Mercurial > repos > sblanck > smagexp

changeset 0:5a57280b9125 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author sblanck
date Thu, 10 Nov 2016 07:34:57 -0500
parents
children f8a2f1fec8ef
files AffyQCnormalization.xml Analyse.xml GEOQuery.xml ImportDataFromMatrix.xml MetaMA.xml MetaRNAseq.xml repository_dependencies.xml
diffstat 7 files changed, 384 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/AffyQCnormalization.xml	Thu Nov 10 07:34:57 2016 -0500
@@ -0,0 +1,61 @@
+<tool id="QCnormalization" name="QCnormalization" version="0.1.0">
+	<description>Quality control and normalization of affymetrix expression data</description>
+	<requirements>
+	  <container type="docker">sblanck/smat</container>
+	</requirements>
+	<command>
+		<![CDATA[
+		/galaxy-tools/stderr_wrapper.py Rscript 
+		/galaxy-tools/transcriptomics/AffyQCnormalization/AffyQCnormalization.R
+		   	#for $input in $inputs
+                "${input}"
+			    "${input.name}"
+     		#end for
+			"${normalization}"
+			$result_export_eset
+       		$result_html
+			$result_html.files_path
+		/galaxy-tools/transcriptomics/AffyQCnormalization/AffyQCnormalization_tpl.html
+		]]>
+		</command>
+	
+		<inputs>
+	
+		<param name="inputs" type="data" format="cel" multiple="true" label=".CEL files" help=".CEL files to be used"/>
+
+		<param name="normalization" type="select" label="Preprocessing/normalization">
+		
+    		<option value="rma">rma (backgroung correction + quantile normalization + log2)</option>
+            <option value="quantile">quantile normalization + log2</option>
+            <option value="background">background correction + log2</option>
+            <option value="log2">log2 only</option>
+           
+		
+		</param>
+		
+	</inputs>
+	<outputs>
+		<data format="rdata" name="result_export_eset" label="export normalized expressionSet"/>		
+		<data format="html" name="result_html" label="QC result"/>
+	</outputs>
+
+	<help>
+<![CDATA[
+		**What it does** 
+		    	
+The QCnormalization tool offers to ensure the quality of the data and to normalize them. Several normalization methods are available :
+
+* rma normalization 
+* quantile normalization + log2
+* background correction + log2
+* log2 only
+
+**Results**
+
+- Several quality figures : microarray images, boxplots and MA plots
+- Rdata object containing the normalized data for further analysis
+  		
+]]>
+</help>
+
+</tool>
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/Analyse.xml	Thu Nov 10 07:34:57 2016 -0500
@@ -0,0 +1,92 @@
+<tool id="LimmaAnalyse" name="Limma analysis" version="0.3.0">
+	<description>Perform gene expression analysis thanks to limma</description>
+	<requirements>
+	  	<container type="docker">sblanck/smagexp</container>
+	</requirements>
+	<command>
+		<![CDATA[ 
+		/galaxy-tools/stderr_wrapper.py Rscript
+		/galaxy-tools/transcriptomics/Analyse/Analyse.R
+		   	"${rdataset}"
+			"${conditions}"
+		 	"${selectCondition1}"
+			"${condition1}"
+		    "${selectCondition2}"
+			"${condition2}"
+			"${nbresult}"
+       		$result_export_eset
+       		$result_html 
+			$result_html.files_path
+			$result_tabular
+		/galaxy-tools/transcriptomics/Analyse/Analyse_tpl.html
+		]]>
+	</command>
+	
+	<inputs>
+		<param name="rdataset" type="data" format="rdata" label="RData" help="RData to be used"/>
+		<param name="conditions" type="data" format="cond" label="Conditions" help="conditions associated with the rData file"/>
+		<param name="selectCondition1" type="select" label="condition 1">
+			<options from_dataset="conditions">
+    		<column name="name" index="1"/>
+    		<column name="value" index="1"/>
+    		<filter type="unique_value" column="1"/>
+		</options>
+		</param>
+		<param name="condition1" type="select" display="checkboxes" label="Condition 1" multiple="true">
