Mercurial > repos > malex > gait_gm
diff 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 |
line wrap: on
line diff
--- a/all_by_all_correlation.xml Fri Jun 18 20:23:19 2021 +0000 +++ b/all_by_all_correlation.xml Thu Jul 29 20:48:10 2021 +0000 @@ -28,7 +28,7 @@ <param name="geneDataset" type="data" format="tabular" label="Gene Expression Wide Dataset" help="Select the Gene Expression Wide Dataset from your history"/> <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."/> <conditional name="geneAnnotation"> - <param name="useGeneAnnot" type="select" label="Use Annotation File?" help="You can chose to input a file containing gene annotation information (e.g. gene names, identifiers, etc.) for labeling output files."> + <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."> <option value="No">No</option> <option value="Yes">Yes</option> </param> @@ -36,11 +36,12 @@ <param name="geneAnnot" type="data" format="tabular" label="Gene Expression Annotation File" help="Select the Gene Expression Annotation File from your history"/> <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."/> </when> + <when value="No" /> </conditional> <param name="metDataset" type="data" format="tabular" label="Metabolite Wide Dataset" help="Select the Metabolite Wide Dataset from your history"/> <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."/> <conditional name="metAnnotation"> - <param name="useMetAnnot" type="select" label="Use Annotation File?" help="You can chose to input a file containing metabolite annotation information (e.g. metabolite names, identifiers, etc.) for labeling output files."> + <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."> <option value="No">No</option> <option value="Yes">Yes</option> </param> @@ -48,6 +49,7 @@ <param name="metAnnot" type="data" format="tabular" label="Metabolite Annotation File" help="Select the Metabolite Annotation File from your history"/> <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"/> </when> + <when value="No" /> </conditional> <param name="method" type="select" label="Correlation Method" help="Select a correlation method."> <option value="pearson">Pearson</option> @@ -63,28 +65,35 @@ </outputs> <tests> <test> - <param name="geneDataset" value="gene_wide_dataset_01fhl.tsv"/> + <param name="geneDataset" value="gene_wide_dataset.tsv"/> <param name="geneId" value="UniqueID"/> - <param name="geneAnnot" value="gene_annotation_file_01fhl.tsv"/> + <param name="geneAnnot" value="gene_annotation.tsv"/> <param name="geneName" value="GeneName"/> - <param name="metDataset" value="metabolite_wide_dataset_01fhl.tsv"/> + <param name="metDataset" value="metabolite_wide_dataset.tsv"/> <param name="metId" value="UniqueID"/> - <param name="metAnnot" value="metabolite_annotation_file_01fhl.tsv"/> + <param name="metAnnot" value="metabolite_annotation.tsv"/> <param name="metName" value="MetName"/> - <output name="output" file="correlation_file_01fhl.tsv"/> - <output name="corMat" file="correlation_matrix_01fhl.tsv"/> - <output name="figure" file="correlation_figure_01fhl.pdf"/> + <output name="output" file="correlation.tsv" compare="diff" lines_diff="10000"/> + <output name="corMat" file="correlation_matrix.tsv" compare="diff" lines_diff="10000"/> + <output name="figure" file="correlation_figure.pdf" compare="sim_size" delta="1000000"/> </test> </tests> <help><![CDATA[ **Tool Description** - The tool performs a correlation analysis between genes (in a gene expression wide dataset) and metabolites (in a metabolite wide dataset) - to generate a table of correlation coefficients. P-values for the correlation coefficients are calculated by simulating individual gene and - metabolite datasets 1000 times using a normal distribution with means and standard deviations generated from the data. Sample size reflects - the input datasets. Correlations are calculated on the simulated data. Correlations must be higher/lower than 95% of the randomly simulated - values to be considered significant. +The tool performs a correlation analysis between genes (Gene Expression Wide Dataset) and +metabolites (Metabolite Wide Dataset) to generate +a table of correlation coefficients. P-values for the correlation