<?xml version="1.0"?>
<tool id="hmmer_nhmmscan" name="nhmmscan" version="@WRAPPER_VERSION@.0">
  <description>search DNA sequence(s) against a DNA profile database</description>
  <macros>
    <import>macros.xml</import>
  </macros>
  <expand macro="requirements"/>
  <expand macro="stdio"/>
  <command><![CDATA[
hmmpress $hmmfile;

nhmmscan

@OFORMAT_WITH_OPTS_N@
@THRESHOLDS_NODOM@
@CUT@
@ACCEL_HEUR@
--B1 $B1
--B2 $B2
--B3 $B3

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

$hmmfile
$seqfile
> $output
      ]]></command>
  <inputs>
    <expand macro="input_hmm" />
    <!-- todo use Galaxy features like data libraries/data tables/??? -->
    <param name="seqfile" type="data" format="fasta" label="Sequence file"/>
    <expand macro="oformat_with_opts_n"/>
    <expand macro="thresholds_nodom"/>
    <expand macro="cut"/>
    <expand macro="accel_heur_xml"/>

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

    <expand macro="adv_opts"/>
    <expand macro="lengths"/>
    <expand macro="seed"/>
  </inputs>
  <outputs>
    <data format="txt" name="output" label="HMM matches of $seqfile.name in $hmmfile.name"/>

    <data format="txt" name="tblout" label="Table of per-sequence hits from HMM matches of $seqfile.name in $hmmfile.name">
      <filter>'tblout' in str(oformat)</filter>
    </data>
    <data format="txt" name="dfamtblout" label="Table of per-sequence/per-domain hits from HMM matches of $seqfile.name in $hmmfile.name">
      <filter>'pfamtblout' in str(oformat)</filter>
    </data>
    <data format="txt" name="aliscoresout" label="Scores for positional matches of $seqfile.name in $hmmfile.name">
      <filter>'aliscoresout' in str(oformat)</filter>
    </data>
  </outputs>
  <tests>
    <test>
      <param name="hmmfile" value="MADE1.hmm"/>
      <param name="seqfile" value="dna_target.fa"/>
      <expand macro="oformat_test" />
      <expand macro="seed_test" />
      <output name="output" file="MADE1.out" lines_diff="140"/>
      <output name="tblout" file="MADE1.out.tblout" lines_diff="30"/>
      <output name="domtblout" file="MADE1.out.domtblout" lines_diff="30"/>
      <output name="pfamtblout" file="MADE1.out.pfamtblout" lines_diff="36"/>
    </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>