Mercurial > repos > grau > dimont_motif_discovery
diff DimontWeb.xml @ 0:b7d6db3ba6bc draft
Uploaded
author | grau |
---|---|
date | Wed, 13 Nov 2013 04:25:23 -0500 |
parents | |
children | eb36f7f72fb1 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/DimontWeb.xml Wed Nov 13 04:25:23 2013 -0500 @@ -0,0 +1,155 @@ +<tool id="Dimont" name="Dimont" version="0.1" force_history_refresh="true"> +<description>- a universal tool for de-novo motif discovery.</description> +<command>java -Xms256M -Xmx2G -jar \$JAR_PATH/DimontWeb.jar --run $script_file $summary $summary.id $__new_file_path__ $summary.extra_files_path</command> +<inputs> +<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)"> +</param> +<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"> +</param> + +<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"> +</param> + +<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"> +</param> + +<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"> +<validator type="in_range" min="1.0" max="10000.0" message="Value is not in the specified range [1.0, 10000.0]."/></param> + +<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"> +</param> + +<param type="integer" name="Dimont_ps_Starts" label="<hr />Starts" help="The number of pre-optimization runs." value="20" optional="false"> +<validator type="in_range" min="1" max="100" message="Value is not in the specified range [1, 100]."/></param> + +<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"> +<validator type="in_range" min="1" max="50" message="Value is not in the specified range [1, 50]."/></param> + +<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"> +<validator type="in_range" min="0" max="3" message="Value is not in the specified range [0, 3]."/></param> + +<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"> +<validator type="in_range" min="-1" max="5" message="Value is not in the specified range [-1, 5]."/></param> + +<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"> +<validator type="in_range" min="0.0" max="Infinity" message="Value is not in the specified range [0.0, Infinity]."/></param> + +<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"> +</param> + +</inputs> +<requirements> + <requirement type="set_environment">JAR_PATH</requirement> + <requirement type="binary" version=">=1.6">java</requirement> +</requirements> +<configfiles> +<configfile name="script_file"> +<Dimont_ps_Input_sequences> +<value> +${Dimont_ps_Input_sequences}</value> +<extension> +${Dimont_ps_Input_sequences.ext}</extension> +</Dimont_ps_Input_sequences> + +<Dimont_ps_Position_tag> +${Dimont_ps_Position_tag}</Dimont_ps_Position_tag> + +<Dimont_ps_Value_tag> +${Dimont_ps_Value_tag}</Dimont_ps_Value_tag> + +<Dimont_ps_Standard_deviation> +${Dimont_ps_Standard_deviation}</Dimont_ps_Standard_deviation> + +<Dimont_ps_Weighting_factor> +${Dimont_ps_Weighting_factor}</Dimont_ps_Weighting_factor> + +<Dimont_ps_Starts> +${Dimont_ps_Starts}</Dimont_ps_Starts> + +<Dimont_ps_Initial_motif_width> +${Dimont_ps_Initial_motif_width}</Dimont_ps_Initial_motif_width> + +<Dimont_ps_Markov_order_of_motif_model> +${Dimont_ps_Markov_order_of_motif_model}</Dimont_ps_Markov_order_of_motif_model> + +<Dimont_ps_Markov_order_of_background_model> +${Dimont_ps_Markov_order_of_background_model}</Dimont_ps_Markov_order_of_background_model> + +<Dimont_ps_Equivalent_sample_size> +${Dimont_ps_Equivalent_sample_size}</Dimont_ps_Equivalent_sample_size> + +<Dimont_ps_Delete_BSs_from_profile> +${Dimont_ps_Delete_BSs_from_profile}</Dimont_ps_Delete_BSs_from_profile> + +</configfile> +</configfiles> +<outputs> +<data format="html" name="summary" label="#if str($Dimont_jobname) == '' then $tool.name + ' on ' + $on_string else $Dimont_jobname#"> +</data> +</outputs> +<tests> + <test> + <param name="Dimont_jobname" value="Test" /> + <param name="Dimont_ps_Input_sequences" value="dimont_test.fasta" /> + <param name="Dimont_ps_Position_tag" value="peakSummit" /> + <param name="Dimont_ps_Value_tag" value="maxT" /> + <param name="Dimont_ps_Standard_deviation" value="75.0" /> + <param name="Dimont_ps_Weighting_factor" value="0.2" /> + <param name="Dimont_ps_Starts" value="20" /> + <param name="Dimont_ps_Initial_motif_width" value="15" /> + <param name="Dimont_ps_Markov_order_of_motif_model" value="0" /> + <param name="Dimont_ps_Markov_order_of_background_model" value="-1" /> + <param name="Dimont_ps_Equivalent_sample_size" value="4.0" /> + <param name="Dimont_ps_Delete_BSs_from_profile" value="True" /> + <output name="summary" file="Test/Test_html.html" /> + </test> +</tests> +<help> +**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. + +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. +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. +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. +In case of ChIP data, this anchor position could for instance be the peak summit. +For instance, an annotated FastA file for ChIP-exo data comprising sequences of length 100 centered around the peak summit could look like:: + + > peak: 50; signal: 515 + ggccatgtgtatttttttaaatttccac... + > peak: 50; signal: 199 + GGTCCCCTGGGAGGATGGGGACGTGCTG... + ... + +where the anchor point is given as 50 for the first two sequences, and the confidence amounts to 515 and 199, respectively. +The FastA comment may contain additional annotations of the format ``key1 : value1; key2: value2;...``. +We also provide an example_ input file and a Perl script_ for preparing data in the format required by Dimont. + +Accordingly, you would need to set the parameter "Position tag" to ``peak`` and the parameter "Value tag" to ``signal`` for the input file. + +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. +However, you may want adjust these parameters to meet your prior information. + +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. +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``. + +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. +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``. + +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. +For PBM data, containing a large number of unspecific probes, this parameter should be set to a lower value, e.g. ``0.01``. + +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. + +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. + +You can also install this web-application within your local Galaxy server. Instructions can be found at the Dimont_ page of Jstacs. +There you can also download a command line version of Dimont. + +If you experience problems using Dimont, please contact_ us. + +.. _example: http://www.jstacs.de/downloads/dimont-example.fa +.. _script: http://www.jstacs.de/index.php/Dimont#Data_preparation +.. _Dimont: http://jstacs.de/index.php/Dimont +.. _contact: mailto:grau@informatik.uni-halle.de +</help> +</tool> +