Mercurial > repos > malex > gait_gm

comparison split_wide_dataset.xml @ 2:2c218a253d56 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
author malex
date Thu, 29 Jul 2021 20:48:10 +0000
parents ec9ee8edb84d
children
comparison
equal deleted inserted replaced
1:ec9ee8edb84d 2:2c218a253d56
1 <tool id="secimtools_split_input_wide_dataset" name="Create: Design, Wide, and Annotation datasets" version="@WRAPPER_VERSION@"> 1 <tool id="secimtools_split_input_wide_dataset" name="Create: Design, Wide, and Annotation datasets" version="@WRAPPER_VERSION@">
2 <description>from an Input wide dataset</description> 2 <description>from an input wide dataset</description>
3 <macros> 3 <macros>
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="requirements" /> 6 <expand macro="requirements" />
7 <stdio> 7 <stdio>
8 <exit_code range="1" level="fatal" description="Repeated Unique IDs"/> 8 <exit_code range="1" level="fatal" description="Repeated Unique IDs"/>
9 </stdio> 9 </stdio>
10 <command detect_errors="exit_code"><![CDATA[ 10 <command detect_errors="exit_code"><![CDATA[
11 split_wide_dataset.py 11 split_wide_dataset.py
12 -i=$input 12 -i=$input
13 #if $cond_UniqID.hasUniqID == "y": 13 #if $cond_UniqID.hasUniqID == "y":
14 -id=$cond_UniqID.uniqID 14 -id=$cond_UniqID.uniqID
38 <option value="n">No</option> 38 <option value="n">No</option>
39 </param> 39 </param>
40 <when value="y"> 40 <when value="y">
41 <param name="prefix2" type="text" size="30" value="" label="Prefix to use during generation of unique IDs" help="This prefix will be prepended to your NUMERIC unique FeatureID, with an underbar in between."/> 41 <param name="prefix2" type="text" size="30" value="" label="Prefix to use during generation of unique IDs" help="This prefix will be prepended to your NUMERIC unique FeatureID, with an underbar in between."/>
42 </when> 42 </when>
43 <when value="n" />
43 </conditional> 44 </conditional>
44 </when> 45 </when>
45 <when value="n"> 46 <when value="n">
46 <param name="prefix" type="text" size="30" value="" label="Prefix to use during generation of unique IDs" help="Unique IDs are required. You can input a prefix for the tool to use when creating a unique identifier (Optional). If you chose not to use a prefix, the tool-created uniqueID will be an underbar followed by a number."/> 47 <param name="prefix" type="text" size="30" value="" label="Prefix to use during generation of unique IDs" help="Unique IDs are required. You can input a prefix for the tool to use when creating a unique identifier (Optional). If you chose not to use a prefix, the tool-created uniqueID will be an underbar followed by a number."/>
47 </when> 48 </when>
53 <data format="tabular" name="design" label="${tool.name} on ${on_string}: Design Dataset"/> 54 <data format="tabular" name="design" label="${tool.name} on ${on_string}: Design Dataset"/>
54 <data format="tabular" name="annot" label="${tool.name} on ${on_string}: Annotation Dataset"/> 55 <data format="tabular" name="annot" label="${tool.name} on ${on_string}: Annotation Dataset"/>
55 </outputs> 56 </outputs>
56 <tests> 57 <tests>
57 <test> 58 <test>
58 <param name="input" value="gene_input_dataset_01fhl.tsv"/> 59 <param name="input" value="gene_input_dataset.tsv"/>
59 <param name="prefix" value="Gene"/> 60 <param name="prefix" value="Gene"/>
61 <param name="hasUniqID" value="n"/>
60 <param name="samples" value="2,3,4,5,6,7,8,9,10,11"/> 62 <param name="samples" value="2,3,4,5,6,7,8,9,10,11"/>
61 <output name="wide" file="gene_wide_dataset_01fhl.tsv"/> 63 <output name="wide" file="gene_wide_dataset.tsv"/>
62 <output name="design" file="gene_design_file_01fhl.tsv"/> 64 <output name="design" file="gene_design.tsv"/>
63 <output name="annot" file="gene_annot_file_01fhl.tsv"/> 65 <output name="annot" file="gene_annotation.tsv"/>
64 </test> 66 </test>
65 <test> 67 <test>
66 <param name="input" value="metabolite_input_dataset_01fhl.tsv"/> 68 <param name="input" value="metabolite_input_dataset.tsv"/>
67 <param name="prefix" value="Met"/> 69 <param name="prefix" value="Met"/>
70 <param name="hasUniqID" value="n"/>
68 <param name="samples" value="2,3,4,5,6,7,8,9,10,11"/> 71 <param name="samples" value="2,3,4,5,6,7,8,9,10,11"/>
69 <output name="wide" file="metabolite_wide_dataset_01fhl.tsv"/> 72 <output name="wide" file="metabolite_wide_dataset.tsv"/>
