|
0
|
1 <tool id="Interval_Maf_Merged_Fasta2" name="Stitch MAF blocks" version="1.0.1">
|
|
|
2 <description>given a set of genomic intervals</description>
|
|
|
3 <command interpreter="python">
|
|
|
4 #if $maf_source_type.maf_source == "user" #interval_maf_to_merged_fasta.py --dbkey=$dbkey --species=$maf_source_type.species --mafSource=$maf_source_type.maf_file --mafIndex=$maf_source_type.maf_file.metadata.maf_index --interval_file=$input1 --output_file=$out_file1 --chromCol=${input1.metadata.chromCol} --startCol=${input1.metadata.startCol} --endCol=${input1.metadata.endCol} --strandCol=${input1.metadata.strandCol} --mafSourceType=$maf_source_type.maf_source --mafIndexFileDir=${GALAXY_DATA_INDEX_DIR}
|
|
|
5 #else #interval_maf_to_merged_fasta.py --dbkey=$dbkey --species=$maf_source_type.species --mafSource=$maf_source_type.maf_identifier --interval_file=$input1 --output_file=$out_file1 --chromCol=${input1.metadata.chromCol} --startCol=${input1.metadata.startCol} --endCol=${input1.metadata.endCol} --strandCol=${input1.metadata.strandCol} --mafSourceType=$maf_source_type.maf_source --mafIndexFileDir=${GALAXY_DATA_INDEX_DIR}
|
|
|
6 #end if# --overwrite_with_gaps=$overwrite_with_gaps
|
|
|
7 </command>
|
|
|
8 <inputs>
|
|
|
9 <page>
|
|
|
10 <param format="interval" name="input1" type="data" label="Choose intervals">
|
|
|
11 <validator type="unspecified_build" />
|
|
|
12 </param>
|
|
|
13 <conditional name="maf_source_type">
|
|
|
14 <param name="maf_source" type="select" label="MAF Source">
|
|
|
15 <option value="cached" selected="true">Locally Cached Alignments</option>
|
|
|
16 <option value="user">Alignments in Your History</option>
|
|
|
17 </param>
|
|
|
18 <when value="user">
|
|
|
19 <param name="maf_file" type="data" format="maf" label="MAF File">
|
|
|
20 <options>
|
|
|
21 <filter type="data_meta" ref="input1" key="dbkey" />
|
|
|
22 </options>
|
|
|
23 <validator type="dataset_ok_validator" />
|
|
|
24 </param>
|
|
|
25 <param name="species" type="select" display="checkboxes" multiple="true" label="Choose species" help="Select species to be included in the final alignment">
|
|
|
26 <options>
|
|
|
27 <filter type="data_meta" ref="maf_file" key="species" />
|
|
|
28 </options>
|
|
|
29 </param>
|
|
|
30 </when>
|
|
|
31 <when value="cached">
|
|
|
32 <param name="maf_identifier" type="select" label="MAF Type" >
|
|
|
33 <options from_file="maf_index.loc">
|
|
|
34 <column name="name" index="0"/>
|
|
|
35 <column name="value" index="1"/>
|
|
|
36 <column name="dbkey" index="2"/>
|
|
|
37 <column name="species" index="3"/>
|
|
|
38 <filter type="data_meta" ref="input1" key="dbkey" column="2" multiple="True" separator=","/>
|
|
|
39 <validator type="no_options" message="No alignments are available for the build associated with the selected interval file"/>
|
|
|
40 </options>
|
|
|
41 </param>
|
|
|
42 <param name="species" type="select" display="checkboxes" multiple="true" label="Choose species" help="Select species to be included in the final alignment">
|
|
|
43 <options from_file="maf_index.loc">
|
|
|
44 <column name="uid" index="1"/>
|
|
|
45 <column name="value" index="3"/>
|
|
|
46 <column name="name" index="3"/>
|
|
|
47 <filter type="param_value" ref="maf_identifier" name="uid" column="1"/>
