|
0
|
1 <tool id="meme_chip" name="MEME-ChIP" version="4.12.0">
|
|
|
2 <description>- motif discovery, enrichment analysis and clustering on large nucleotide datasets</description>
|
|
|
3 <macros>
|
|
|
4 <import>macros.xml</import>
|
|
|
5 </macros>
|
|
|
6 <expand macro="requirements" />
|
|
|
7 <command detect_errors="exit_code"><![CDATA[
|
|
|
8 #set options_type = $options_type_cond.options_type
|
|
|
9 meme-chip $input
|
|
|
10 -noecho
|
|
|
11 -db $meme_motif_databases.fields.path
|
|
|
12 #if $sequence_alphabet == 'dna':
|
|
|
13 -dna
|
|
|
14 #else:
|
|
|
15 -rna
|
|
|
16 -norc
|
|
|
17 #end if
|
|
|
18 -o '$output.files_path'
|
|
|
19
|
|
|
20 #if str($options_type)=='advanced':
|
|
|
21 -order $options_type_cond.background_model_order
|
|
|
22 #if str($options_type_cond.subsampling) == "no":
|
|
|
23 -norand
|
|
|
24 #end if
|
|
|
25 #if str($options_type_cond.subsampling_cond.subsampling) != "yes":
|
|
|
26 #set seed = $options_type_cond.subsampling_cond.subsampling.seed
|
|
|
27 #if str($seed) != "0":
|
|
|
28 -seed $options_type_cond.subsampling_cond.subsampling.seed
|
|
|
29 #end if
|
|
|
30 #end if
|
|
|
31 #if str($options_type_cond.nmeme) != "0":
|
|
|
32 -nmeme $options_type_cond.nmeme
|
|
|
33 #end if
|
|
|
34 #if str($options_type_cond.ccut) != "0":
|
|
|
35 -ccut $options_type_cond.ccut
|
|
|
36 #end if
|
|
|
37 -group-thresh $options_type_cond.group_threash
|
|
|
38 #if str($options_type_cond.group_weak) != "0":
|
|
|
39 -group-weak $options_type_cond.group_weak
|
|
|
40 #end if
|
|
|
41 -filter-thresh $options_type_cond.filter_threash
|
|
|
42 -meme-mod $options_type_cond.meme_mod
|
|
|
43 #if str($options_type_cond.meme_minw) != "0":
|
|
|
44 -meme-minw $options_type_cond.meme_minw
|
|
|
45 #end if
|
|
|
46 #if str($options_type_cond.meme_maxw) != "0":
|
|
|
47 -meme-maxw $options_type_cond.meme_maxw
|
|
|
48 #end if
|
|
|
49 #if str($options_type_cond.meme_nmotifs) != '0':
|
|
|
50 -meme-nmotifs $options_type_cond.meme_nmotifs
|
|
|
51 #end if
|
|
|
52 #if str($options_type_cond.meme_minsites) != "0":
|
|
|
53 -meme-minsites $options_type_cond.meme_minsites
|
|
|
54 #end if
|
|
|
55 #if str($options_type_cond.meme_maxsites) != "0":
|
|
|
56 -meme-maxsites $options_type_cond.meme_maxsites
|
|
|
57 #end if
|
|
|
58 #if str($options_type_cond.meme_pal) == "true":
|
|
|
59 -meme-pal
|
|
|
60 #end if
|
|
|
61 -dreme-e $options_type_cond.dreme_e
|
|
|
62 -dreme-m $options_type_cond.dreme_m
|
|
|
63 #if str($options_type_cond.centrimo_local) == "true":
|
|
|
64 -centrimo-local
|
|
|
65 #end if
|
|
|
66 #if str($options_type_cond.centrimo_score) != "0":
|
|
|
67 -centrimo-score $options_type_cond.centrimo_score
|
|
|
68 #end if
|
|
|
69 #if str($options_type_cond.centrimo_maxreg) != "0":
|
|
|
70 -centrimo-maxreg $options_type_cond.centrimo_maxreg
|
|
|
71 #end if
|
|
|
72 #if str($options_type_cond.centrimo_ethresh) != "0":
|
|
|
73 -centrimo-ethresh $options_type_cond.centrimo_ethresh
|
|
|
74 #end if
|
|
|
75 #if str($options_type_cond.centrimo_noseq) == "true":
|
|
|
76 -centrimo-noseq
|
|
|
77 #end if
|
|
|
78 #if str($options_type_cond.centrimo_flip) == "true":
|
|
|
79 -centrimo-flip
|
|
|
80 #end if
|
|
|
81 -spamo-skip
|
|
|
82 -fimo-skip
|
|
|
83 #end if
|
|
|
84 &>meme_chip_log.txt;
|
|
|
85 if [[ $? -ne 0 ]]; then
|
|
|
86 cp meme_chip_log.txt '$output';
|
|
|
87 exit 1;
|
|
|
88 fi]]></command>
|
|
|
89 <inputs>
|
|
|
90 <param name="input" type="data" format="fasta" label="Primary sequences" help="Nucleotide sequences must have equal length"/>
|
|
|
91 <param name="sequence_alphabet" type="select" label="Sequence alphabet">
|
|
|
92 <option value="dna" selected="true">DNA</option>
