Mercurial > repos > malex > gait_gm
annotate all_by_all_correlation.xml @ 2:2c218a253d56 draft default tip
"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 |
rev | line source |
---|---|
1 | 1 <tool id="allByAllCorr" name="Metabolite - Gene Correlation" version="@WRAPPER_VERSION@"> |
2 <description></description> | |
3 <macros> | |
4 <import>macros.xml</import> | |
5 </macros> | |
6 <expand macro="requirements" /> | |
7 <command detect_errors="exit_code"><![CDATA[ | |
8 all_by_all_correlation.py | |
9 -g=$geneDataset | |
10 -gid=$geneId | |
11 #if $geneAnnotation.useGeneAnnot == "Yes": | |
12 -ga=$geneAnnotation.geneAnnot | |
13 -gn=$geneAnnotation.geneAnnotName | |
14 #end if | |
15 -m=$metDataset | |
16 -mid=$metId | |
17 #if $metAnnotation.useMetAnnot == "Yes": | |
18 -ma=$metAnnotation.metAnnot | |
19 -mn=$metAnnotation.metAnnotName | |
20 #end if | |
21 -me=$method | |
22 -t=$threshold | |
23 -o=$output | |
24 -c=$corMat | |
25 -f=$figure | |
26 ]]></command> | |
27 <inputs> | |
28 <param name="geneDataset" type="data" format="tabular" label="Gene Expression Wide Dataset" help="Select the Gene Expression Wide Dataset from your history"/> | |
29 <param name="geneId" type="text" size="30" value="" label="Unique Gene FeatureID" help="Name of the Column in your Gene Expression Wide Dataset that contains unique identifiers."/> | |
30 <conditional name="geneAnnotation"> | |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
31 <param name="useGeneAnnot" type="select" label="Use Annotation File?" help="You can choose to input a file containing gene annotation information (e.g. gene names, identifiers, etc.) for labeling output files."> |
1 | 32 <option value="No">No</option> |
33 <option value="Yes">Yes</option> | |
34 </param> | |
35 <when value="Yes"> | |
36 <param name="geneAnnot" type="data" format="tabular" label="Gene Expression Annotation File" help="Select the Gene Expression Annotation File from your history"/> | |
37 <param name="geneAnnotName" type="text" value="" label="Gene Labels" help="Name of the column in the Gene Expression Annotation File to use for labeling output files."/> | |
38 </when> | |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
39 <when value="No" /> |
1 | 40 </conditional> |
41 <param name="metDataset" type="data" format="tabular" label="Metabolite Wide Dataset" help="Select the Metabolite Wide Dataset from your history"/> | |
42 <param name="metId" type="text" size="30" value="" label="Unique Metabolite FeatureID" help="Name of the column in your Metabolite Wide Dataset that contains unique identifiers."/> | |
43 <conditional name="metAnnotation"> | |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
44 <param name="useMetAnnot" type="select" label="Use Annotation File?" help="You can choose to input a file containing metabolite annotation information (e.g. metabolite names, identifiers, etc.) for labeling output files."> |
1 | 45 <option value="No">No</option> |
46 <option value="Yes">Yes</option> | |
47 </param> | |
48 <when value="Yes"> | |
49 <param name="metAnnot" type="data" format="tabular" label="Metabolite Annotation File" help="Select the Metabolite Annotation File from your history"/> | |
50 <param name="metAnnotName" type="text" value="" label="Metabolite Labels" help="Name of the column in the Metabolite Annotation File to use for labeling output files"/> | |
51 </when> | |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
52 <when value="No" /> |
1 | 53 </conditional> |
54 <param name="method" type="select" label="Correlation Method" help="Select a correlation method."> | |
55 <option value="pearson">Pearson</option> | |
56 <option value="spearman">Spearman</option> | |
57 <option value="kendall">Kendall</option> | |
58 </param> | |
59 <param name="threshold" type="text" value="0.05" label="P-Value threshold." help="Default: 0.05"/> | |
60 </inputs> | |
61 <outputs> | |
62 <data format="tabular" name="output" label="${tool.name} on ${on_string}: Correlation File"/> | |
63 <data format="tabular" name="corMat" label="${tool.name} on ${on_string}: Correlation Matrix"/> | |
64 <data format="pdf" name="figure" label="${tool.name} on ${on_string}: Correlation Figure"/> | |
65 </outputs> | |
66 <tests> | |
67 <test> | |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
68 <param name="geneDataset" value="gene_wide_dataset.tsv"/> |
1 | 69 <param name="geneId" value="UniqueID"/> |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
70 <param name="geneAnnot" value="gene_annotation.tsv"/> |
1 | 71 <param name="geneName" value="GeneName"/> |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
72 <param name="metDataset" value="metabolite_wide_dataset.tsv"/> |
1 | 73 <param name="metId" value="UniqueID"/> |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
74 <param name="metAnnot" value="metabolite_annotation.tsv"/> |
