annotate DimontWeb.xml @ 2:31963c6688ef draft default tip

Deleted selected files
author grau
date Wed, 20 Nov 2013 04:33:37 -0500
parents eb36f7f72fb1
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
1 <tool id="Dimont" name="Dimont" version="0.1" force_history_refresh="true">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
2 <description>- a universal tool for de-novo motif discovery.</description>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
3 <command>java -Xms256M -Xmx2G -jar \$JAR_PATH/DimontWeb.jar --run $script_file $summary $summary.id $__new_file_path__ $summary.extra_files_path</command>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
4 <inputs>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
5 <param type="text" size="40" name="Dimont_jobname" label="Job name" value="" optional="true" help="Please enter a name for your job that should be used in the history (optional)">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
6 </param>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
7 <param type="data" format="fasta" name="Dimont_ps_Input_sequences" label="&lt;hr /&gt;Input sequences" help="The input sequences for de-novo motif discovery (can be uploaded using &quot;GetData&quot; -&gt; &quot;Upload File&quot;), annotated FastA format. The required format is described in the help section." value="" optional="false">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
8 </param>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
9
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
10 <param type="text" size="40" name="Dimont_ps_Position_tag" label="Position tag" help="The tag for the position information in the FastA-annotation of the input file" value="" optional="false">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
11 </param>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
12
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
13 <param type="text" size="40" name="Dimont_ps_Value_tag" label="Value tag" help="The tag for the value information in the FastA-annotation of the input file" value="" optional="false">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
14 </param>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
15
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
16 <param type="float" name="Dimont_ps_Standard_deviation" label="Standard deviation" help="The standard deviation of the position distribution centered at the position specified by the position tag" value="75.0" optional="false">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
17 <validator type="in_range" min="1.0" max="10000.0" message="Value is not in the specified range [1.0, 10000.0]."/></param>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
18
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
19 <param type="text" size="40" name="Dimont_ps_Weighting_factor" label="Weighting factor" help="The value for weighting the data; either a value between 0 and 1, or a description relative to the standard deviation (e.g. +4sd)" value="0.2" optional="false">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
20 </param>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
21
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
22 <param type="integer" name="Dimont_ps_Starts" label="&lt;hr /&gt;Starts" help="The number of pre-optimization runs." value="20" optional="false">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
23 <validator type="in_range" min="1" max="100" message="Value is not in the specified range [1, 100]."/></param>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
24
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
25 <param type="integer" name="Dimont_ps_Initial_motif_width" label="&lt;hr /&gt;Initial motif width" help="The motif width that is used initially, may be adjusted during optimization." value="15" optional="false">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
26 <validator type="in_range" min="1" max="50" message="Value is not in the specified range [1, 50]."/></param>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
27
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
28 <param type="integer" name="Dimont_ps_Markov_order_of_motif_model" label="Markov order of motif model" help="The Markov order of the model for the motif." value="0" optional="false">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
29 <validator type="in_range" min="0" max="3" message="Value is not in the specified range [0, 3]."/></param>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
30
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
31 <param type="integer" name="Dimont_ps_Markov_order_of_background_model" label="Markov order of background model" help="The Markov order of the model for the background sequence and the background sequence, -1 defines uniform distribution." value="-1" optional="false">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
32 <validator type="in_range" min="-1" max="5" message="Value is not in the specified range [-1, 5]."/></param>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
33
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
34 <param type="float" name="Dimont_ps_Equivalent_sample_size" label="&lt;hr /&gt;Equivalent sample size" help="Reflects the strength of the prior on the model parameters." value="4.0" optional="false">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
35 <validator type="in_range" min="0.0" max="Infinity" message="Value is not in the specified range [0.0, Infinity]."/></param>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
36
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
37 <param type="boolean" name="Dimont_ps_Delete_BSs_from_profile" label="Delete BSs from profile" help="A switch for deleting binding site positions of discovered motifs from the profile before searching for futher motifs." checked="True" optional="false">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
38 </param>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
39
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
40 </inputs>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
41 <requirements>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
42 <requirement type="set_environment">JAR_PATH</requirement>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
43 <requirement type="binary" version=">=1.6">java</requirement>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
44 </requirements>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
45 <configfiles>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
46 <configfile name="script_file">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
47 &lt;Dimont_ps_Input_sequences&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
48 &lt;value&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
49 ${Dimont_ps_Input_sequences}&lt;/value&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
