comparison bbnorm.xml @ 5:770bceda7785 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bbtools commit cd59ba2c349865259b92302a1d70e103b8a5e3cb

4:1baa4ad1ac2f

            <when value="PE_2files">
                <param name="read1" type="data" format="fastqsanger,fastqsanger.gz" label="Forward reads"/>
                <param name="read2" type="data" format="fastqsanger,fastqsanger.gz" label="Reverse reads"/>
            </when>
            <when value="paired">
                <param name="reads_collection" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="paired" label="Collection of forward and reverse reads"/>
            </when>
        </conditional>
        <param argument="target" type="integer" value="100" min="1" label="Target normalization depth" help="All depth parameters control kmer depth, not read depth. For kmer depth Dk, read depth Dr, read length R, and kmer size K: Dr=Dk*(R/(R-K+1))"/>
        <section name="norm_params" title="Normalization parameters">
            <param argument="maxdepth" type="integer" value="-1" min="-1" label="Reads will not be downsampled when below this depth, even if they are above the target depth." help="All depth parameters control kmer depth, not read depth. For kmer depth Dk, read depth Dr, read length R, and kmer size K: Dr=Dk*(R/(R-K+1))"/>
            <param argument="mindepth" type="integer" value="5" min="0" label="kmers with depth below this number will not be included when calculating the depth of a read." help="All depth parameters control kmer depth, not read depth. For kmer depth Dk, read depth Dr, read length R, and kmer size K: Dr=Dk*(R/(R-K+1))"/>
            <param argument="minkmers" type="integer" value="15" min="0" label="Reads must have at least this many kmers over min depth to be retained."/>
            <param argument="percentile" type="integer" value="54" min="1" max="100" label="Percentile to infer read depth" help="Read depth is by default inferred from the 54th percentile of kmer depth, but this may be changed to any number 1-100."/>
            <param argument="uselowerdepth" type="boolean" checked="true" label="For pairs, use the depth of the lower read as the depth proxy."/>
            <param argument="deterministic" type="boolean" checked="true" label="Generate random numbers deterministically" help="This would ensure identical output between multiple runs. May decrease speed with a huge number of threads."/>
            <param argument="fixspikes" type="boolean" checked="false" label="Do a slower, high-precision bloom filter lookup of kmers that appear to have an abnormally high depth due to collisions."/>
            <param argument="passes" type="integer" value="2" label="Number of passes to perform" help=" pass is the basic mode. 2 passes allows greater accuracy, error detection, better contol of output depth."/>
        </section>
        <section name="hashing_params" title="Hashing parameters">
            <param argument="k" type="integer" value="31" min="1" label="kmer length" help="Values under 32 are most efficient, but arbitrarily high values are supported."/>
            <param argument="bits" type="select" label="Bits per cell in bloom filter" help="Maximum kmer depth recorded is 2^c bits. Large values decrease accuracy for a fixed amount of memory, so use the lowest number you can that will still capture highest-depth kmers.">
                <option value="2">2</option>
                <option value="4">4</option>
                <option value="8">8</option>
                <option value="16" selected="true">16</option>
                <option value="32">32</option>
            </param>
            <param argument="hashes" type="integer" value="3" min="1" label="Number of times each kmer is hashed and stored." help="Higher is slower. Higher is more accurate if there is enough memory, but less accurate if there is not enough memory."/>
            <conditional name="prefilter">
                <param argument="prefilter" type="select" label="Use a prefilter to eliminate low-depth kmers" help="True is slower, but generally more accurate; filters out low-depth kmers from the main hashtable. The prefilter is more memory-efficient because it uses 2-bit cells.">
                    <option value="true">Yes</option>
                    <option value="false" selected="true">No</option>
                </param>
                <when value="false"/>
                <when value="true">
                    <param argument="prehashes" type="integer" value="2" min="1" label="Number of hashes for the prefilter"/>
                    <param argument="prefilterbits" type="integer" value="2" min="1" label="Bits per cell in prefilter"/>
                    <param argument="prefiltersize" type="float" value="0.35" min="0" max="1" label="Fraction of memory to allocate for the prefilter."/>
                </when>
            </conditional>          
            <param argument="buildpasses" type="integer" value="1" min="1" label="Number of passes" help="More passes can sometimes increase accuracy by iteratively removing low-depth kmers"/>
            <param argument="minq" type="integer" value="6" min="0" label="Ignore kmers containing bases with quality below this threshold"/>
            <param argument="minprob" type="float" value="0.5" min="0" max="1" label="Ignore kmers with overall probability of correctness below this threshold"/>
            <param argument="rdk" type="boolean" checked="true" label="Remove duplicate kmers" help="When true, a kmer's count will only be incremented once per read pair, even if that kmer occurs more than once."/>
        </section>
        <section name="error_det_params" title="Error detection parameters">
            <param argument="hdp" type="integer" value="90" min="0" max="100" label="highdepthpercentile" help="Position in sorted kmer depth array used as proxy of a read's high kmer depth."/>
            <param argument="ldp" type="integer" value="25" min="0" max="100" label="lowdepthpercentile" help="Position in sorted kmer depth array used as proxy of a read's low kmer depth."/>
            <param argument="tossbadreads" type="boolean" checked="false" label="Throw away reads detected as containing errors."/>
            <param argument="requirebothbad" type="boolean" checked="false" label="Only toss bad pairs if both reads are bad."/>
            <param argument="errordetectratio" type="integer" value="125" min="0" label="Error detection ratio" help="Reads with a ratio of at least this much between their high and low depth kmers will be classified as error reads."/>
            <param argument="highthresh" type="integer" value="12" min="0" label="Threshold for high kmer" help="A high kmer at this or above are considered non-error."/>
            <param argument="lowthresh" type="integer" value="3" min="0" label="Threshold for low kmer" help="Kmers at this and below are always considered errors."/>
        </section>
        