1 | 75 <param name="metName" value="MetName"/> |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
76 <output name="output" file="correlation.tsv" compare="diff" lines_diff="10000"/> |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
77 <output name="corMat" file="correlation_matrix.tsv" compare="diff" lines_diff="10000"/> |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
78 <output name="figure" file="correlation_figure.pdf" compare="sim_size" delta="1000000"/> |
1 | 79 </test> |
80 </tests> | |
81 <help><![CDATA[ | |
82 | |
83 **Tool Description** | |
84 | |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
85 The tool performs a correlation analysis between genes (Gene Expression Wide Dataset) and |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
86 metabolites (Metabolite Wide Dataset) to generate |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
87 a table of correlation coefficients. P-values for the correlation coefficients are calculated by |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
88 simulating gene and metabolite datasets 1000 times using the mean and standard deviation of both |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
89 datasets. |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
90 |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
91 The tool outputs 2 TSV files and a PDF figure. The 'correlation file' contains gene-metabolite |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
92 correlation coefficients with p-values |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
93 less than the user-specified threshold. The tool also outputs the results in matrix format, the |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
94 ‘correlation matrix file’. The ‘correlation |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
95 figure’ is a network representation of the top 500 gene-metabolite correlations based on the |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
96 absolute value of the correlation coefficients. |
1 | 97 |
98 -------------------------------------------------------------------------------- | |
99 | |
100 **Input** | |
101 | |
102 (1) **Gene Expression Dataset** A wide formatted dataset containing measurements for each sample (where samples are in columns): | |
103 | |
104 +-----------+---------+---------+---------+-----+ | |
105 | UniqueID | sample1 | sample2 | sample3 | ... | | |
106 +===========+=========+=========+=========+=====+ | |
107 | gene_1 | 1.2 | 3.5 | 2.9 | ... | | |
108 +-----------+---------+---------+---------+-----+ | |
109 | gene_2 | 1.6 | 3.2 | 3.2 | ... | | |
110 +-----------+---------+---------+---------+-----+ | |
111 | gene_3 | 1.4 | 3.0 | 3.1 | ... | | |
112 +-----------+---------+---------+---------+-----+ | |
113 | gene_4 | 1.6 | 2.9 | 3.1 | ... | | |
114 +-----------+---------+---------+---------+-----+ | |
115 | ... | ... | ... | ... | ... | | |
116 +-----------+---------+---------+---------+-----+ | |
117 | |
118 (2) **Unique Gene FeatureID** Name of the column in your Gene Expression Wide Dataset that contains unique gene identifiers. **NOTE:** This identifier must be the gene symbol. | |
119 | |
120 (3) **Metabolomic Wide Dataset** A wide formatted metabolomic dataset that contains measurements for each sample (where samples are in columns): | |
121 | |
122 +------------+---------+---------+---------+-----+ | |
123 | UniqueID | sample1 | sample2 | sample3 | ... | | |
124 +============+=========+=========+=========+=====+ | |
125 | met_1 | 10 | 20 | 10 | ... | | |
126 +------------+---------+---------+---------+-----+ | |
127 | met_2 | 5 | 22 | 30 | ... | | |
128 +------------+---------+---------+---------+-----+ | |
129 | met_3 | 30 | 27 | 2 | ... | | |
130 +------------+---------+---------+---------+-----+ | |
131 | met_4 | 32 | 17 | 8 | ... | | |
132 +------------+---------+---------+---------+-----+ | |
133 | ... | ... | ... | ... | ... | | |
134 +------------+---------+---------+---------+-----+ | |
135 | |
136 (4) **Unique Metabolite FeatureID** Name of the column in your Metabolite Wide Dataset that contains unique metabolite identifiers. | |
137 | |
138 (5) **Annotation Files** The user can provide (optional) Annotation Files for the Gene Expression and/or Metabolite Datasets to label the results for easier readability. The user must provide the name of the column with the desired feature name (e.g. Gene Symbol). | |
139 | |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
140 +-----------+--------------+-------------+-----+ |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
141 | UniqueID | ENSEMBL_ID | Gene_Symbol | ... | |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
142 +===========+==============+=============+=====+ |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
143 | gene_1 | ENS... | one | ... | |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
