|
1
|
1 <tool id="Dimont" name="Dimont" version="0.1" force_history_refresh="true">
|
|
|
2 <description>Dimont, a universal tool for de-novo motif discovery (beta).</description>
|
|
|
3 <command>java -Xms256M -Xmx2G -jar /Users/dev/Desktop/ChIP-seq/galaxy/DimontWeb.jar --run $script_file $summary $summary.id $__new_file_path__ $summary.extra_files_path</command>
|
|
|
4 <inputs>
|
|
|
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)">
|
|
|
6 </param>
|
|
|
7 <param type="data" format="fasta" name="Dimont_ps_Input_sequences" label="<hr />Input sequences" help="The input sequences for de-novo motif discovery (can be uploaded using "GetData" -> "Upload File"), annotated FastA format. The required format is described in the help section." value="" optional="false">
|
|
|
8 </param>
|
|
|
9
|
|
|
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">
|
|
|
11 </param>
|
|
|
12
|
|
|
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">
|
|
|
14 </param>
|
|
|
15
|
|
|
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">
|
|
|
17 <validator type="in_range" min="1.0" max="10000.0" message="Value is not in the specified range [1.0, 10000.0]."/></param>
|
|
|
18
|
|
|
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">
|
|
|
20 </param>
|
|
|
21
|
|
|
22 <param type="integer" name="Dimont_ps_Starts" label="<hr />Starts" help="The number of pre-optimization runs." value="20" optional="false">
|
|
|
23 <validator type="in_range" min="1" max="100" message="Value is not in the specified range [1, 100]."/></param>
|
|
|
24
|
|
|
25 <param type="integer" name="Dimont_ps_Initial_motif_width" label="<hr />Initial motif width" help="The motif width that is used initially, may be adjusted during optimization." value="15" optional="false">
|
|
|
26 <validator type="in_range" min="1" max="50" message="Value is not in the specified range [1, 50]."/></param>
|
|
|
27
|
|
|
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">
|
|
|
29 <validator type="in_range" min="0" max="3" message="Value is not in the specified range [0, 3]."/></param>
|
|
|
30
|
|
|
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">
|
|
|
32 <validator type="in_range" min="-1" max="5" message="Value is not in the specified range [-1, 5]."/></param>
|
|
|
33
|
|
|
34 <param type="float" name="Dimont_ps_Equivalent_sample_size" label="<hr />Equivalent sample size" help="Reflects the strength of the prior on the model parameters." value="4.0" optional="false">
|
|
|
35 <validator type="in_range" min="0.0" max="Infinity" message="Value is not in the specified range [0.0, Infinity]."/></param>
|
|
|
36
|
|
|
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">
|
|
|
38 </param>
|
|
|
39
|
|
|
40 </inputs>
|
|
|
41 <configfiles>
|
|
|
42 <configfile name="script_file">
|
|
|
43 <Dimont_ps_Input_sequences>
|
|
|
44 <value>
|
|
|
45 ${Dimont_ps_Input_sequences}</value>
|
|
|
46 <extension>
|
|
|
47 ${Dimont_ps_Input_sequences.ext}</extension>
|
|
|
48 </Dimont_ps_Input_sequences>
|
|
|
49
|
|
|
50 <Dimont_ps_Position_tag>
|
|
|
51 ${Dimont_ps_Position_tag}</Dimont_ps_Position_tag>
|
|
|
52
|
|
|
53 <Dimont_ps_Value_tag>
|
|
|
54 ${Dimont_ps_Value_tag}</Dimont_ps_Value_tag>
|
|
|
55
|
|
|
56 <Dimont_ps_Standard_deviation>
|
|
|
57 ${Dimont_ps_Standard_deviation}</Dimont_ps_Standard_deviation>
|
|
|
58
|
|
|
59 <Dimont_ps_Weighting_factor>
|
|
|
60 ${Dimont_ps_Weighting_factor}</Dimont_ps_Weighting_factor>
|
|
|
61
|
|
|
62 <Dimont_ps_Starts>
|
|
|
63 ${Dimont_ps_Starts}</Dimont_ps_Starts>
|
|
|
64
|
|
|
65 <Dimont_ps_Initial_motif_width>
|
