sequence
                        files.

optional arguments:
  --version             show program's version number and exit
  --info                print citation information
  -h, --help            show this help message and exit
  -k KSIZE, --ksize KSIZE
                        k-mer size to use (default: 32)
  -U UNIQUE_KMERS, --unique-kmers UNIQUE_KMERS
                        approximate number of unique kmers in the input set
                        (default: 0)
  --fp-rate FP_RATE     Override the automatic FP rate setting for the current
                        script (default: None)
  -M MAX_MEMORY_USAGE, --max-memory-usage MAX_MEMORY_USAGE
                        maximum amount of memory to use for data structure
                        (default: None)
  --small-count         Reduce memory usage by using a smaller counter for
                        individual kmers. (default: False)
  -T THREADS, --threads THREADS
                        Number of simultaneous threads to execute (default: 1)
  -b, --no-bigcount     The default behaviour is to count past 255 using
                        bigcount. This flag turns bigcount off, limiting
                        counts to 255. (default: True)
  -s FORMAT, --summary-info FORMAT
                        What format should the machine readable run summary be
                        in? (`json` or `tsv`, disabled by default) (default:
                        None)
  -f, --force           Overwrite output file if it exists (default: False)
  -q, --quiet

Note: with `-b`/`--no-bigcount` the output will be the exact size of the k-mer
countgraph and this script will use a constant amount of memory. In exchange
k-mer counts will stop at 255. The memory usage of this script with `-b` will
be about 1.15x the product of the `-x` and `-N` numbers.

Example:

    load-into-counting.py -k 20 -x 5e7 out data/100k-filtered.fa

Multiple threads can be used to accelerate the process, if you have extra cores
to spare.

Example:

    load-into-counting.py -k 20 -x 5e7 -T 4 out data/100k-filtered.fa


    ]]></help>
    <citations>
        <citation type="bibtex">
@misc{githubkhmer,
  author = {Crusoe, Michael},
  year = {2015},
  title = {khmer},
  publisher = {GitHub},
  journal = {GitHub repository},
  url = {https://github.com/dib-lab/khmer},
}</citation>
    </citations>
</tool>