+			<options from_dataset="conditions">
+    		<column name="name" index="2"/>
+    		<column name="value" index="0"/>
+			<filter  type="param_value" ref="selectCondition1" column="1"/>
+		</options>
+		</param>	
+		<param name="selectCondition2" type="select" label="condition 2">
+			<options from_dataset="conditions">
+    		<column name="name" index="1"/>
+    		<column name="value" index="1"/>
+			<filter type="unique_value" column="1"/>    		
+		</options>
+		</param>	
+		<param name="condition2" type="select" display="checkboxes" label="Condition 2" multiple="true">
+			<options from_dataset="conditions">
+    		<column name="name" index="2"/>
+    		<column name="value" index="0"/>
+			<filter  type="param_value" ref="selectCondition2" column="1"/>
+		</options>
+		</param>	
+		<param name="nbresult" type="integer" value="1000" min="1" label="number of top genes" help="Number of genes to be displayed in result datatable"/>
+	</inputs>
+	<outputs>
+		<data format="html" name="result_html" label="Results of analysis of ${rdataset.name}"/>
+		<data format="rdata" name="result_export_eset" label="Export of expression set of ${rdataset.name}"/>
+		<data format="tabular" name="result_tabular" label="Text Results of analysis of ${rdataset.name}"/>
+		
+	</outputs>
+	<help>
+<![CDATA[ 
+**What it does**
+		
+The Limma analysis tool performs single analysis either of data previously retrieved from GEO database or normalized affymetrix .CEL files data. 
+Given a .cond file, it runs a standard limma differential expression analysis. 
+
+**Example** of .cond file      	
+
+The .cond file should look like this 
+::
+
+ Sample ID 	Condition			Description
+ GSM80460	series of 16 tumors	GSM80460 OSCE-2T SERIES OF 16 TUMORS
+ GSM80461	series of 16 tumors	GSM80461 OSCE-4T Series of 16 Tumors
+ GSM80462	series of 16 tumors	GSM80462 OSCE-6T Series of 16 Tumors
+ GSM80476	series of 4 normals	GSM80476 OSCE-2N Series of 4 Normals
+ GSM80477	series of 4 normals	GSM80477 OSCE-9N Series of 4 Normals
+	
+		
+**Results**
+		
+- Boxplots, p-value histograms and a volcano plot 
+- Table summarizing the differentially expressed genes and their annotations. This table is sortable and requestable.
+- Rdata object to perform further meta-analysis. 
+]]>
+	</help>
+
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/GEOQuery.xml	Thu Nov 10 07:34:57 2016 -0500
@@ -0,0 +1,65 @@
+<tool id="GEOQuery" name="GEOQuery">
+	<description>GEOQuery wrapper</description>
+	<requirements>
+	  	<container type="docker">sblanck/smagexp</container>
+	</requirements>
+	<command>
+		<![CDATA[ 
+			/galaxy-tools/stderr_wrapper.py Rscript 
+			/galaxy-tools/transcriptomics/GEOquery/GEOQuery.R 
+			$GEOQueryID 
+			$GEOQueryData 
+			$GEOQueryRData 
+			$conditions
+			$transformation
+		]]>
+	</command>
+
+	<inputs>
+		<param name="GEOQueryID" type="text" size="12" optional="false" label="GEOQuery ID" help="">
+			<validator type="empty_field"/>
+		</param>
+	<param name="transformation" type="select" label="log2 transformation">
+			<option value="auto">auto</option>
+            <option value="yes">yes</option>
+            <option value="no">no</option>
+        </param>
+	</inputs>
+
+		<outputs>
+		<data format="tabular" name="GEOQueryData" label="GEOQuery Data of ${GEOQueryID}"/>
+		<data format="cond" name="conditions" label="conditions of ${GEOQueryID}"/>
+        <data format="rdata" name="GEOQueryRData" label="GEOQuery RData of ${GEOQueryID}"/>		
+	</outputs>
+	<help>
+<![CDATA[ 
+**What it does**     	
+
+This tool fetches microarray data directly from GEO database, based on the GEOQuery R package. Given a GSE accession ID, it returns an Rdata object containing the data and a text file (.cond file) summarizing the conditions of the experiment. 