|
|
|
93 <option value="rna">RNA</option>
|
|
|
94 </param>
|
|
|
95 <param name="meme_motif_databases" type="select" label="MEME motif database">
|
|
|
96 <options from_data_table="meme_motif_databases">
|
|
|
97 <filter type="sort_by" column="1"/>
|
|
|
98 <validator type="no_options" message="No MEME motif databases are available for the selected input"/>
|
|
|
99 </options>
|
|
|
100 </param>
|
|
|
101 <conditional name="options_type_cond">
|
|
|
102 <param name="options_type" type="select" label="Options Configuration">
|
|
|
103 <option value="basic" selected="true">Basic</option>
|
|
|
104 <option value="advanced">Advanced</option>
|
|
|
105 </param>
|
|
|
106 <when value="basic"/>
|
|
|
107 <when value="advanced">
|
|
|
108 <param name="background_model_order" type="select" label="Select the order of the Markov background model">
|
|
|
109 <option value="0">0-order model of sequences</option>
|
|
|
110 <option value="1" selected="True">1st order model of sequences</option>
|
|
|
111 <option value="2">2nd order model of sequences</option>
|
|
|
112 <option value="3">3rd order model of sequences</option>
|
|
|
113 <option value="4">4th order model of sequences</option>
|
|
|
114 </param>
|
|
|
115 <conditional name="subsampling_cond">
|
|
|
116 <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)">
|
|
|
117 <option value="yes" selected="true">Yes</option>
|
|
|
118 <option value="no">No</option>
|
|
|
119 </param>
|
|
|
120 <when value="yes">
|
|
|
121 <param name="seed" type="integer" value="0" min="0" label="Seed for the randomized selection of sequences" help="Zero value indicates random seeding"/>
|
|
|
122 </when>
|
|
|
123 <when value="no"/>
|
|
|
124 </conditional>
|
|
|
125 <param name="nmeme" type="integer" value="0" min="0" label="Limit of sequences to pass to MEME" help="Zero value has no effect"/>
|
|
|
126 <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"/>
|
|
|
127 <param name="group_threash" type="float" value="0.05" min="0" label="Primary threshold for clustering motifs" />
|
|
|
128 <param name="group_weak" type="float" value="0" min="0" label="Secondary threshold for clustering motifs" help="Zero value results in 2*primary threshold"/>
|
|
|
129 <param name="filter_thresh" type="float" value="0.05" min="0" label="E-value threshold for including motifs"/>
|
|
|
130 <param name="meme_mod" type="select" label="What is the expected motif site distribution?">
|
|
|
131 <option value="oops" selected="True">One occurance per sequence</option>
|
|
|
132 <option value="zoops">Zero or one occurances per sequence</option>
|
|
|
133 <option value="anr">Any number of repititions</option>
|
|
|
134 </param>
|
|
|
135 <param name="meme_minw" type="integer" value="0" min="0" label="Minimum motif width"/>
|
|
|
136 <param name="meme_maxw" type="integer" value="0" min="0" label="Maximum motif width"/>
|
|
|
137 <param name="meme_nmotifs" type="integer" value="0" min="0" label="Maximum number of motifs to find"/>
|
|
|
138 <param name="meme_minsites" type="integer" value="0" min="0" label="Minimum number of sites per motif"/>
|
|
|
139 <param name="meme_maxsites" type="integer" value="0" label="Maximum number of sites per motif"/>
|
|
|
140 <param name="meme_pal" type="boolean" truevalue="true" falsevalue="" checked="False" label="Look for palindromes only"/>
|
|
|
141 <param name="dreme_e" type="float" value="0.05" min="0" label="Stop DREME searching after reaching this E-value threshold"/>
|
|
|
142 <param name="dreme_m" type="integer" value="10" min="1" label="Stop DREME searching after finding this many motifs" />
|
|
|
