comparison mafft.xml @ 14:6f28e90db932 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/mafft commit 1570f3a28232b4b88385cdfbb68f79d80ff1dabb

13:a65296ffb4a0

<?xml version="1.0" encoding="UTF-8"?>
<tool id="rbc_mafft" name="MAFFT" version="@TOOL_VERSION@+galaxy@VERSION@">
  <description>Multiple alignment program for amino acid or nucleotide sequences</description>
  <macros>
    <import>macros.xml</import>
  </macros>
  <expand macro="requirements" />
  <stdio>
    <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error" />
    <exit_code range=":-1" level="fatal" description="Error occurred. Please check Tool Standard Error" />
  </stdio>

      <param name="inputSequences" value="sample.fa"/>
      <param name="flavourType" value="mafft-nwns"/>
      <param name="outputFormat" value="--clustalout"/>
      <output name="outputAlignment" ftype="clustal" file="mafft_nwns_result.aln" lines_diff="2" />
    </test>
    <test expect_num_outputs="1" >
      <param name="inputSequences" value="sample.fa"/>
      <param name="flavourType" value="custom"/>
      <param name="matrix_condition" value="BLOSUM"/>
      <param name="BLOSUM" value="62"/>
      <param name="distance_method" value="--fastapair"/>
      <param name="weighti" value="2.7"/>
      <param name="iterations" value="1000"/>
      <param name="outputFormat" value="--clustalout"/>
      <output name="outputAlignment" ftype="clustal" file="mafft_custom_result.aln" lines_diff="2" />
    </test>
  </tests>
  <help>    <![CDATA[
      **What it does**
      MAFFT is a multiple sequence alignment program for unix-like operating systems.
      It offers a range of multiple alignment methods, L-INS-i (accurate; for alignment of <∼200 sequences),
      FFT-NS-2 (fast; for alignment of <∼30,000 sequences), etc.
      From the MAFFT man page, an overview of the different predefined flavours of the tool.
      **Accuracy-oriented methods:**
      - L-INS-i (probably most accurate; recommended for <200 sequences; iterative refinement method incorporating local pairwise alignment information):
      - mafft --localpair --maxiterate 1000 input [> output]
      - G-INS-i (suitable for sequences of similar lengths; recommended for <200 sequences; iterative refinement method incorporating global pairwise alignment information):
      - mafft --globalpair --maxiterate 1000 input [> output]
      - E-INS-i (suitable for sequences containing large unalignable regions; recommended for <200 sequences):
      - mafft --ep 0 --genafpair --maxiterate 1000 input [> output]. For E-INS-i, the --ep 0 option is recommended to allow large gaps.
      **Speed-oriented methods:**
      - FFT-NS-i (iterative refinement method; two cycles only):
      - mafft --retree 2 --maxiterate 2 input [> output]
      - FFT-NS-i (iterative refinement method; max. 1000 iterations):
      - mafft --retree 2 --maxiterate 1000 input [> output]
      - FFT-NS-2 (fast; progressive method):

      - mafft --retree 2 --maxiterate 0 --nofft input [> output]
      - NW-NS-PartTree-1 (recommended for ~10,000 to ~50,000 sequences; progressive method with the PartTree algorithm):
      - mafft --retree 1 --maxiterate 0 --nofft --parttree input [> output]

      **Options:**
      --auto
      Automatically selects an appropriate strategy from L-INS-i, FFT-NS-i and FFT-NS-2, according to data size. Default: off (always FFT-NS-2)
      --adjustdirection
      Generate reverse complement sequences, as necessary, and align them together with the remaining sequences. In the case of protein alignment, these options are just ignored.
      --op
      Gap opening penalty, default: 1.53
      --ep
      Offset (works like gap extension penalty), default: 0.0
      --maxiterate
      Maximum number of iterative refinement, default: 0
      --clustalout
      Output: clustal format, default: fasta
      --thread
      Number of threads (if unsure, --thread -1)
      --retree number
      Guide tree is built number times in the progressive stage.
      Valid with 6mer distance.  Default: 2
      ]]>
    </help>
  <expand macro="citations" />
</tool>