+The .cond file is a text file containing one line per sample in the experiment. Each line is made of 3 columns:
+
+	- Sample ID 
+	- Condition of the biological sample
+	- Description of the biological sample
+
+**Example** of .cond file      	
+::
+
+ Sample ID 	Condition			Description
+ GSM80460	series of 16 tumors	GSM80460 OSCE-2T SERIES OF 16 TUMORS
+ GSM80461	series of 16 tumors	GSM80461 OSCE-4T Series of 16 Tumors
+ GSM80462	series of 16 tumors	GSM80462 OSCE-6T Series of 16 Tumors
+ GSM80476	series of 4 normals	GSM80476 OSCE-2N Series of 4 Normals
+ GSM80477	series of 4 normals	GSM80477 OSCE-9N Series of 4 Normals
+    
+**Results**
+	
+- Rdata object containing data for further analysis
+- Condition (.cond) file summarizing conditions of the experiment
+- Tabular (.txt) file containing expression data for each sample
+]]> 		
+
+	</help>
+
+
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/ImportDataFromMatrix.xml	Thu Nov 10 07:34:57 2016 -0500
@@ -0,0 +1,78 @@
+<tool id="importMatrixData" name="Import custom data">
+	<description>Quality control and normalization of a custom matrix expression data</description>
+	<requirements>
+	  	<container type="docker">sblanck/smagexp</container>
+	</requirements>
+	<command>
+		<![CDATA[ 
+		/galaxy-tools/stderr_wrapper.py Rscript 
+		/galaxy-tools/transcriptomics/ImportDataFromMatrix/ImportDataFromMatrix.R
+		    $input
+			$normalization
+			$conditions
+			$annotations
+			$result_export_eset
+       		$result_html
+			$result_html.files_path
+		/galaxy-tools/transcriptomics/ImportDataFromMatrix/ImportDataFromMatrix_tpl.html
+		]]>		
+		</command>
+		
+	
+	<inputs>
+		<param name="input" type="data" format="tabular" label="Input data" help="Input data"/>
+		<param name="normalization" type="select" label="Preprocessing/normalization">
+    		<option value="quantile">quantile normalization + log2</option>
+            <option value="log2">log2 only</option>
+            <option value="none">none</option>
+		</param>
+		<param name="conditions" type="data" format="cond" label="Conditions" help="conditions associated with the input file"/>
+		<param name="annotations" type="text" label="Annotation GPL code" help="GPL code for annotations"/>		
+	</inputs>
+
+	<outputs>
+		<data format="rdata" name="result_export_eset" label="export normalized expressionSet"/>		
+		<data format="html" name="result_html" label="QC result"/>
+	</outputs>
+
+	<help>
+<![CDATA[ 
+**What it does**
+		     	
+This tool imports data stored in a tabular text file. 
+Column titles (chip IDs) must match the IDs of the .cond file.
+GPL annotation code is also required to fetch annotations from GEO.
+
+**Exemple**
+
+Header of input tabular text file
+::
+
+""	"GSM80460"	"GSM80461"	"GSM80462"	"GSM80463"	"GSM80464"
+"1007_s_at"	-0.0513991525066443	0.306845500314283	0.0854246562526777	-0.142417044615852	0.0854246562526777
+"1053_at"	-0.187707155126729	-0.488026018218199	-0.282789700980404	0.160920188181103	0.989865622866287
+"117_at"	0.814755482809874	-2.15842936260448	-0.125006361067033	-0.256700472111743	0.0114956388378294
+"121_at"	-0.0558912008920451	-0.0649174766813385	0.49467161164755	-0.0892673380970874	0.113700499164728
+"1294_at"	0.961993677420255	-0.0320936297098533	-0.169744675832317	-0.0969617298870879	-0.181149439104566
+"1316_at"	0.0454429707611671	0.43616183931445	-0.766111939825723	-0.182786075741673	0.599317793698226
+"1405_i_at"	2.23450132056221	0.369606070031838	-1.06190243892591	-0.190997225060914	0.595503660502742
+
+
+The .cond file should look like this 
+::
+
+ Sample ID 	Condition			Description
+ GSM80460	series of 16 tumors	GSM80460 OSCE-2T SERIES OF 16 TUMORS
+ GSM80461	series of 16 tumors	GSM80461 OSCE-4T Series of 16 Tumors
+ GSM80462	series of 16 tumors	GSM80462 OSCE-6T Series of 16 Tumors
+ GSM80476	series of 4 normals	GSM80476 OSCE-2N Series of 4 Normals
+ GSM80477	series of 4 normals	GSM80477 OSCE-9N Series of 4 Normals
+
+				
+**Results**
+	- Bboxplots and MA plots 
+	- Rdata object containing the data for further analysis.