        <section name="error_corr_params" title="Error correction parameters">
            <conditional name="ecc">
                <param argument="ecc" type="select" label="What should be done with detected errors?" help="Tadpole is now preferred for error correction, as it does a better job.">
                    <option value="true" >Correct errors when possible</option>
                    <option value="false" selected="true">Do not attempt to correct errors</option>
                </param>
                <when value="false"/>
                <when value="true">
                    <param argument="ecclimit" type="integer" value="3" min="1" label="Correct up to this many errors per read." help="If more are detected, the read will remain unchanged."/>
                    <param argument="errorcorrectratio" type="integer" value="140" min="0" label="Depth ratio" help="Adjacent kmers with a depth ratio of at least this much between will be classified as an error."/>
                    <param argument="echighthresh" type="integer" value="22" min="0" label="Threshold for high kmer" help="A kmer at this or above may be considered non-error."/>
                    <param argument="eclowthresh" type="integer" value="2" min="0" label="Threshold for low kmer." help="kmers at this depth or below will be considered as errors."/>
                    <param argument="eccmaxqual" type="integer" value="127" min="0" label="Do not correct bases with quality above this value."/>
                    <param argument="meo" type="boolean" checked="false" label="Marks errors by reducing quality value of suspected errors; does not correct anything."/>
                    <param argument="mue" type="boolean" checked="true" label="Mark errors only on uncorrectable reads."/>
                    <param argument="overlap" type="boolean" checked="false" label="Correct errors by read overlap."/>
                </when>
            </conditional>
        </section>

        <section name="output_options" title="Output options">
            <param name="save_discarded_reads" type="boolean" checked="false" label="Save the reads that were eliminated from the input datasets to the history"/>
            <param name="save_kmer_hists" type="boolean" checked="false" label="Save the kmer histograms (in tabular format) for the input and output datasets to the history"/>
        </section>
    </inputs>

