Mercurial > repos > rnateam > blockclust

comparison blockclust.xml @ 2:f973ec6e5192 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author rnateam
date Tue, 08 Jul 2014 13:04:30 -0400
parents a92d8689aa30
children 27dde42069e0
comparison
equal deleted inserted replaced
1:a92d8689aa30 2:f973ec6e5192
1 <tool id="blockclust" name="BlockClust" version="1.0.0"> 1 <tool id="blockclust" name="BlockClust" version="1.0.0">
2 <description>Non-coding RNA clustering from deep sequencing read profiles</description> 2 <description>efficient clustering and classification of non-coding RNAs from short read RNA-seq profiles</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="1.0">blockclust</requirement> 4 <requirement type="package" version="1.0">blockclust</requirement>
5 <requirement type="package" version="1.1">eden</requirement> 5 <requirement type="package" version="1.1">eden</requirement>
6 <requirement type="package" version="3.0.1">R_3_0_1</requirement> 6 <requirement type="package" version="3.0.1">R_3_0_1</requirement>
7 <requirement type="package" version="0.1.19">samtools</requirement> 7 <requirement type="package" version="0.1.19">samtools</requirement>
8 <requirement type="package" version="12.135">mcl</requirement> 8 <requirement type="package" version="12.135">mcl</requirement>
9 <requirement type="package" version="1.0">blockclust_rlibs</requirement> 9 <requirement type="package" version="1.0">blockclust_rlibs</requirement>
10 </requirements> 10 </requirements>
11 <version_command>echo '1.0'</version_command> 11 <version_command>echo '1.0'</version_command>
12 <command> 12 <command>
13
14 #if str($tool_mode.operation) == "pre": 13 #if str($tool_mode.operation) == "pre":
15 BlockClustPipeLine.pl -m PRE -bam $tool_mode.reads_bam -tbed $tags_bed 14 BlockClustPipeLine.pl -m PRE -bam $tool_mode.reads_bam -tbed $tags_bed
16 #elif str($tool_mode.operation) == "clust": 15 #elif str($tool_mode.operation) == "clust":
17 #set $outputdir = $clusters.files_path 16 #set $outputdir = $clusters.files_path
18 #set $accept_bed=list() 17 #set $accept_bed=list()
71 </command> 70 </command>
72 <inputs> 71 <inputs>
73 <conditional name="tool_mode"> 72 <conditional name="tool_mode">
74 <param name="operation" type="select" label="Select mode of operation"> 73 <param name="operation" type="select" label="Select mode of operation">
75 <option value="pre">Pre-processing </option> 74 <option value="pre">Pre-processing </option>
76 <option value="clust">Clustering</option> 75 <option value="clust">Clustering and classification</option>
77 <option value="post">Post-processing</option> 76 <option value="post">Post-processing</option>
78 </param> 77 </param>
79 <when value="pre"> 78 <when value="pre">
80 <param name="reads_bam" type="data" format="bam" label="BAM file containing alignments" /> 79 <param name="reads_bam" type="data" format="bam" label="BAM file containing alignments" />
81 </when> 80 </when>
117 <filter> tool_mode["operation"]=="pre"</filter> 116 <filter> tool_mode["operation"]=="pre"</filter>
118 </data> 117 </data>
119 <data format="pdf" name="hclust_plot" label="BlockClust: Hierarchical clustering plot on ${on_string}" > 118 <data format="pdf" name="hclust_plot" label="BlockClust: Hierarchical clustering plot on ${on_string}" >
120 <filter> tool_mode["operation"]=="clust"</filter> 119 <filter> tool_mode["operation"]=="clust"</filter>
121 </data> 120 </data>
122 <data format="bed" name="clusters" label="BlockClust: Clustering BED on ${on_string}"> 121 <data format="bed" name="clusters" label="BlockClust: BED of predicted clusters on ${on_string}">
123 <filter> tool_mode["operation"]=="clust"</filter> 122 <filter> tool_mode["operation"]=="clust"</filter>
124 </data> 123 </data>
125 <data format="bed" name="model_based_pred_bed" label="BlockClust: Model based prediction BED on ${on_string}"> 124 <data format="bed" name="model_based_pred_bed" label="BlockClust: Model based predictions BED on ${on_string}">