+]]>
+	</help>
+
+</tool>
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/MetaMA.xml	Thu Nov 10 07:34:57 2016 -0500
@@ -0,0 +1,50 @@
+<tool id="metaMA" name="Microarray data meta-analysis" version="0.1.0">
+	<description>Perform meta-analysis thanks to metaMA.</description>
+	<requirements>
+	  <container type="docker">sblanck/smagexp</container>
+	</requirements>
+	<command>
+		<![CDATA[ 
+		/galaxy-tools/stderr_wrapper.py Rscript 
+		/galaxy-tools/transcriptomics/MetaMA/MetaMA.R
+		#for $currentInput in $inputList
+        	"${currentInput.rdataset}"
+		 #end for
+       		$result_html 
+			$result_html.extra_files_path
+		/galaxy-tools/transcriptomics/MetaMA/MetaMa_tpl.html
+		]]>
+	</command>
+	
+	<inputs>
+		<repeat name="inputList" title="Datasets">
+			<param name="rdataset" type="data" format="rdata" label="RData" help="RData to be used"/>
+		</repeat>
+	</inputs>
+	
+	<outputs>
+		<data format="html" name="result_html" label="Meta-analysis results"/>
+	</outputs>
+
+	<help>
+<![CDATA[ 
+**What it does**
+		
+Given several Rdata object this tool run a meta-analysis using the metaMA R package.
+		
+**Results**
+		
+- Venn Diagram summarizing the results of the meta-analysis
+- A list of indicators to evaluate the quality of the performance of the meta-analysis
+		
+	- DE : Number of differentially expressed genes 
+	- IDD (Integration Driven discoveries) : number of genes that are declared differentially expressed in the meta-analysis that were not identified in any of the single studies alone
+	- Loss : Number of genes that are identified differentially expressed in single studies but not in meta-analysis 
+	- DR (Integration-driven Discovery Rate) : corresponding proportion of IDD
+	- IRR (Integration-driven Revision) : corresponding proportion of Loss
+		
+- Fully sortable and requestable table, with gene annotations and hypertext links to NCBI gene database.
+]]>
+	</help>
+
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/MetaRNAseq.xml	Thu Nov 10 07:34:57 2016 -0500
@@ -0,0 +1,34 @@
+<tool id="metarnaseq" name="RNA-seq data meta-analysis">
+	<description>perform meta-analysis thanks to metaRNAseq</description>
+	<requirements>
+	  	<container type="docker">sblanck/smagexp</container>
+	</requirements>
+	<command>
+		<![CDATA[ 	
+		/galaxy-tools/stderr_wrapper.py Rscript 
+		/galaxy-tools/transcriptomics/MetaRNASeq/MetaRNASeq.R 
+		#for $currentInput in $inputList
+        	"${currentInput}"
+			"${currentInput.name}"	
+		 #end for	
+			$top_table 
+			$diagnostic_html 
+			"$diagnostic_html.files_path"
+		/galaxy-tools/transcriptomics/MetaRNASeq/MetaRNASeq_tpl.html
+	]]>	
+	</command>
+
+	<inputs>
+		<param format="tabular" name="inputList" multiple="true" type="data" optional="false" label="Counts file" help="Must have the same number of row in each study. The experimental conditions must be specified in the header of each file"/>
+	</inputs>
+
+	<outputs>
+		<data format="tabular" name="top_table" label="Summary of meta-analysis and single studie analysis from ${tool.name} on ${on_string}"/>
+		<data format="html" name="diagnostic_html" label="Charts for ${tool.name} on ${on_string}"/>
+	</outputs>
+
+	<help>
+		
+	</help>
+
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/repository_dependencies.xml	Thu Nov 10 07:34:57 2016 -0500
@@ -0,0 +1,4 @@
+<?xml version="1.0"?>
+<repositories description="smagexp datatypes">
+  <repository changeset_revision="f66f8566fd75" name="smagexp_datatypes" owner="sblanck" toolshed="https://testtoolshed.g2.bx.psu.edu" />
+</repositories>