|
1
|
1 <tool id="ballgown" name="Ballgown" version="0.5.0" workflow_compatible="true">
|
|
|
2 <description>Flexible, isoform-level differential expression analysis</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="2.2.0">bioconductor-ballgown</requirement>
|
|
|
5 <requirement type="package" version="0.5.0">r-dplyr</requirement>
|
|
|
6 <requirement type="package" version="1.3.2">r-optparse</requirement>
|
|
|
7
|
|
|
8 </requirements>
|
|
|
9 <command interpreter="Rscript" detect_errors="aggressive">
|
|
|
10 ##------------------------------------------------------------------------------------
|
|
|
11 ## This function reads the input file with the mapping between samples and files
|
|
|
12 ## E.g. of result:
|
|
|
13 ## mapping = {
|
|
|
14 ## "e2t.ctab" : "sample1",
|
|
|
15 ## "other.ctab" : "sample2",
|
|
|
16 ## "i2t.ctab" : "sample1",
|
|
|
17 ## "t_data.ctab": "sample1"
|
|
|
18 ## ...
|
|
|
19 ## }
|
|
|
20 ##------------------------------------------------------------------------------------
|
|
|
21 #def read_sample_mapping_file(sample_mapping_file):
|
|
|
22 #try
|
|
|
23 #set mapping = {}
|
|
|
24 #set file = open($sample_mapping_file.dataset.dataset.get_file_name(),'r')
|
|
|
25 #for $line in $file:
|
|
|
26 #set content= $line.strip().split('\t')
|
|
|
27 #for $map in $content:
|
|
|
28 #set mapping[$map]= $content[0]
|
|
|
29 #end for
|
|
|
30 #end for
|
|
|
31 #return $mapping
|
|
|
32 #except
|
|
|
33 #return None
|
|
|
34 #end try
|
|
|
35 #end def
|
|
|
36
|
|
|
37 ##------------------------------------------------------------------------------------
|
|
|
38 ## This function returns the name of the sample associated to a given file
|
|
|
39 ##------------------------------------------------------------------------------------
|
|
|
40 #def get_sample_name($dataset, $sample_mapping):
|
|
|
41 ##If the file with samples mapping was provided
|
|
|
42 #if $sample_mapping != None:
|
|
|
43 #return $sample_mapping.get($dataset.name, None)
|
|
|
44 ##Otherwise with extract the sample name from the filename
|
|
|
45 #else:
|
|
|
46 #return str($dataset.element_identifier)
|
|
|
47 #end if
|
|
|
48 #end def
|
|
|
49
|
|
|
50 ##------------------------------------------------------------------------------------
|
|
|
51 ## This function reads a dataset or list of datasets and sets the corresponding value
|
|
|
52 ## in the $result variable
|
|
|
53 ## e.g. of result
|
|
|
54 ##'sample1' : {
|
|
|
55 ## 'e_data': '/export/galaxy-central/database/files/000/dataset_13.dat'
|
|
|
56 ## 'i_data': '/export/galaxy-central/database/files/000/dataset_10.dat',
|
|
|
57 ## 't_data': '/export/galaxy-central/database/files/000/dataset_12.dat',
|
|
|
58 ## 'e2t': '/export/galaxy-central/database/files/000/dataset_9.dat',
|
|
|
59 ## 'i2t': '/export/galaxy-central/database/files/000/dataset_11.dat'
|
|
|
60 ## },
|
|
|
61 ##------------------------------------------------------------------------------------
|
|
|
62 #def read_input_files($param_name, $param_value, $result, $sample_mapping, $create_if_empty):
|
|
|
63 ## If input is a data collection
|
|
|
64 #if isinstance($param_value, list):
|
|
|
65 ## For each dataset
|
|
|
66 #for $dataset in $param_value:
|
|
|
67 ## Get the sample name
|
|
|
68 #set sample_name = $get_sample_name($dataset, $sample_mapping)
|
|
|
69 ## Check if sample is already registered
|
|
|
70 #if not($result.has_key($sample_name)):
|
|
|
71 #if ($create_if_empty == True):
|
|
|
72 #set result[$sample_name] = {}
|
|
|
73 #else:
|
|
|
74 #raise ValueError("Error in input. Please check that input contains all the required files for sample " + $sample_name)
|
|
|
75 #end if
|
|
|
76 #end if
|
|
|
77 ## Register the file to the sample
|
|
|
78 #set result[$sample_name][$param_name] = str($dataset.dataset.dataset.get_file_name())
|
|
|
79 #end for
|
|
|