|
|
|
48 <filter type="multiple_splitter" column="3" separator=","/>
|
|
|
49 </options>
|
|
|
50 </param>
|
|
|
51 </when>
|
|
|
52 </conditional>
|
|
|
53 <param name="overwrite_with_gaps" type="select" label="Split into Gapless MAF blocks" help="When set to Yes, blocks are divided around gaps appearing in any species. This will prevent gaps occurring in the interior of the sequence for an aligning species from overwriting a nucleotide found for the same position in a lower-scoring block.">
|
|
|
54 <option value="True" selected="true">No</option>
|
|
|
55 <option value="False">Yes</option>
|
|
|
56 </param>
|
|
|
57 </page>
|
|
|
58 </inputs>
|
|
|
59 <outputs>
|
|
|
60 <data format="fasta" name="out_file1" />
|
|
|
61 </outputs>
|
|
|
62 <tests>
|
|
|
63 <test>
|
|
|
64 <param name="input1" value="13.bed" dbkey="hg18" ftype="bed"/>
|
|
|
65 <param name="maf_source" value="cached"/>
|
|
|
66 <param name="maf_identifier" value="17_WAY_MULTIZ_hg18"/>
|
|
|
67 <param name="species" value="hg18,mm8"/>
|
|
|
68 <param name="overwrite_with_gaps" value="True"/>
|
|
|
69 <output name="out_file1" file="interval_maf_to_merged_fasta_out3.fasta" />
|
|
|
70 </test>
|
|
|
71 <test>
|
|
|
72 <param name="input1" value="1.bed" dbkey="hg17" ftype="bed"/>
|
|
|
73 <param name="maf_source" value="cached"/>
|
|
|
74 <param name="maf_identifier" value="8_WAY_MULTIZ_hg17"/>
|
|
|
75 <param name="species" value="canFam1,hg17,mm5,panTro1,rn3"/>
|
|
|
76 <param name="overwrite_with_gaps" value="True"/>
|
|
|
77 <output name="out_file1" file="interval_maf_to_merged_fasta_out.dat" />
|
|
|
78 </test>
|
|
|
79 <test>
|
|
|
80 <param name="input1" value="1.bed" dbkey="hg17" ftype="bed"/>
|
|
|
81 <param name="maf_source" value="user"/>
|
|
|
82 <param name="maf_file" value="5.maf"/>
|
|
|
83 <param name="species" value="canFam1,hg17,mm5,panTro1,rn3"/>
|
|
|
84 <param name="overwrite_with_gaps" value="True"/>
|
|
|
85 <output name="out_file1" file="interval_maf_to_merged_fasta_user_out.dat" />
|
|
|
86 </test>
|
|
|
87 </tests>
|
|
|
88 <help>
|
|
|
89 **What it does**
|
|
|
90
|
|
|
91 A single genomic region can be covered by multiple alignment blocks. In many cases it is desirable to stitch these alignment blocks together. This tool accepts a list of genomic intervals. For every interval it performs the following:
|
|
|
92
|
|
|
93 * finds all MAF blocks that overlap the interval;
|
|
|
94 * sorts MAF blocks by alignment score;
|
|
|
95 * stitches blocks together and resolves overlaps based on alignment score;
|
|
|
96 * outputs alignments in FASTA format.
|
|
|
97
|
|
|
98 ------
|
|
|
99
|
|
|
100 **Example**
|
|
|
101
|
|
|
102 Here three MAF blocks overlapping a single interval are stitched together. Space between blocks 2 and 3 is filled with gaps:
|
|
|
103
|
|
|
104 .. image:: ./static/images/maf_icons/stitchMaf.png
|
|
|
105
|
|
|
106 ------
|
|
|
107
|
|
|
108 **Citation**
|
|
|
109
|
|
|
110 If you use this tool, please cite `Blankenberg D, Taylor J, Nekrutenko A; The Galaxy Team. Making whole genome multiple alignments usable for biologists. Bioinformatics. 2011 Sep 1;27(17):2426-2428. <http://www.ncbi.nlm.nih.gov/pubmed/21775304>`_
|
|
|
111
|
|
|
112
|
|
|
113 </help>
|
|
|
114 </tool>
|