50 &lt;extension&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
51 ${Dimont_ps_Input_sequences.ext}&lt;/extension&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
52 &lt;/Dimont_ps_Input_sequences&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
53
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
54 &lt;Dimont_ps_Position_tag&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
55 ${Dimont_ps_Position_tag}&lt;/Dimont_ps_Position_tag&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
56
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
57 &lt;Dimont_ps_Value_tag&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
58 ${Dimont_ps_Value_tag}&lt;/Dimont_ps_Value_tag&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
59
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
60 &lt;Dimont_ps_Standard_deviation&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
61 ${Dimont_ps_Standard_deviation}&lt;/Dimont_ps_Standard_deviation&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
62
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
63 &lt;Dimont_ps_Weighting_factor&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
64 ${Dimont_ps_Weighting_factor}&lt;/Dimont_ps_Weighting_factor&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
65
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
66 &lt;Dimont_ps_Starts&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
67 ${Dimont_ps_Starts}&lt;/Dimont_ps_Starts&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
68
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
69 &lt;Dimont_ps_Initial_motif_width&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
70 ${Dimont_ps_Initial_motif_width}&lt;/Dimont_ps_Initial_motif_width&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
71
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
72 &lt;Dimont_ps_Markov_order_of_motif_model&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
73 ${Dimont_ps_Markov_order_of_motif_model}&lt;/Dimont_ps_Markov_order_of_motif_model&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
74
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
75 &lt;Dimont_ps_Markov_order_of_background_model&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
76 ${Dimont_ps_Markov_order_of_background_model}&lt;/Dimont_ps_Markov_order_of_background_model&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
77
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
78 &lt;Dimont_ps_Equivalent_sample_size&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
79 ${Dimont_ps_Equivalent_sample_size}&lt;/Dimont_ps_Equivalent_sample_size&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
80
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
81 &lt;Dimont_ps_Delete_BSs_from_profile&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
82 ${Dimont_ps_Delete_BSs_from_profile}&lt;/Dimont_ps_Delete_BSs_from_profile&gt;
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
83
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
84 </configfile>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
85 </configfiles>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
86 <outputs>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
87 <data format="html" name="summary" label="#if str($Dimont_jobname) == '' then $tool.name + ' on ' + $on_string else $Dimont_jobname#">
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
88 </data>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
89 </outputs>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
90 <tests>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
91 <test>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
92 <param name="Dimont_jobname" value="Test" />
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
93 <param name="Dimont_ps_Input_sequences" value="dimont_test.fasta" />
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
94 <param name="Dimont_ps_Position_tag" value="peakSummit" />
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
95 <param name="Dimont_ps_Value_tag" value="maxT" />
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
96 <param name="Dimont_ps_Standard_deviation" value="75.0" />
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
97 <param name="Dimont_ps_Weighting_factor" value="0.2" />
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
98 <param name="Dimont_ps_Starts" value="20" />
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
99 <param name="Dimont_ps_Initial_motif_width" value="15" />
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
100 <param name="Dimont_ps_Markov_order_of_motif_model" value="0" />
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
101 <param name="Dimont_ps_Markov_order_of_background_model" value="-1" />
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
102 <param name="Dimont_ps_Equivalent_sample_size" value="4.0" />
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
103 <param name="Dimont_ps_Delete_BSs_from_profile" value="True" />
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
104 <output name="summary" file="Test/Test_html.html" />
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
105 </test>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
106 </tests>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
107 <help>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
108 **Dimont** is a universal tool for de-novo motif discovery. Dimont has successfully been applied to ChIP-seq, ChIP-exo and protein-binding microarray (PBM) data.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
109
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
110 Input sequences must be supplied in an annotated FastA format as a file uploaded by the "Upload File" task in section "Get Data" of Galaxy or generated using the "Dimont Data Extractor" tool.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
111 In the annotation of each sequence, you need to provide a value that reflects the confidence that this sequence is bound by the factor of interest.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
112 Such confidences may be peak statistics (e.g., number of fragments under a peak) for ChIP data or signal intensities for PBM data. In addition, you need to provide an anchor position within the sequence.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
113 In case of ChIP data, this anchor position could for instance be the peak summit.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
114 For instance, an annotated FastA file for ChIP-exo data comprising sequences of length 100 centered around the peak summit could look like::
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
115
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
116 > peak: 50; signal: 515
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
117 ggccatgtgtatttttttaaatttccac...