144 +-----------+--------------+-------------+-----+ |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
145 | gene_2 | ENS... | two | ... | |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
146 +-----------+--------------+-------------+-----+ |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
147 | gene_3 | ENS... | three | ... | |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
148 +-----------+--------------+-------------+-----+ |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
149 | gene_4 | ENS... | four | ... | |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
150 +-----------+--------------+-------------+-----+ |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
151 | ... | ... | ... | ... | |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
152 +-----------+--------------+-------------+-----+ |
1 | 153 |
154 (6) **Correlation method** Select the correlation coefficient to be computed from the list. Pearson, kendall, or spearman are available. | |
155 | |
156 (7) **P-Value threshold** User specified value that limits the data in the resulting 'Correlation File' to only those correlations with P-values less than this value. | |
157 | |
158 -------------------------------------------------------------------------------- | |
159 | |
160 **Output** | |
161 | |
162 The user will obtain three outputs from the Gene - Metabolite Correlation Tool: | |
163 | |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
164 (1) **Correlation File.** A file sorted by the absolute values of the correlation coefficient and including the P-value. The file contains only the correlation coefficients where the associated P-values is less than a user-specified value (default = 0.05). |
1 | 165 |
166 +--------+------------+-------------+-----------+ | |
167 | Gene | Metabolite | Correlation | (p-value) | | |
168 +========+============+=============+===========+ | |
169 | gene_1 | met_1 | 0.99 | 0.000 | | |
170 +--------+------------+-------------+-----------+ | |
171 | gene_2 | met_4 | -0.98 | 0.000 | | |
172 +--------+------------+-------------+-----------+ | |
173 | gene_3 | met_5 | 0.96 | 0.001 | | |
174 +--------+------------+-------------+-----------+ | |
175 | gene_4 | met_1 | 0.95 | 0.002 | | |
176 +--------+------------+-------------+-----------+ | |
177 | ... | ... | ... | ... | | |
178 +--------+------------+-------------+-----------+ | |
179 | |
180 (2) **Correlation Matrix.** Output correlation matrix. | |
181 | |
182 +--------+-------+-------+-------+-------+-----+ | |
183 | Gene | met_1 | met_2 | met_3 | met_4 | ... | | |
184 +========+=======+=======+=======+=======+=====+ | |
185 | gene_1 | 0.99 | 0.56 | 0.25 | 0.33 | ... | | |
186 +--------+-------+-------+-------+-------+-----+ | |
187 | gene_2 | -0.57 | 0.63 | -0.14 | 0.01 | ... | | |
188 +--------+-------+-------+-------+-------+-----+ | |
189 | gene_3 | 0.62 | 0.96 | 0.20 | 0.32 | ... | | |
190 +--------+-------+-------+-------+-------+-----+ | |
191 | gene_4 | 0.95 | 0.25 | 0.16 | 0.44 | ... | | |
192 +--------+-------+-------+-------+-------+-----+ | |
193 | ... | ... | ... | ... | ... | ... | | |
194 +--------+-------+-------+-------+-------+-----+ | |
195 | |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
196 (3) **Correlation Figure.** Network representation of the top 500 gene-metabolite correlations based on the absolute value of the correlation coefficients. Maximum number of correlations in the network is 500. |
1 | 197 |
198 ]]> | |
199 </help> | |
200 <citations> | |
201 <citation type="bibtex">@ARTICLE{Kirpich17secimtools, | |
202 author = {Alexander S. Kirpich, Miguel Ibarra, Oleksandr Moskalenko, Justin M. Fear, Joseph Gerken, Xinlei Mi, Ali Ashrafi, Alison M. Morse, Lauren M. McIntyre}, | |
203 title = {SECIMTools: A suite of Metabolomics Data Analysis Tools}, | |
204 journal = {BMC Bioinformatics}, | |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
205 year = {2018} |
1 | 206 }</citation> |
2
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
207 <citation type="bibtex">@article{Mor2021GaitGM, |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
208 title={GAIT-GM integrative cross-omics analyses reveal cholinergic defects in a C. elegans model of Parkinson's disease}, |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
209 author={Mor, DE and Huertas, F and Morse, AM and Kaletsky, R and Murphy, CT and Kalia, V and Miller, GW and Moskalenko, O and Conesa, A and McIntyre, LM}, |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
210 journal={BMC Genomics}, |
2c218a253d56
"planemo upload for repository https://github.com/secimTools/gait-gm/tree/main/galaxy commit 758394addb95b09e794132a23a1f7e95ba39df0b"
malex
parents:
1
diff
changeset
|
211 year={submitted}, |
1 | 212 }</citation> |
213 </citations> | |
214 </tool> |