80 #else:
|
|
|
81 #if not($result.has_key("sample_1")):
|
|
|
82 #set result["sample_1"] = {}
|
|
|
83 #end if
|
|
|
84 #set result["sample_1"][$param_name] = str($param_name.dataset.dataset.get_file_name())
|
|
|
85 #end if
|
|
|
86 #return $result
|
|
|
87 #end def
|
|
|
88
|
|
|
89 ##------------------------------------------------------------------------------------
|
|
|
90 ## Main body of the tool
|
|
|
91 ##------------------------------------------------------------------------------------
|
|
|
92 ## Set the params for the next R script
|
|
|
93 #set result={}
|
|
|
94 #set sample_mapping=None
|
|
|
95
|
|
|
96 ## If the samples mapping file was provided, parse the content
|
|
|
97 #if $samples_names != None and not(isinstance($samples_names, list) and (None in $samples_names)):
|
|
|
98 #set sample_mapping = $read_sample_mapping_file($samples_names)
|
|
|
99 #end if
|
|
|
100
|
|
|
101 ## READ THE CONTENT FOR e_data AND STORE THE FILES
|
|
|
102 ## INDEXED BY THEIR SAMPLE NAME
|
|
|
103 ## e.g. 'HBR_Rep1' : {
|
|
|
104 ## 'e_data': '/export/galaxy-central/database/files/000/dataset_13.dat'
|
|
|
105 ## 'i_data': '/export/galaxy-central/database/files/000/dataset_10.dat',
|
|
|
106 ## 't_data': '/export/galaxy-central/database/files/000/dataset_12.dat',
|
|
|
107 ## 'e2t': '/export/galaxy-central/database/files/000/dataset_9.dat',
|
|
|
108 ## 'i2t': '/export/galaxy-central/database/files/000/dataset_11.dat'
|
|
|
109 ## },
|
|
|
110 ## 'HBR_Rep2' : {...}
|
|
|
111 #set $result = $read_input_files("e_data.ctab", $e_data, $result, $sample_mapping, True)
|
|
|
112 #set $result = $read_input_files("i_data.ctab", $i_data, $result, $sample_mapping, False)
|
|
|
113 #set $result = $read_input_files("t_data.ctab", $t_data, $result, $sample_mapping, False)
|
|
|
114 #set $result = $read_input_files("e2t.ctab", $e2t, $result, $sample_mapping, False)
|
|
|
115 #set $result = $read_input_files("i2t.ctab", $i2t, $result, $sample_mapping, False)
|
|
|
116
|
|
|
117 ## For each input sample, create a directory and link the input files for ballgown
|
|
|
118 #import os
|
|
|
119 #set n_sample = 1
|
|
|
120 #for $key, $value in $result.iteritems():
|
|
|
121 #set dir_name = str($output.files_path) + "/" + $key + "/"
|
|
|
122 $os.makedirs($dir_name)
|
|
|
123 #for $file_name, $file_path in $value.iteritems():
|
|
|
124 $os.symlink($file_path, $dir_name + $file_name)
|
|
|
125 #end for
|
|
|
126 #set n_sample = $n_sample + 1
|
|
|
127 #end for
|
|
|
128
|
|
|
129 ## Run the R script with the location of the linked files and the name for outpot file
|
|
|
130 ballgown.R --directory $output.files_path --outputtranscript $output --outputgenes $outputgn --texpression $trexpression --phendat $phendata --bgout $bgo
|
|
|
131 </command>
|
|
|
132 <inputs>
|
|
|
133 <param name="e_data" type="data" multiple="true" format="tabular" label="Exon-level expression measurements" help="One row per exon. See below for more details."/>
|
|
|
134 <param name="i_data" type="data" multiple="true" format="tabular" label="Intron- (i.e., junction-) level expression measurements" help="One row per intron. See below for more details."/>
|
|
|
135 <param name="t_data" type="data" multiple="true" format="tabular" label="Transcript-level expression measurements" help="One row per transcript. See below for more details."/>
|
|
|
136 <param name="e2t" type="data" multiple="true" format="tabular" label="Exons-transcripts mapping" help="Table with two columns, e_id and t_id, denoting which exons belong to which transcripts. See below for more details."/>
|
|
|
137 <param name="i2t" type="data" multiple="true" format="tabular" label="Introns-transcripts mapping" help="Table with two columns, i_id and t_id, denoting which introns belong to which transcripts. See below for more details."/>
|
|
|
