|
1
|
1 <tool id="secimtools_ensembl2symbol" name="Map ENSEMBLIDs to Gene Symbols." version="@WRAPPER_VERSION@">
|
|
|
2 <description></description>
|
|
|
3 <macros>
|
|
|
4 <import>macros.xml</import>
|
|
|
5 </macros>
|
|
|
6 <expand macro="requirements" />
|
|
|
7 <stdio>
|
|
|
8 <exit_code range="1" level="fatal" description="Repeated Unique IDs"/>
|
|
|
9 </stdio>
|
|
|
10 <command detect_errors="exit_code"><![CDATA[
|
|
|
11 ensembl2symbol.py
|
|
|
12 -s=$species
|
|
|
13 -ga=$geneAnnot
|
|
|
14 -id=$uniqId
|
|
|
15 -e=$ensemblId
|
|
|
16 -o=$output
|
|
|
17 ]]></command>
|
|
|
18 <inputs>
|
|
|
19 <param name="species" type="select" label="Select the species your ENSEMBLIDs are from" >
|
|
|
20 <option value="human">Homo sapiens</option>
|
|
|
21 <option value="mouse">Mus musculus</option>
|
|
|
22 <option value="rat">Rattus norvegicus</option>
|
|
|
23 <option value="fruitfly">Drosophila melanogaster</option>
|
|
|
24 </param>
|
|
|
25 <param name="geneAnnot" type="data" format="tabular" label="Select the Dataset from your History containing the ENSEMBLIDs"/>
|
|
|
26 <param name="uniqId" type="text" size="30" value="" label="Unique Gene FeatureID" help="Name of the column in your dataset containing unique FeatureIDs."/>
|
|
|
27 <param name="ensemblId" type="text" size="30" value="" label="ENSEMBLID" help="Name of the column containing the ENSEMBLIDs to use for linking to gene symbols."/>
|
|
|
28 </inputs>
|
|
|
29 <outputs>
|
|
|
30 <data format="tabular" name="output" label="${tool.name} on ${on_string}: ENSEMBL to GeneSymbol Annotation File"/>
|
|
|
31 </outputs>
|
|
|
32 <tests>
|
|
|
33 <test>
|
|
|
34 <param name="species" value="rat"/>
|
|
|
35 <param name="geneAnnot" value="gene_annotation_file_01fhl.tsv"/>
|
|
|
36 <param name="uniqId" value="UniqueID"/>
|
|
|
37 <param name="ensemblId" value="GeneName"/>
|
|
|
38 <param name="Output" value="ensembl2symbol_annotation_file_01fhl.tsv"/>
|
|
|
39 </test>
|
|
|
40 </tests>
|
|
|
41 <help><![CDATA[
|
|
|
42
|
|
|
43 **Tool Description**
|
|
|
44
|
|
|
45 This tool takes a dataset containing unique FeatureIDs and ENSEMBLIDs and provides gene symbols. The link from the ENSEMBLIDs to gene symbols is made using Biomart. The tool adds the following columns to the input dataset: GeneSymbol, Score, Selected, and Tie. The GeneSymbol column contains the short identifiers (typically 3 letter abbreviations) of the gene name. The Score column contains a value that represents how well the ENSEMBLID matched the returned GeneSymbol using the PyPi package Gene 3.0.0 (https://www.ncbi.nlm.nih.gov/pubmed/23175613). The Selected column = 'Yes' when an ENSEMBLID uniquely matches a GeneSymbol or when that row has the highest Score value. The Selected column = 'No' in the absence of a unique match for rows lower than the maximum score. If there is a tie in the Score the alphabetically first value is selected and the Tie column has a value of Yes. We note that FeatureID may not be unique in the resulting output dataset.
