Mercurial > repos > iuc > meme_chip
view meme_chip.xml @ 2:34a8d71a6ee2 draft
Uploaded
| author | iuc |
|---|---|
| date | Wed, 14 Mar 2018 11:20:49 -0400 |
| parents | fd58302909b8 |
| children | 8d3877046d78 |
line wrap: on
line source
<tool id="meme_chip" name="MEME-ChIP" version="4.12.0"> <description>- motif discovery, enrichment analysis and clustering on large nucleotide datasets</description> <macros> <import>macros.xml</import> </macros> <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ #set options_type = $options_type_cond.options_type meme-chip $input -noecho -db $meme_motif_databases.fields.path #if $sequence_alphabet == 'dna': -dna #else: -rna -norc #end if -o '$output.files_path' #if str($options_type)=='advanced': -order $options_type_cond.background_model_order #if str($options_type_cond.subsampling) == "no": -norand #end if #if str($options_type_cond.subsampling_cond.subsampling) != "yes": #set seed = $options_type_cond.subsampling_cond.subsampling.seed #if str($seed) != "0": -seed $options_type_cond.subsampling_cond.subsampling.seed #end if #end if #if str($options_type_cond.nmeme) != "0": -nmeme $options_type_cond.nmeme #end if #if str($options_type_cond.ccut) != "0": -ccut $options_type_cond.ccut #end if -group-thresh $options_type_cond.group_threash #if str($options_type_cond.group_weak) != "0": -group-weak $options_type_cond.group_weak #end if -filter-thresh $options_type_cond.filter_threash -meme-mod $options_type_cond.meme_mod #if str($options_type_cond.meme_minw) != "0": -meme-minw $options_type_cond.meme_minw #end if #if str($options_type_cond.meme_maxw) != "0": -meme-maxw $options_type_cond.meme_maxw #end if #if str($options_type_cond.meme_nmotifs) != '0': -meme-nmotifs $options_type_cond.meme_nmotifs #end if #if str($options_type_cond.meme_minsites) != "0": -meme-minsites $options_type_cond.meme_minsites #end if #if str($options_type_cond.meme_maxsites) != "0": -meme-maxsites $options_type_cond.meme_maxsites #end if #if str($options_type_cond.meme_pal) == "true": -meme-pal #end if -dreme-e $options_type_cond.dreme_e -dreme-m $options_type_cond.dreme_m #if str($options_type_cond.centrimo_local) == "true": -centrimo-local #end if #if str($options_type_cond.centrimo_score) != "0": -centrimo-score $options_type_cond.centrimo_score #end if #if str($options_type_cond.centrimo_maxreg) != "0": -centrimo-maxreg $options_type_cond.centrimo_maxreg #end if #if str($options_type_cond.centrimo_ethresh) != "0": -centrimo-ethresh $options_type_cond.centrimo_ethresh #end if #if str($options_type_cond.centrimo_noseq) == "true": -centrimo-noseq #end if #if str($options_type_cond.centrimo_flip) == "true": -centrimo-flip #end if -spamo-skip -fimo-skip #end if &>meme_chip_log.txt; if [[ $? -ne 0 ]]; then cp meme_chip_log.txt '$output'; exit 1; fi]]></command> <inputs> <param name="input" type="data" format="fasta" label="Primary sequences" help="Nucleotide sequences must have equal length"/> <param name="sequence_alphabet" type="select" label="Sequence alphabet"> <option value="dna" selected="true">DNA</option> <option value="rna">RNA</option> </param> <param name="meme_motif_databases" type="select" label="MEME motif database"> <options from_data_table="meme_motif_databases"> <filter type="sort_by" column="1"/> <validator type="no_options" message="No MEME motif databases are available for the selected input"/> </options> </param> <conditional name="options_type_cond"> <param name="options_type" type="select" label="Options Configuration"> <option value="basic" selected="true">Basic</option> <option value="advanced">Advanced</option> </param> <when value="basic"/> <when value="advanced"> <param name="background_model_order" type="select" label="Select the order of the Markov background model"> <option value="0">0-order model of sequences</option> <option value="1" selected="True">1st order model of sequences</option> <option value="2">2nd order model of sequences</option> <option value="3">3rd order model of sequences</option> <option value="4">4th order model of sequences</option> </param> <conditional name="subsampling_cond"> <param name="subsampling" type="select" label="Should subsampling be random?" help="Select 'No' if your input sequences are sorted in order of confidence (best to worst)"> <option value="yes" selected="true">Yes</option> <option value="no">No</option> </param> <when value="yes"> <param name="seed" type="integer" value="0" min="0" label="Seed for the randomized selection of sequences" help="Zero value indicates random seeding"/> </when> <when value="no"/> </conditional> <param name="nmeme" type="integer" value="0" min="0" label="Limit of sequences to pass to MEME" help="Zero value has no effect"/> <param name="ccut" type="integer" value="100" min="0" label="maximum size of a sequence before it is cut down to a centered section" help="Zero value indicates the sequences should not be cut down"/> <param name="group_threash" type="float" value="0.05" min="0" label="Primary threshold for clustering motifs" /> <param name="group_weak" type="float" value="0" min="0" label="Secondary threshold for clustering motifs" help="Zero value results in 2*primary threshold"/> <param name="filter_thresh" type="float" value="0.05" min="0" label="E-value threshold for including motifs"/> <param name="meme_mod" type="select" label="What is the expected motif site distribution?"