138 <param name="samples_names" type="data" optional="true" multiple="false" format="tabular" label="File names for samples" help="Optional. Use in case that the names for the analysed samples cannot be extracted from the filenames."/>
|
|
|
139 <param argument="--phendat" name="phendata" type="data" format="csv" label="phenotype data" />
|
|
|
140 <param argument="--texpression" name="trexpression" type="float" value="0.5" label="minimal transcript expression to appear in the results"/>
|
|
|
141 </inputs>
|
|
|
142 <outputs>
|
|
|
143 <data name="bgo" format="rda" file="ballgown_object.rda" label="${tool.name} on ${on_string}: ballgown object (R data file)"/>
|
|
|
144 <data name="output" format="csv" file="output_transcript.csv" label="${tool.name} on ${on_string}: transcripts expression (tabular)"/>
|
|
|
145 <data name="outputgn" format="csv" file="output_genes.csv" label="${tool.name} on ${on_string}: genes expression (tabular)"/>
|
|
|
146 </outputs>
|
|
|
147 <tests>
|
|
|
148 </tests>
|
|
|
149 <help>
|
|
|
150
|
|
|
151 =======================
|
|
|
152 Ballgown
|
|
|
153 =======================
|
|
|
154 -----------------------
|
|
|
155 **What it does**
|
|
|
156 -----------------------
|
|
|
157
|
|
|
158 Ballgown is a software package designed to facilitate flexible differential expression analysis of RNA-seq data.
|
|
|
159 The Ballgown package provides functions to organize, visualize, and analyze the expression measurements for your transcriptome assembly.
|
|
|
160
|
|
|
161 ----
|
|
|
162
|
|
|
163 -----------------------
|
|
|
164 **How to use**
|
|
|
165 -----------------------
|
|
|
166 The input for this tools consists on 5 files for each sample in your experiment:
|
|
|
167
|
|
|
168 - **e_data**: exon-level expression measurements. Tab file or collection of tab files. One row per exon. Columns are e_id (numeric exon id), chr, strand, start, end (genomic location of the exon), and the following expression measurements for each sample:
|
|
|
169 * rcount: reads overlapping the exon
|
|
|
170 * ucount: uniquely mapped reads overlapping the exon
|
|
|
171 * mrcount: multi-map-corrected number of reads overlapping the exon
|
|
|
172 * cov average per-base read coverage
|
|
|
173 * cov_sd: standard deviation of per-base read coverage
|
|
|
174 * mcov: multi-map-corrected average per-base read coverage
|
|
|
175 * mcov_sd: standard deviation of multi-map-corrected per-base coverage
|
|
|
176 - **i_data**: intron- (i.e., junction-) level expression measurements. Tab file or collection of tab files. One row per intron. Columns are i_id (numeric intron id), chr, strand, start, end (genomic location of the intron), and the following expression measurements for each sample:
|
|
|
177 * rcount: number of reads supporting the intron
|
|
|
178 * ucount: number of uniquely mapped reads supporting the intron
|
|
|
179 * mrcount: multi-map-corrected number of reads supporting the intron
|
|
|
180 - **t_data**: transcript-level expression measurements. Tab file or collection of tab files. One row per transcript. Columns are:
|
|
|
181 * t_id: numeric transcript id
|
|
|
182 * chr, strand, start, end: genomic location of the transcript
|
|
|
183 * t_name: Cufflinks-generated transcript id
|
|
|
184 * num_exons: number of exons comprising the transcript
|
|
|
185 * length: transcript length, including both exons and introns
|
|
|
186 * gene_id: gene the transcript belongs to
|
|
|
187 * gene_name: HUGO gene name for the transcript, if known
|
|
|
188 * cov: per-base coverage for the transcript (available for each sample)
|
|
|
189 * FPKM: Cufflinks-estimated FPKM for the transcript (available for each sample)
|
|
|
190 - **e2t**: Tab file or collection of tab files. Table with two columns, e_id and t_id, denoting which exons belong to which transcripts. These ids match the ids in the e_data and t_data tables.