14:6f28e90db932

<?xml version="1.0" encoding="UTF-8"?>
<tool id="rbc_mafft" name="MAFFT" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
<description>Multiple alignment program for amino acid or nucleotide sequences</description>
  <macros>
    <import>macros.xml</import>
  </macros>
  <expand macro="biotools"/>
  <expand macro="requirements" />
  <stdio>
    <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error" />
    <exit_code range=":-1" level="fatal" description="Error occurred. Please check Tool Standard Error" />
  </stdio>

      <param name="inputSequences" value="sample.fa"/>
      <param name="flavourType" value="mafft-nwns"/>
      <param name="outputFormat" value="--clustalout"/>
      <output name="outputAlignment" ftype="clustal" file="mafft_nwns_result.aln" lines_diff="2" />
    </test>
    <!-- WARNING: the results of the following test depends on #threads.
    The result seems deterministic for single threaded execution, i.e. GALAXY_SLOTS=1 planemo test
    However, GH CI/CD uses 2 threads and results vary -->
    <test expect_num_outputs="1" >
      <param name="inputSequences" value="sample.fa"/>
      <param name="flavourType" value="custom"/>
      <conditional name="matrix_condition">
        <param name="matrix" value="BLOSUM"/>
      </conditional>
      <param name="BLOSUM" value="62"/>
      <param name="distance_method" value="--fastapair"/>
      <param name="weighti" value="2.7"/>
      <param name="iterations" value="1000"/>
      <param name="outputFormat" value="--clustalout"/>
      <output name="outputAlignment" ftype="clustal" file="mafft_custom_result.aln" compare="sim_size">
        <assert_contents>
          <has_n_lines n="458" delta="0"/>
          <has_text text="CLUSTAL format alignment by MAFFT F-INS-i"/>
          <has_text text="NPIVYGISHPKY"/>
          <has_text text="1=="/>
          <has_text text="36=="/>
          <has_line line="8=opsin,        ------------------------------------------------------------"/>
        </assert_contents>
      </output>
    </test>
  </tests>
  <help>    <![CDATA[
      **What it does**

      MAFFT is a multiple sequence alignment program for unix-like operating systems.
      It offers a range of multiple alignment methods, L-INS-i (accurate; for alignment of <∼200 sequences),
      FFT-NS-2 (fast; for alignment of <∼30,000 sequences), etc.
      From the MAFFT man page, an overview of the different predefined flavours of the tool is as follows:

      **Accuracy-oriented methods:**

      - L-INS-i (probably most accurate; recommended for <200 sequences; iterative refinement method incorporating local pairwise alignment information):
      - mafft --localpair --maxiterate 1000 input [> output]
      - G-INS-i (suitable for sequences of similar lengths; recommended for <200 sequences; iterative refinement method incorporating global pairwise alignment information):
      - mafft --globalpair --maxiterate 1000 input [> output]
      - E-INS-i (suitable for sequences containing large unalignable regions; recommended for <200 sequences):
      - mafft --ep 0 --genafpair --maxiterate 1000 input [> output]. For E-INS-i, the --ep 0 option is recommended to allow large gaps.

      **Speed-oriented methods:**

      - FFT-NS-i (iterative refinement method; two cycles only):
      - mafft --retree 2 --maxiterate 2 input [> output]
      - FFT-NS-i (iterative refinement method; max. 1000 iterations):
      - mafft --retree 2 --maxiterate 1000 input [> output]
      - FFT-NS-2 (fast; progressive method):

      - mafft --retree 2 --maxiterate 0 --nofft input [> output]
      - NW-NS-PartTree-1 (recommended for ~10,000 to ~50,000 sequences; progressive method with the PartTree algorithm):
      - mafft --retree 1 --maxiterate 0 --nofft --parttree input [> output]

      **Options:**

      - --auto Automatically selects an appropriate strategy from L-INS-i, FFT-NS-i and FFT-NS-2, according to data size. Default: off (always FFT-NS-2)
      - --adjustdirection Generate reverse complement sequences, as necessary, and align them together with the remaining sequences. In the case of protein alignment, these options are just ignored.
      - --op Gap opening penalty, default: 1.53
      - --ep Offset (works like gap extension penalty), default: 0.0
      - --maxiterate Maximum number of iterative refinement, default: 0
      - --clustalout Output: clustal format, default: fasta
      - --retree number Guide tree is built number times in the progressive stage. Valid with 6mer distance. Default: 2
      ]]>
    </help>
  <expand macro="citations" />
</tool>