70 <output name="design" file="met_design_file_01fhl.tsv"/> 73 <output name="design" file="metabolite_design.tsv"/>
71 <output name="annot" file="met_annot_file_01fhl.tsv"/> 74 <output name="annot" file="metabolite_annotation.tsv"/>
72 </test> 75 </test>
73 </tests> 76 </tests>
74 <help><![CDATA[ 77 <help><![CDATA[
75 78
76 **Tool Description** 79 **Tool Description**
77 80
78 This tool can be used to perform two tasks 1) convert a single file that contains 81 This tool takes a single file containing both feature data (e.g. gene or metabolite expression values) and annotation
79 data and annotation in wide format to two files in wide format, one with data and 82 information (e.g. m/z ratio, compound name) and generates the following three files;
80 one with annotation 2) create a design file template that will be compatible with 83
81 the wide data and annotation files. The tool will automatically check for a column 84 (1) a wide dataset containing a unique row identifier and the expression values,
82 containing unique feature identifiers (FeatureIDs). If no unique FeatureID is located 85 (2) a wide annotation file with the unique row identifier and any non-data descriptor columns, and
83 the tool will generate one. The user can specify a prefix for the unique FeatureID 86 (3) a design file with a single column called ‘sampleID’ with the name of the columns containing the expression data.
84 (e.g. 'met' for metabolite data). The Design Dataset is a template with an exact 87
85 match to the columns with a single column called 'SampleID' that contains the names 88 If the input dataset does not already contain a column with a unique identifier, the tool will create one.
86 of the samples in the input Wide Dataset. This Design Dataset can be modified by 89 The user can specify a prefix for the unique identifier column (e.g. 'met' for metabolite data). In cases where the input
87 the user to include metadata columns. The tool also creates a separate Annotation 90 dataset contains a numeric identifier, the tool will append a user-specified prefix or, if no prefix is specified, an underbar.
88 Dataset containing the unique FeatureIDs (user-specified or generated by the tool) 91 Since the user specifies which columns contain expression values, the resulting wide dataset contains only these data columns
89 and any non-sample descriptor columns that were present in the input wide dataset 92 and the unique row identifier column. Columns not specified as containing expression values are output into the annotation dataset.
90 (such as m/z ratio, retention time, compound name, etc.). Finally, the tool creates 93 The resulting design file template contains a single column called ‘sampleID’ that contains the names of the user-specified samples
91 a 'clean' Wide Dataset containing only samples in columns and features in rows. 94 in the input data file. The design file can be modified by the user to include additional metadata columns.
92 95
93 -------------------------------------------------------------------------------- 96 --------------------------------------------------------------------------------
94 97
95 **INPUT** 98 **INPUT**
96 99
108 | 4 | 8.594 | 17 | 8 | ... | 111 | 4 | 8.594 | 17 | 8 | ... |
109 +---------+-----------+---------+---------+-----+ 112 +---------+-----------+---------+---------+-----+
110 | ... | ... | ... | ... | ... | 113 | ... | ... | ... | ... | ... |
111 +---------+-----------+---------+---------+-----+ 114 +---------+-----------+---------+---------+-----+
112 115
113 **NOTE:** The input dataset has features in rows and samples in columns. Any descriptor columns that are present will be used to populate the Annotation File. 116 **NOTE:** The input dataset has features in rows and samples in columns. Any descriptor columns that are present will be used to populate the Annotation File.
114 117
115 **Unique FeatureID** 118 **Unique FeatureID**
116 119
117 If the Input Dataset has a column with unique FeatureIDs, the user can specify the name of this column. If the Input Dataset does not have a column with unique FeatureIDs, the tool will create a numeric one. 120 If the Input Dataset has a column with unique FeatureIDs, the user can specify the name of this column. If the Input Dataset does not have a column with unique FeatureIDs, the tool will create a numeric one.
118 121