    </outputs>
    <tests>
        <!-- Single end sequencing -->
        <test expect_num_outputs="1">
            <param name="input_type" value="single_end"/>
            <param name="read1" ftype="fastqsanger" value="bbnorm/input_R1.fastq"/>
            <param name="target" value="4"/>
            <section name="norm_params">
                <param name="deterministic" value="true"/>
                <param name="mindepth" value="0"/>
            </section>
            <output name="output_normalised_R1" ftype="fastqsanger" value="bbnorm/normalised_R1.fastq"/>
        </test>
        <!-- Single end sequencing, compressed -->
        <test expect_num_outputs="1">
            <param name="input_type" value="single_end"/>
            <param name="read1" ftype="fastqsanger.gz" value="bbnorm/input_R1.fastq.gz"/>
            <param name="target" value="4"/>
            <section name="norm_params">
                <param name="deterministic" value="true"/>
                <param name="mindepth" value="0"/>
            </section>
            <output name="output_normalised_R1" ftype="fastqsanger.gz" value="bbnorm/normalised_R1.fastq"/>
        </test>
        <!-- PE as an interleaved file -->
        <test expect_num_outputs="4">
            <param name="input_type" value="PE_1file"/>
            <param name="read1" ftype="fastqsanger" value="bbnorm/input_interleaved.fastq"/>
            <param name="target" value="4"/>
            <section name="norm_params">
                <param name="deterministic" value="true"/>
                <param name="mindepth" value="0"/>
            </section>

            <output name="kmer_hist_output" ftype="tabular" file="bbnorm/kmer_hist_output.tabular"/>
        </test>
        <!-- PE as 2 files -->
        <test expect_num_outputs="2">
            <param name="input_type" value="PE_2files"/>
            <param name="read1" ftype="fastqsanger" value="bbnorm/input_R1.fastq"/>
            <param name="read2" ftype="fastqsanger" value="bbnorm/input_R2.fastq"/>
            <param name="target" value="4"/>
            <section name="norm_params">
                <param name="deterministic" value="true"/>
                <param name="mindepth" value="0"/>
            </section>

* The sequencing platform has a very high error rate (ex: ONT) that might mislead this algorithm.