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
118 > peak: 50; signal: 199
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
119 GGTCCCCTGGGAGGATGGGGACGTGCTG...
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
120 ...
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
121
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
122 where the anchor point is given as 50 for the first two sequences, and the confidence amounts to 515 and 199, respectively.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
123 The FastA comment may contain additional annotations of the format ``key1 : value1; key2: value2;...``.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
124 We also provide an example_ input file and a Perl script_ for preparing data in the format required by Dimont.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
125
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
126 Accordingly, you would need to set the parameter "Position tag" to ``peak`` and the parameter "Value tag" to ``signal`` for the input file.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
127
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
128 For the standard deviation of the position prior, the initial motif length and the number of pre-optimization runs, we provide default values that worked well in our studies on ChIP and PBM data.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
129 However, you may want adjust these parameters to meet your prior information.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
130
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
131 The parameter "Markov order of the motif model" sets the order of the inhomogeneous Markov model used for modeling the motif. If this parameter is set to ``0``, you obtain a position weight matrix (PWM) model.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
132 If it is set to ``1``, you obtain a weight array matrix (WAM) model. You can set the order of the motif model to at most ``3``.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
133
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
134 The parameter "Markov order of the background model" sets the order of the homogeneous Markov model used for modeling positions not covered by a motif.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
135 If this parameter is set to ``-1``, you obtain a uniform distribution, which worked well for ChIP data. For PBM data, orders of up to ``4`` resulted in an increased prediction performance in our case studies. The maximum allowed value is ``5``.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
136
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
137 The parameter "Weighting factor" defines the proportion of sequences that you expect to be bound by the targeted factor with high confidence. For ChIP data, the default value of ``0.2`` typically works well.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
138 For PBM data, containing a large number of unspecific probes, this parameter should be set to a lower value, e.g. ``0.01``.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
139
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
140 The "Equivalent sample size" reflects the strength of the influence of the prior on the model parameters, where higher values smooth out the parameters to a greater extent.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
141
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
142 The parameter "Delete BSs from profile" defines if BSs of already discovered motifs should be deleted, i.e., "blanked out", from the sequence before searching for futher motifs.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
143
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
144 You can also install this web-application within your local Galaxy server. Instructions can be found at the Dimont_ page of Jstacs.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
145 There you can also download a command line version of Dimont.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
146
1
eb36f7f72fb1 Uploaded
grau
parents: 0
diff changeset
147 If you use Dimont, please cite
eb36f7f72fb1 Uploaded
grau
parents: 0
diff changeset
148
eb36f7f72fb1 Uploaded
grau
parents: 0
diff changeset
149 \J. Grau, S. Posch, I. Grosse, and J. Keilwagen. A general approach for discriminative de-novo motif discovery from high-throughput data. *Nucleic Acids Research*, 41(21):e197, 2013.
eb36f7f72fb1 Uploaded
grau
parents: 0
diff changeset
150
0
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
151 If you experience problems using Dimont, please contact_ us.
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
152
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
153 .. _example: http://www.jstacs.de/downloads/dimont-example.fa
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
154 .. _script: http://www.jstacs.de/index.php/Dimont#Data_preparation
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
155 .. _Dimont: http://jstacs.de/index.php/Dimont
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
156 .. _contact: mailto:grau@informatik.uni-halle.de
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
157 </help>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
158 </tool>
b7d6db3ba6bc Uploaded
grau
parents:
diff changeset
159