|
|
|
46
|
|
|
47 --------------------------------------------------------------------------------
|
|
|
48
|
|
|
49 **INPUT**
|
|
|
50
|
|
|
51 **Dataset with unique FeatureIDs and ENSEMBLIDs**
|
|
|
52
|
|
|
53 +-------------+--------------+-----+
|
|
|
54 | FeatureID | ENSEMBLID | ... |
|
|
|
55 +=============+==============+=====+
|
|
|
56 | FeatureID_1 | ENS... | ... |
|
|
|
57 +-------------+--------------+-----+
|
|
|
58 | FeatureID_2 | ENS... | ... |
|
|
|
59 +-------------+--------------+-----+
|
|
|
60 | FeatureID_3 | ENS... | ... |
|
|
|
61 +-------------+--------------+-----+
|
|
|
62 | ... | ... | ... |
|
|
|
63 +-------------+--------------+-----+
|
|
|
64
|
|
|
65 **NOTE:** This file must contain at least two columns, a column with unique FeatureIDs and a column containing ENSEMBLIDs. Other columns may be present.
|
|
|
66
|
|
|
67 **Unique FeatureID**
|
|
|
68
|
|
|
69 Name of the column in your input dataset that has unique FeatureIDs.
|
|
|
70
|
|
|
71 **ENSEMBLID**
|
|
|
72
|
|
|
73 Name of the column containing the ENSEMBLIDs.
|
|
|
74
|
|
|
75 --------------------------------------------------------------------------------
|
|
|
76
|
|
|
77 **OUTPUT**
|
|
|
78
|
|
|
79 The user will get a single output file.
|
|
|
80
|
|
|
81 **Output Table**
|
|
|
82
|
|
|
83 +------------+------------+--------------+-------------+-----------+----------+
|
|
|
84 | FeatureID | ENSEMBLID | ... | GeneSymbol | Score | Selected |
|
|
|
85 +============+============+==============+=============+===========+==========+
|
|
|
86 | FeatureID_1 | ENS... | ... | one* | 13.550056 | Yes |
|
|
|
87 +------------+------------+--------------+-------------+-----------+----------+
|
|
|
88 | FeatureID_2 | ENS... | ... | two* | 12.984067 | Yes |
|
|
|
89 +------------+------------+--------------+-------------+-----------+----------+
|
|
|
90 | FeatureID_2 | ENS... | ... | three* | 11.995048 | No |
|
|
|
91 +------------+------------+--------------+-------------+-----------+----------+
|
|
|
92 | FeatureID_3 | ENS... | ... | four* | 12.549084 | Yes |
|
|
|
93 +------------+------------+--------------+-------------+-----------+----------+
|
|
|
94 | ... | ... | ... | ... | ... | ... |
|
|
|
95 +------------+------------+--------------+-------------+-----------+----------+
|
|
|
96
|
|
|
97 ]]>
|
|
|
98 </help>
|
|
|
99 <citations>
|
|
|
100 <citation type="bibtex">@article{wu2014mygene,
|
|
|
101 title={MyGene. info: gene annotation query as a service},
|
|
|
102 author={Wu, Chunlei and Mark, Adam and Su, Andrew I},
|
|
|
103 journal={bioRxiv},
|
|
|
104 pages={009332},
|
|
|
105 year={2014},
|
|
|
106 publisher={Cold Spring Harbor Laboratory}
|
|
|
107 }</citation>
|
|
|
108 <citation type="bibtex">@ARTICLE{Kirpich17secimtools,
|
|
|
109 author = {Alexander S. Kirpich, Miguel Ibarra, Oleksandr Moskalenko, Justin M. Fear, Joseph Gerken, Xinlei Mi, Ali Ashrafi, Alison M. Morse, Lauren M. McIntyre},
|
|
|
110 title = {SECIMTools: A suite of Metabolomics Data Analysis Tools},
|
|
|
111 journal = {BMC Bioinformatics},
|
|
|
112 year = {in press}
|
|
|
113 }</citation>
|
|
|
114 <citation type="bibtex">
|
|
|
115 @article{garcia2010paintomics,
|
|
|
116 title={Paintomics: a web based tool for the joint visualization of transcriptomics and metabolomics data},
|
|
|
117 author={Garc{\'\i}a-Alcalde, Fernando and Garc{\'\i}a-L{\'o}pez, Federico and Dopazo, Joaqu{\'\i}n and Conesa, Ana},
|
|
|
118 journal={Bioinformatics},
|
|
|
119 volume={27},
|
|
|
120 number={1},
|
|
|
121 pages={137--139},
|
|
|
122 year={2010},
|
|
|
123 publisher={Oxford University Press}
|
|
|
124 }</citation>
|
|
|
125 </citations>
|
|
|
126 </tool>
|
