annotate nhmmscan.xml @ 7:e7d281a290a6 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/hmmer3 commit 061757dd7b3bfe66b7738fd54bd6c5e135d9afe8

<?xml version="1.0"?>
<tool id="hmmer_nhmmscan" name="nhmmscan" version="@TOOL_VERSION@+galaxy1">
  <description>search DNA sequence(s) against a DNA profile database</description>
  <macros>
    <import>macros.xml</import>
  </macros>
  <expand macro="bio_tools"/>
  <expand macro="requirements"/>
  <expand macro="stdio"/>
  <command><![CDATA[
@ADDTHREADS@
@INPUTHMMCHOICE@
nhmmscan

@OFORMAT_WITH_OPTS@
@THRESHOLDS@
@ACCEL_HEUR@
--B1 $B1
--B2 $B2
--B3 $B3

@ADV_OPTS@
@LENGTHS@
@CPU@
@SEED@

'$input_hmm_filename'
'$seqfile'
> '$output'
  ]]></command>
  <inputs>
    <expand macro="input_hmm_choice" />
    <!-- todo use Galaxy features like data libraries/data tables/??? -->
    <param name="seqfile" type="data" format="fasta" label="Sequence file"/>
    <expand macro="oformat_with_opts_dfam_alisc"/>
    <expand macro="thresholds_cut_xml"/>
    <expand macro="accel_heur_xml"/>

    <param argument="--B1" type="integer" value="110" label="window length for biased-composition modifier (MSV)" />
    <param argument="--B2" type="integer" value="240" label="window length for biased-composition modifier (Vit)" />
    <param argument="--B3" type="integer" value="1000" label="window length for biased-composition modifier (Fwd)" />

    <expand macro="adv_opts"/>
    <expand macro="lengths"/>
    <expand macro="seed"/>
  </inputs>
  <outputs>
    <expand macro="output_dfam_alisc" tool="NHMMSCAN"/>
  </outputs>
  <tests>
    <test expect_num_outputs="3">
      <param name="input_hmm_conditional|input_hmm_source" value="history"/>
      <param name="input_hmm_conditional|hmmfile" value="MADE1.hmm"/>
      <param name="seqfile" value="dna_target.fa"/>
      <expand macro="oformat_test" />
      <expand macro="seed_test" />
      <output name="output" file="MADE1.nhmmscan_out" lines_diff="12">
          <expand macro="assert_out" tool="nhmmscan"/>
      </output>
      <output name="tblout" file="MADE1.nhmmscan_out.tblout" lines_diff="10">
          <!-- nhmmscan reports as hmmscan https://github.com/EddyRivasLab/hmmer/issues/190 -->
          <expand macro="assert_tblout" tool="nhmmscan"/>
      </output>
      <output name="dfamtblout" file="MADE1.nhmmscan_out.dfamtblout">
          <assert_contents>
              <has_line_matching expression="# hit scores"/>
          </assert_contents>
      </output>
      <!--not test because https://github.com/EddyRivasLab/hmmer/issues/190 <output name="aliscoresout" file="MADE1.nhmmscan_out.aliscoresout" lines_diff="10" />-->
    </test>
  </tests>
  <help><![CDATA[
@HELP_PRE@

nhmmscan is used to search nucleotide sequences against collections of
nucleotide profiles. For each sequence in <seqfile>, use that query sequence to
search the target database of profiles in <hmmfile>, and output ranked lists of
the profiles with the most significant matches to the sequence.

The <seqfile> may contain more than one query sequence. It can be in FASTA
format, or several other common sequence file formats (genbank, embl, and
uniprot, among others), or in alignment file formats (stockholm, aligned fasta,
and others). See the --qformat option for a complete list.

@HELP_PRE_OTH@

@OFORMAT_WITH_OPTS_N_HELP@
@THRESHOLDS_NODOM_HELP@
@CUT_HELP@
@ACCEL_HEUR_HELP@
@BIAS_COMP_HELP@
@ADV_OPTS_HELP@
@LENGTHS_HELP@
@SEED_HELP@


@ATTRIBUTION@
]]></help>
  <expand macro="citation"/>
</tool>