126 <filter> 125 <filter>
127 (( 126 ((
128 tool_mode["operation"] == 'clust' and 127 tool_mode["operation"] == 'clust' and
129 tool_mode["pred"]["enable_pred"] == "yes" and 128 tool_mode["pred"]["enable_pred"] == "yes" and
130 tool_mode["pred"]["pred_mode"] == "model_based" 129 tool_mode["pred"]["pred_mode"] == "model_based"
131 )) 130 ))
132 </filter> 131 </filter>
133 </data> 132 </data>
134 <data format="bed" name="nearest_neighbour_pred_bed" label="BlockClust: Nearest neighbour prediction BED on ${on_string}"> 133 <data format="bed" name="nearest_neighbour_pred_bed" label="BlockClust: Nearest neighbor predictions BED on ${on_string}">
135 <filter> 134 <filter>
136 (( 135 ((
137 tool_mode["operation"] == 'clust' and 136 tool_mode["operation"] == 'clust' and
138 tool_mode["pred"]["enable_pred"] == "yes" and 137 tool_mode["pred"]["enable_pred"] == "yes" and
139 tool_mode["pred"]["pred_mode"] == "nearest_neighbour" 138 tool_mode["pred"]["pred_mode"] == "nearest_neighbour"
154 153
155 .. class:: infomark 154 .. class:: infomark
156 155
157 **What it does** 156 **What it does**
158 157
159 Clusters the read profiles (i.e., blockgroups) from the blockbuster tool. 158 BlockClust is an efficient approach to detect transcripts with similar
159 processing patterns. We propose a novel way to encode expression profiles
160 in compact discrete structures, which can then be processed using
161 fast graph-kernel techniques. BlockClust allows both clustering and
162 classification of small non-coding RNAs.
163
164 BlockClust runs in three modes:
165 1) Pre-processing - converts given mapped reads (BAM) into BED file of tags
166 2) Clustering and classification - of given input block groups (from blockbuster tool) as explained in [1]_
167 3) Post-processing - extracts distribution of clusters searched against Rfam database and plots hierarchical clustering made out of centroids of each BlockClust predicted cluster.
168
169 For a thorough analysis of your data, we suggest you to use complete blockclust workflow, which contains all three modes of operation.
160 170
161 **Inputs** 171 **Inputs**
162 172
163 BlockClust needs output of tool blockbuster as input 173 BlockClust input files are dependent on the mode of operation:
174 1) Pre-processing mode:
175 Binary Sequence Alignment Map (BAM) file
176
177 2) Clustering and classification:
178 A blockgroups file generated by blockbuster tool
179 Select reference genome
180
181 3) Post-processing:
182 Output of cmsearch, searched clusters generated by BlockClust against Rfam
183 BED file containing clusters generated by BlockClust
184 Pairwise similarities of blockgroups generated by BlockClust
164 185
165 **Output** 186 **Output**
166 187 1) Pre-processing mode:
167 BlockClust produces a fasta file containing clusters. 188 BED file of tags with expressions
189
190 2) Clustering and classification:
191 Hierarchical clustering plot of all input blockgroups by their similarity
192 Pairwise similarities of all input blockgroups
193 BED file containing predicted clusters
194 BED file containing prediction of blockgroups by pre-compiled SVM binary classification model.
195
196 3) Post-processing:
197 Distribution of clusters with annotations searched against Rfam database
198 hierarchical clustering made out of centroids of each BlockClust predicted cluster
168 199
169 ------ 200 ------
170 201
171 **Licenses** 202 **Licenses**
172 203
173 If **BlockClust** is used to obtain results for scientific publications it 204 If **BlockClust** is used to obtain results for scientific publications it should be cited as [1]_.
174 should be cited as [1]_.
175 205
176 **References** 206 **References**
177 207
178 .. [1] 208 [1] Pavankumar Videm, Dominic Rose, Fabrizio Costa, and Rolf Backofen. "BlockClust: efficient clustering and classification of non-coding RNAs from short read RNA-seq profiles." Bioinformatics 30, no. 12 (2014): i274-i282.
179 209
180 210
181 </help> 211 </help>
182 </tool> 212 </tool>