> <option value="oops" selected="True">One occurance per sequence</option> <option value="zoops">Zero or one occurances per sequence</option> <option value="anr">Any number of repititions</option> </param> <param name="meme_minw" type="integer" value="0" min="0" label="Minimum motif width"/> <param name="meme_maxw" type="integer" value="0" min="0" label="Maximum motif width"/> <param name="meme_nmotifs" type="integer" value="0" min="0" label="Maximum number of motifs to find"/> <param name="meme_minsites" type="integer" value="0" min="0" label="Minimum number of sites per motif"/> <param name="meme_maxsites" type="integer" value="0" label="Maximum number of sites per motif"/> <param name="meme_pal" type="boolean" truevalue="true" falsevalue="" checked="False" label="Look for palindromes only"/> <param name="dreme_e" type="float" value="0.05" min="0" label="Stop DREME searching after reaching this E-value threshold"/> <param name="dreme_m" type="integer" value="10" min="1" label="Stop DREME searching after finding this many motifs" /> <param name="centrimo_local" type="boolean" truevalue="true" falsevalue="" checked="False" label="Compute enrichment of all regions"/> <param name="centrimo_score" type="integer" value="0" min="0" label="Minimum allowed CentriMo match score"/> <param name="centrimo_maxreg" type="integer" value="0" min="0" label="Maximum CentriMo region size to be considered"/> <param name="centrimo_ethresh" type="integer" value="0" min="0" label="CentriMo E-value threshold for reporting" /> <param name="centrimo_noseq" type="boolean" truevalue="true" falsevalue="" checked="False" label="Store CentriMo sequence IDs in the output"/> <param name="centrimo_flip" type="boolean" truevalue="true" falsevalue="" checked="False" label="Reflect CentriMo matches on reverse strand around center"/> </when> </conditional> <param name="non_commercial_use" label="I certify that I am not using this tool for commercial purposes." type="boolean" truevalue="NON_COMMERCIAL_USE" falsevalue="COMMERCIAL_USE" checked="False"> <validator type="expression" message="This tool is only available for non-commercial use.">value == True</validator> </param> </inputs> <outputs> <data name="output" format="html" label="${tool.name} (html) on ${on_string}"/> </outputs> <tests> <test> <param name="input" value="extract_genomic_dna.fa" ftype="fasta"/> <output name="output" file="sample_output.html" ftype="html"/> </test> </tests> <help> .. class:: warningmark **WARNING: This tool is only available for non-commercial use. Use for educational, research and non-profit purposes is permitted. Before using, be sure to review, agree, and comply with the license.** MWMW-ChIP perform motif discovery, motif enrichment analysis and clustering on large nucleotide datasets. If you want to specify sequence weights, you must include them at the top of your input FASTA file. MEME discovers novel, ungapped motifs (recurring, fixed-length patterns) in your sequences (sample output from sequences). MEME splits variable-length patterns into two or more separate motifs. A motif is a sequence pattern that occurs repeatedly in a group of related sequences. MEME represents motifs as position-dependent letter-probability matrices which describe the probability of each possible letter at each position in the pattern. Individual MEME motifs do not contain gaps. Patterns with variable-length gaps are split by MEME into two or more separate motifs. MEME takes as input a group of sequences and outputs as many motifs as requested. MEME uses statistical modeling techniques to automatically choose the best width, number of occurrences, and description for each motif. .. class:: infomark For detailed information on MEME, click here_, or view the license_. .. _here: http://meme-suite.org/doc/meme.html?man_type=web .. _license: http://meme-suite.org/doc/copyright.html?man_type=web </help> <citations> <citation type="bibtex"> @article{Proceedings of the Second International Conference on Intelligent Systems for Molecular Biology, pp. 28-36, AAAI Press, Menlo Park, California, author = {Bailey,Timothy L. and Elkan, Charles}, title = {Fitting a mixture model by expectation maximization to discover motifs in biopolymers}, year = {1994}, eprint = {None}, url = {http://www.sdsc.edu/~tbailey/papers/ismb94.pdf} }</citation> </citations> </tool>