|
|
|
191 - **i2t**: Tab file or collection of tab files. Table with two columns, i_id and t_id, denoting which introns belong to which transcripts. These ids match the ids in the i_data and t_data tables.
|
|
|
192 - samples_names: (optional) Tab file. Table with five columns, one row per sample. Defines which files from the input belong to each sample in the experiment.
|
|
|
193
|
|
|
194 .. class:: infomark
|
|
|
195
|
|
|
196 '''TIP''' *Note* Here's an example of a good phenotype data file for your expirement.
|
|
|
197
|
|
|
198 +--------------+-------------------------+-------------------------+---+
|
|
|
199 |ids |experimental variable 1 |experimental variable 2 |...|
|
|
|
200 +==============+=========================+=========================+===+
|
|
|
201 |sample 1 |value 1 |value 2 |...|
|
|
|
202 +--------------+-------------------------+-------------------------+---+
|
|
|
203 |sample 2 |value 2 |value 1 |...|
|
|
|
204 +--------------+-------------------------+-------------------------+---+
|
|
|
205 |sample 3 |value 1 |value 2 |...|
|
|
|
206 +--------------+-------------------------+-------------------------+---+
|
|
|
207 |sample 4 |value 2 |value 1 |...|
|
|
|
208 +--------------+-------------------------+-------------------------+---+
|
|
|
209 |... |value 1 |value 2 |...|
|
|
|
210 +--------------+-------------------------+-------------------------+---+
|
|
|
211
|
|
|
212
|
|
|
213 .. class:: infomark
|
|
|
214
|
|
|
215 *Note* The minimal transcript expression is a number used to filter the transcripts that
|
|
|
216 are less or not expressed in our samples when compared to the genome
|
|
|
217
|
|
|
218 -----------------------
|
|
|
219 **Outputs**
|
|
|
220 -----------------------
|
|
|
221
|
|
|
222 This tool has 3 outputs:
|
|
|
223
|
|
|
224 - **transcripts expression** : this is a csv file containing all the transcripts that are expressed above the transcripts expression value
|
|
|
225 - **genes expression** : this is a csv file containing all the genes that are expressed above the transcripts expression value
|
|
|
226 - **Ballgown object** : this is the ballgown object created during the process. This file can be re-used later for further analysis in a R console.
|
|
|
227
|
|
|
228 ----
|
|
|
229
|
|
|
230 **Authors**: Théo Collard [SLU Global Bioinformatics Centre], Rafael Hernández de Diego [SLU Global Bioinformatics Centre], and Tomas Klingström [SLU Global Bioinformatics Centre]
|
|
|
231
|
|
|
232 Sources are available at https://github.com/CollardT/Ballgown-Wrapper
|
|
|
233
|
|
|
234 </help>
|
|
|
235 </tool>
|