coefficients are calculated by +simulating gene and metabolite datasets 1000 times using the mean and standard deviation of both +datasets. + +The tool outputs 2 TSV files and a PDF figure. The 'correlation file' contains gene-metabolite +correlation coefficients with p-values +less than the user-specified threshold. The tool also outputs the results in matrix format, the +‘correlation matrix file’. The ‘correlation +figure’ is a network representation of the top 500 gene-metabolite correlations based on the +absolute value of the correlation coefficients. -------------------------------------------------------------------------------- @@ -128,19 +137,19 @@ (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). - +-----------+------------+-------------+-----+ - | UniqueID | ENSEMBL_ID | Gene_Symbol | ... | - +===========+============+=============+=====+ - | gene_1 | ENS... | one | ... | - +-----------+------------+-------------+-----+ - | gene_2 | ENS... | two | ... | - +-----------+------------+-------------+-----+ - | gene_3 | ENS... | three | ... | - +-----------+------------+-------------+-----+ - | gene_4 | ENS... | four | ... | - +-----------+------------+-------------+-----+ - | ... | ... | ... | ... | - +-----------+------------+-------------+-----+ + +-----------+--------------+-------------+-----+ + | UniqueID | ENSEMBL_ID | Gene_Symbol | ... | + +===========+==============+=============+=====+ + | gene_1 | ENS... | one | ... | + +-----------+--------------+-------------+-----+ + | gene_2 | ENS... | two | ... | + +-----------+--------------+-------------+-----+ + | gene_3 | ENS... | three | ... | + +-----------+--------------+-------------+-----+ + | gene_4 | ENS... | four | ... | + +-----------+--------------+-------------+-----+ + | ... | ... | ... | ... | + +-----------+--------------+-------------+-----+ (6) **Correlation method** Select the correlation coefficient to be computed from the list. Pearson, kendall, or spearman are available. @@ -152,7 +161,7 @@ The user will obtain three outputs from the Gene - Metabolite Correlation Tool: - (1) **Correlation File.** A file sorted by the absolute values of the correlation coeficient 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) **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). +--------+------------+-------------+-----------+ | Gene | Metabolite | Correlation | (p-value) | @@ -184,33 +193,22 @@ | ... | ... | ... | ... | ... | ... | +--------+-------+-------+-------+-------+-----+ - (3) **Correlation Figure.** Network representation of the top 500 gene-metabolite correlations based on the absolute value of the correlation coeficients. Maximum number of correlations in the netork is 500. + (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. ]]> </help> <citations> - <citation type="bibtex">@article{dejean2013mixomics, - title={mixOmics: Omics data integration project}, - author={Dejean, Sebastien and Gonzalez, Ignacio and L{\^e} Cao, Kim-Anh and Monget, Pierre and Coquery, J and Yao, F and Liquet, B and Rohart, F}, - journal={R package}, - year={2013} - }</citation> <citation type="bibtex">@ARTICLE{Kirpich17secimtools, author = {Alexander S. Kirpich, Miguel Ibarra, Oleksandr Moskalenko, Justin M. Fear, Joseph Gerken, Xinlei Mi, Ali Ashrafi, Alison M. Morse, Lauren M. McIntyre}, title = {SECIMTools: A suite of Metabolomics Data Analysis Tools}, journal = {BMC Bioinformatics}, - year = {in press} + year = {2018} }</citation> - <citation type="bibtex"> - @article{garcia2010paintomics, - title={Paintomics: a web based tool for the joint visualization of transcriptomics and metabolomics data}, - author={Garc{\'\i}a-Alcalde, Fernando and Garc{\'\i}a-L{\'o}pez, Federico and Dopazo, Joaqu{\'\i}n and Conesa, Ana}, - journal={Bioinformatics}, - volume={27}, - number={1}, - pages={137--139}, - year={2010}, - publisher={Oxford University Press} + <citation type="bibtex">@article{Mor2021GaitGM, + title={GAIT-GM integrative cross-omics analyses reveal cholinergic defects in a C. elegans model of Parkinson's disease}, + 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}, + journal={BMC Genomics}, + year={submitted}, }</citation> </citations> </tool>