    </help>
    <expand macro="citations"/>
</tool>

5:770bceda7785

            <when value="PE_2files">
                <param name="read1" type="data" format="fastqsanger,fastqsanger.gz" label="Forward reads"/>
                <param name="read2" type="data" format="fastqsanger,fastqsanger.gz" label="Reverse reads"/>
            </when>
            <when value="paired">
                <param name="reads_collection" type="data_collection" format="fastqsanger,fastqsanger.gz" label="Collection of forward and reverse reads" collection_type="paired"/>
            </when>
        </conditional>
        <param argument="target" type="integer" min="1" value="100" label="Target normalization depth" help="All depth parameters control kmer depth, not read depth. For kmer depth Dk, read depth Dr, read length R, and kmer size K: Dr=Dk*(R/(R-K+1))"/>
        <section name="norm_params" title="Normalization parameters">
            <param argument="maxdepth" type="integer" min="-1" value="-1" label="Reads will not be downsampled when below this depth, even if they are above the target depth." help="All depth parameters control kmer depth, not read depth. For kmer depth Dk, read depth Dr, read length R, and kmer size K: Dr=Dk*(R/(R-K+1))"/>
            <param argument="mindepth" type="integer" min="0" value="5" label="kmers with depth below this number will not be included when calculating the depth of a read." help="All depth parameters control kmer depth, not read depth. For kmer depth Dk, read depth Dr, read length R, and kmer size K: Dr=Dk*(R/(R-K+1))"/>
            <param argument="minkmers" type="integer" min="0" value="15" label="Reads must have at least this many kmers over min depth to be retained."/>
            <param argument="percentile" type="integer" min="1" max="100" value="54" label="Percentile to infer read depth" help="Read depth is by default inferred from the 54th percentile of kmer depth, but this may be changed to any number 1-100."/>
            <param argument="uselowerdepth" type="boolean" checked="true" label="For pairs, use the depth of the lower read as the depth proxy."/>
            <param argument="deterministic" type="boolean" checked="true" label="Generate random numbers deterministically" help="This would ensure identical output between multiple runs. May decrease speed with a huge number of threads."/>
            <param argument="fixspikes" type="boolean" checked="false" label="Do a slower, high-precision bloom filter lookup of kmers that appear to have an abnormally high depth due to collisions."/>
            <param argument="passes" type="integer" value="2" label="Number of passes to perform" help=" pass is the basic mode. 2 passes allows greater accuracy, error detection, better contol of output depth."/>
        </section>
        <section name="hashing_params" title="Hashing parameters">
            <param argument="k" type="integer" min="1" value="31" label="kmer length" help="Values under 32 are most efficient, but arbitrarily high values are supported."/>
            <param argument="bits" type="select" label="Bits per cell in bloom filter" help="Maximum kmer depth recorded is 2^c bits. Large values decrease accuracy for a fixed amount of memory, so use the lowest number you can that will still capture highest-depth kmers.">
                <option value="2">2</option>
                <option value="4">4</option>
                <option value="8">8</option>
                <option value="16" selected="true">16</option>
                <option value="32">32</option>
            </param>
            <param argument="hashes" type="integer" min="1" value="3" label="Number of times each kmer is hashed and stored." help="Higher is slower. Higher is more accurate if there is enough memory, but less accurate if there is not enough memory."/>
            <conditional name="prefilter">
                <param argument="prefilter" type="select" label="Use a prefilter to eliminate low-depth kmers" help="True is slower, but generally more accurate; filters out low-depth kmers from the main hashtable. The prefilter is more memory-efficient because it uses 2-bit cells.">
                    <option value="true">Yes</option>
                    <option value="false" selected="true">No</option>
                </param>
                <when value="false"/>
                <when value="true">
                    <param argument="prehashes" type="integer" min="1" value="2" label="Number of hashes for the prefilter"/>
                    <param argument="prefilterbits" type="integer" min="1" value="2" label="Bits per cell in prefilter"/>
                    <param argument="prefiltersize" type="float" min="0" max="1" value="0.35" label="Fraction of memory to allocate for the prefilter."/>
                </when>
            </conditional>
            <param argument="buildpasses" type="integer" min="1" value="1" label="Number of passes" help="More passes can sometimes increase accuracy by iteratively removing low-depth kmers"/>
            <param argument="minq" type="integer" min="0" value="6" label="Ignore kmers containing bases with quality below this threshold"/>
            <param argument="minprob" type="float" min="0" max="1" value="0.5" label="Ignore kmers with overall probability of correctness below this threshold"/>
            <param argument="rdk" type="boolean" checked="true" label="Remove duplicate kmers" help="When true, a kmer's count will only be incremented once per read pair, even if that kmer occurs more than once."/>
        </section>
        <section name="error_det_params" title="Error detection parameters">
            <param argument="hdp" type="integer" min="0" max="100" value="90" label="highdepthpercentile" help="Position in sorted kmer depth array used as proxy of a read's high kmer depth."/>
            <param argument="ldp" type="integer" min="0" max="100" value="25" label="lowdepthpercentile" help="Position in sorted kmer depth array used as proxy of a read's low kmer depth."/>
            <param argument="tossbadreads" type="boolean" checked="false" label="Throw away reads detected as containing errors."/>
            <param argument="requirebothbad" type="boolean" checked="false" label="Only toss bad pairs if both reads are bad."/>
            <param argument="errordetectratio" type="integer" min="0" value="125" label="Error detection ratio" help="Reads with a ratio of at least this much between their high and low depth kmers will be classified as error reads."/>
            <param argument="highthresh" type="integer" min="0" value="12" label="Threshold for high kmer" help="A high kmer at this or above are considered non-error."/>
            <param argument="lowthresh" type="integer" min="0" value="3" label="Threshold for low kmer" help="Kmers at this and below are always considered errors."/>
        </section>
        <section name="error_corr_params" title="Error correction parameters">
            <conditional name="ecc">
                <param argument="ecc" type="select" label="What should be done with detected errors?" help="Tadpole is now preferred for error correction, as it does a better job.">
                    <option value="true">Correct errors when possible</option>
                    <option value="false" selected="true">Do not attempt to correct errors</option>
                </param>
                <when value="false"/>
                <when value="true">
                    <param argument="ecclimit" type="integer" min="1" value="3" label="Correct up to this many errors per read." help="If more are detected, the read will remain unchanged."/>
                    <param argument="errorcorrectratio" type="integer" min="0" value="140" label="Depth ratio" help="Adjacent kmers with a depth ratio of at least this much between will be classified as an error."/>
                    <param argument="echighthresh" type="integer" min="0" value="22" label="Threshold for high kmer" help="A kmer at this or above may be considered non-error."/>
                    <param argument="eclowthresh" type="integer" min="0" value="2" label="Threshold for low kmer." help="kmers at this depth or below will be considered as errors."/>
                    <param argument="eccmaxqual" type="integer" min="0" value="127" label="Do not correct bases with quality above this value."/>
                    <param argument="meo" type="boolean" checked="false" label="Marks errors by reducing quality value of suspected errors; does not correct anything."/>
                    <param argument="mue" type="boolean" checked="true" label="Mark errors only on uncorrectable reads."/>
                    <param argument="overlap" type="boolean" checked="false" label="Correct errors by read overlap."/>
                </when>
            </conditional>
        </section>
        <section name="output_options" title="Output options">
            <param name="save_discarded_reads" type="boolean" checked="false" label="Save the reads that were eliminated from the input datasets to the history"/>
            <param name="save_kmer_hists" type="boolean" checked="false" label="Save the kmer histograms (in tabular format) for the input and output datasets to the history"/>
        </section>
    </inputs>

