Mercurial > repos > sblanck > mpagenomics
diff segmentFracB.xml @ 0:4d539083cf7f draft
planemo upload for repository https://github.com/sblanck/MPAgenomics4Galaxy/tree/master/mpagenomics_wrappers commit 689d0d8dc899a683ee18700ef385753559850233-dirty
author | sblanck |
---|---|
date | Tue, 12 May 2020 10:40:36 -0400 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/segmentFracB.xml Tue May 12 10:40:36 2020 -0400 @@ -0,0 +1,178 @@ +<tool id="segFracB" name="Segmentation of allele B fraction " force_history_refresh="True" version="1.0.0"> + <description></description> + <command> + <![CDATA[ + Rscript + ${__tool_directory__}/segmentFracB.R + --chrom '$chrom' + --input '$input' + --output '$output' + --new_file_path '$__new_file_path__' + #if $settings.settingsType == "file": + --settings_type '$settings.inputs' + #end if + #if $settings.settingsType == "dataset": + --settings_type '$settings.settingsType' + #end if + --output_graph '$outputgraph' + --zip_figures '$zipfigures' + --settings_tumor '$tumorcsv' + --outputlog '$outputlog' + --log '$log' + --userid '$__user_id__' + --method '$method' + ]]> + </command> + <inputs> + <param name="input" type="data" format="dsf" label="Dataset summary file" help="Summary text file generated by the Data normalization tool"/> + + <conditional name="settings"> + <param name="settingsType" type="select" label="Files selection Mode" help="Select the whole cel files dataset or pick-up only few files from the dataset"> + <option value="dataset">Select whole dataset</option> + <option value="file">Select file individually</option> + </param> + <when value="dataset" /> + <when value="file"> + <param name="inputs" type="select" format="cel" multiple="true" label="Cel files"> + <options from_dataset="input"> + <column name="name" index="0"/> + <column name="value" index="0"/> + </options> + </param> + </when> + </conditional> + + <param name="tumorcsv" type="data" format="csv" label="Normal-tumor csv file" help="Normal-tumor csv file. See below for more information."/> + + + <!--param name="chrom" type="text" value="All" label="Chromosomes" help="Chromosomes to segment. Use comma to choose multiple chromosomes: e.g. 1, 3, 8. Use 'All' for a segmentation on all chromosomes" /--> + + <param name="chrom" type="select" size="6" multiple="true" label="Chromosomes" help="leave blank for all chromosomes"> + <option value="All">All</option> + <option value="1">chr 1</option> + <option value="2">chr 2</option> + <option value="3">chr 3</option> + <option value="4">chr 4</option> + <option value="5">chr 5</option> + <option value="6">chr 6</option> + <option value="7">chr 7</option> + <option value="8">chr 8</option> + <option value="9">chr 9</option> + <option value="10">chr 10</option> + <option value="11">chr 11</option> + <option value="12">chr 12</option> + <option value="13">chr 13</option> + <option value="14">chr 14</option> + <option value="15">chr 15</option> + <option value="16">chr 16</option> + <option value="17">chr 17</option> + <option value="18">chr 18</option> + <option value="19">chr 19</option> + <option value="20">chr 20</option> + <option value="21">chr 21</option> + <option value="22">chr 22</option> + <option value="23">chr 23</option> + <option value="24">chr 24</option> + <option value="25">chr 25</option> + </param> + <param name="method" type="select" label="Segmentation method" help=""> + <option value="cghseg">cghseg</option> + <option value="PELT">PELT</option> + </param> + <param name="outputgraph" type="select" label="Output figures"> + <option value="TRUE">Yes</option> + <option value="FALSE">No</option> + </param> + <param name="outputlog" type="select" label="Output log"> + <option value="TRUE">Yes</option> + <option value="FALSE">No</option> + </param> + </inputs> + <outputs> + <data format="sar" name="output" label="allele B fraction segmentation of ${input.name}" /> + <data format="zip" name="zipfigures" label="allele B fraction segmentation figures of ${input.name}"> + <filter>outputgraph == "TRUE"</filter> + </data> + <data format="log" name="log" label="log of allele B fraction segmentation of ${input.name}"> + <filter>outputlog == "TRUE"</filter> + </data> + </outputs> + <stdio> + <exit_code range="1:" level="fatal" description="See logs for more details" /> + </stdio> +<help> +.. class:: warningmark + +Data normalization must be run (with the data normalization tool) prior to segmentation. + +----- + +**What it does** +This tool segments allele B fraction extracted from the previously normalized data. This tools works only on normal-tumor study. + +Outputs: + +*A tabular text file containing 6 columns which describe all the segment (1 line per segment):* + + - sampleNames: Name of the file. + - chrom: The chromosome of the segment. + - chromStart: The starting position (in bp) of the segment. This position is not included in the segment. + - chromEnd: The ending position (in bp) of the segment. This position is included in the segment. + - probes: Number of probes in the segment. + - means: Mean of the segment. + +*A .zip file containing all the figures (optionnal)* + +----- + +**Normal-tumor csv files** + +Normal-tumor csv file is required to segment Allele B fraction, because naive genotyping is based on normal samples : + + - The first column contains the names of the files corresponding to normal samples of the dataset. + + - The second column contains the names of the tumor samples files. + + - Column names of these two columns are respectively normal and tumor. + + - Columns are separated by a comma. + + - *Extensions of the files (.CEL for example) should be removed* + + + +**Example** + +Let 6 .cel files in the studied dataset (3 patients, each of them being represented by a couple of normal and tumor cel files.) :: + + patient1_normal.cel + patient1_tumor.cel + patient2_normal.cel + patient2_tumor.cel + patient3_normal.cel + patient3_tumor.cel + + +The csv file should look like this :: + + normal,tumor + patient1_normal,patient1_tumor + patient2_normal,patient2_tumor + patient3_normal,patient3_tumor + +----- + + +**Citation** + +If you use this tool please cite : + +`Q. Grimonprez, A. Celisse, M. Cheok, M. Figeac, and G. Marot. MPAgenomics : An R package for multi-patients analysis of genomic markers, 2014. Preprint <http://fr.arxiv.org/abs/1401.5035>`_ + +If segmentation is performed with PELT, please cite `R. Killick, P. Fearnhead, and I. A. Eckley. Optimal detection of changepoints with a linear computational cost. Journal of the American Statistical Association, 107(500):1590–1598, 2012. <http://arxiv.org/abs/1101.1438>`_ + +If segmentation is performed by cghseg, please cite `Picard, F., Robin, S., Lavielle, M., Vaisse, C., and Daudin, J.-J. (2005). A statistical approach for array CGH data analysis. BMC Bioinformatics, 6(1):27. <http://www.ncbi.nlm.nih.gov/pubmed/15705208>`_ , +and also cite Rigaill, G. (2010). `Pruned dynamic programming for optimal multiple change-point detection. <http://arxiv.org/abs/1004.0887>`_ + +</help> +</tool> \ No newline at end of file