|
|
66 ${Dimont_ps_Initial_motif_width}</Dimont_ps_Initial_motif_width>
|
|
|
67
|
|
|
68 <Dimont_ps_Markov_order_of_motif_model>
|
|
|
69 ${Dimont_ps_Markov_order_of_motif_model}</Dimont_ps_Markov_order_of_motif_model>
|
|
|
70
|
|
|
71 <Dimont_ps_Markov_order_of_background_model>
|
|
|
72 ${Dimont_ps_Markov_order_of_background_model}</Dimont_ps_Markov_order_of_background_model>
|
|
|
73
|
|
|
74 <Dimont_ps_Equivalent_sample_size>
|
|
|
75 ${Dimont_ps_Equivalent_sample_size}</Dimont_ps_Equivalent_sample_size>
|
|
|
76
|
|
|
77 <Dimont_ps_Delete_BSs_from_profile>
|
|
|
78 ${Dimont_ps_Delete_BSs_from_profile}</Dimont_ps_Delete_BSs_from_profile>
|
|
|
79
|
|
|
80 </configfile>
|
|
|
81 </configfiles>
|
|
|
82 <outputs>
|
|
|
83 <data format="html" name="summary" label="#if str($Dimont_jobname) == '' then $tool.name + ' on ' + $on_string else $Dimont_jobname#">
|
|
|
84 </data>
|
|
|
85 </outputs>
|
|
|
86 <help>
|
|
|
87 **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.
|
|
|
88
|
|
|
89 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.
|
|
|
90 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.
|
|
|
91 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.
|
|
|
92 In case of ChIP data, this anchor position could for instance be the peak summit.
|
|
|
93 For instance, an annotated FastA file for ChIP-exo data comprising sequences of length 100 centered around the peak summit could look like::
|
|
|
94
|
|
|
95 > peak: 50; signal: 515
|
|
|
96 ggccatgtgtatttttttaaatttccac...
|
|
|
97 > peak: 50; signal: 199
|
|
|
98 GGTCCCCTGGGAGGATGGGGACGTGCTG...
|
|
|
99 ...
|
|
|
100
|
|
|
101 where the anchor point is given as 50 for the first two sequences, and the confidence amounts to 515 and 199, respectively.
|
|
|
102 The FastA comment may contain additional annotations of the format ``key1 : value1; key2: value2;...``.
|
|
|
103 We also provide an example_ input file and a Perl script_ for preparing data in the format required by Dimont.
|
|
|
104
|
|
|
105 Accordingly, you would need to set the parameter "Position tag" to ``peak`` and the parameter "Value tag" to ``signal`` for the input file.
|
|
|
106
|
|
|
107 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.
|
|
|
108 However, you may want adjust these parameters to meet your prior information.
|
|
|
109
|
|
|
110 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.
|
|
|
111 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``.
|
|
|
112
|
|
|
113 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.
|
|
|
114 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``.
|
|
|
115
|
|
|
116 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.
|
|
|
117 For PBM data, containing a large number of unspecific probes, this parameter should be set to a lower value, e.g. ``0.01``.
|
|
|
118
|
|
|
119 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.
|
|
|
120
|
|
|
121 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.
|
|
|
122
|
|
|
123 You can also install this web-application within your local Galaxy server. Instructions can be found at the Dimont_ page of Jstacs.
|
|
|
124 There you can also download a command line version of Dimont.
|
|
|
125
|
|
|
126 If you experience problems using Dimont, please contact_ us.
|
|
|
127
|
|
|
128 .. _example: http://www.jstacs.de/downloads/dimont-example.fa
|
|
|
129 .. _script: http://www.jstacs.de/index.php/Dimont#Data_preparation
|
|
|
130 .. _Dimont: http://jstacs.de/index.php/Dimont
|
|
|
131 .. _contact: mailto:grau@informatik.uni-halle.de
|
|
|
132 </help>
|
|
|
133 </tool>
|
|
|
134
|