    </outputs>
    <tests>
        <!-- Single end sequencing -->
        <test expect_num_outputs="1">
            <param name="input_type" value="single_end"/>
            <param name="read1" value="bbnorm/input_R1.fastq" ftype="fastqsanger"/>
            <param name="target" value="4"/>
            <section name="norm_params">
                <param name="deterministic" value="true"/>
                <param name="mindepth" value="0"/>
            </section>
            <output name="output_normalised_R1" ftype="fastqsanger" value="bbnorm/normalised_R1.fastq"/>
        </test>
        <!-- Single end sequencing, compressed -->
        <test expect_num_outputs="1">
            <param name="input_type" value="single_end"/>
            <param name="read1" value="bbnorm/input_R1.fastq.gz" ftype="fastqsanger.gz"/>
            <param name="target" value="4"/>
            <section name="norm_params">
                <param name="deterministic" value="true"/>
                <param name="mindepth" value="0"/>
            </section>
            <output name="output_normalised_R1" ftype="fastqsanger.gz" value="bbnorm/normalised_R1.fastq"/>
        </test>
        <!-- PE as an interleaved file -->
        <test expect_num_outputs="4">
            <param name="input_type" value="PE_1file"/>
            <param name="read1" value="bbnorm/input_interleaved.fastq" ftype="fastqsanger"/>
            <param name="target" value="4"/>
            <section name="norm_params">
                <param name="deterministic" value="true"/>
                <param name="mindepth" value="0"/>
            </section>

            <output name="kmer_hist_output" ftype="tabular" file="bbnorm/kmer_hist_output.tabular"/>
        </test>
        <!-- PE as 2 files -->
        <test expect_num_outputs="2">
            <param name="input_type" value="PE_2files"/>
            <param name="read1" value="bbnorm/input_R1.fastq" ftype="fastqsanger"/>
            <param name="read2" value="bbnorm/input_R2.fastq" ftype="fastqsanger"/>
            <param name="target" value="4"/>
            <section name="norm_params">
                <param name="deterministic" value="true"/>
                <param name="mindepth" value="0"/>
            </section>

* The sequencing platform has a very high error rate (ex: ONT) that might mislead this algorithm.

    </help>
    <expand macro="citations"/>
</tool>