143 <param name="centrimo_local" type="boolean" truevalue="true" falsevalue="" checked="False" label="Compute enrichment of all regions"/>
|
|
|
144 <param name="centrimo_score" type="integer" value="0" min="0" label="Minimum allowed CentriMo match score"/>
|
|
|
145 <param name="centrimo_maxreg" type="integer" value="0" min="0" label="Maximum CentriMo region size to be considered"/>
|
|
|
146 <param name="centrimo_ethresh" type="integer" value="0" min="0" label="CentriMo E-value threshold for reporting" />
|
|
|
147 <param name="centrimo_noseq" type="boolean" truevalue="true" falsevalue="" checked="False" label="Store CentriMo sequence IDs in the output"/>
|
|
|
148 <param name="centrimo_flip" type="boolean" truevalue="true" falsevalue="" checked="False" label="Reflect CentriMo matches on reverse strand around center"/>
|
|
|
149 </when>
|
|
|
150 </conditional>
|
|
|
151 <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">
|
|
|
152 <validator type="expression" message="This tool is only available for non-commercial use.">value == True</validator>
|
|
|
153 </param>
|
|
|
154 </inputs>
|
|
|
155 <outputs>
|
|
|
156 <data name="output" format="html" label="${tool.name} (html) on ${on_string}"/>
|
|
|
157 </outputs>
|
|
|
158 <tests>
|
|
|
159 <test>
|
|
|
160 <param name="input" value="extract_genomic_dna.fa" ftype="fasta"/>
|
|
|
161 <output name="output" file="sample_output.html" ftype="html"/>
|
|
|
162 </test>
|
|
|
163 </tests>
|
|
|
164 <help>
|
|
|
165 .. class:: warningmark
|
|
|
166
|
|
|
167 **WARNING: This tool is only available for non-commercial use. Use for educational, research and non-profit purposes is permitted.
|
|
|
168 Before using, be sure to review, agree, and comply with the license.**
|
|
|
169
|
|
|
170 MWMW-ChIP perform motif discovery, motif enrichment analysis and clustering on large nucleotide datasets.
|
|
|
171
|
|
|
172 If you want to specify sequence weights, you must include them at the top of your input FASTA file.
|
|
|
173
|
|
|
174 MEME discovers novel, ungapped motifs (recurring, fixed-length patterns) in your sequences (sample output from sequences).
|
|
|
175 MEME splits variable-length patterns into two or more separate motifs. A motif is a sequence pattern that occurs repeatedly
|
|
|
176 in a group of related sequences. MEME represents motifs as position-dependent letter-probability matrices which describe the
|
|
|
177 probability of each possible letter at each position in the pattern. Individual MEME motifs do not contain gaps. Patterns
|
|
|
178 with variable-length gaps are split by MEME into two or more separate motifs. MEME takes as input a group of sequences and
|
|
|
179 outputs as many motifs as requested. MEME uses statistical modeling techniques to automatically choose the best width, number
|
|
|
180 of occurrences, and description for each motif.
|
|
|
181
|
|
|
182 .. class:: infomark
|
|
|
183
|
|
|
184 For detailed information on MEME, click here_, or view the license_.
|
|
|
185
|
|
|
186 .. _here: http://meme-suite.org/doc/meme.html?man_type=web
|
|
|
187 .. _license: http://meme-suite.org/doc/copyright.html?man_type=web
|
|
|
188
|
|
|
189 </help>
|
|
|
190 <citations>
|
|
|
191 <citation type="bibtex">
|
|
|
192 @article{Proceedings of the Second International Conference on Intelligent Systems for Molecular Biology, pp. 28-36, AAAI Press, Menlo Park, California,
|
|
|
193 author = {Bailey,Timothy L. and Elkan, Charles},
|
|
|
194 title = {Fitting a mixture model by expectation maximization to discover motifs in biopolymers},
|
|
|
195 year = {1994},
|
|
|
196 eprint = {None},
|
|
|
197 url = {http://www.sdsc.edu/~tbailey/papers/ismb94.pdf}
|
|
|
198 }</citation>
|
|
|
199 </citations>
|
|
|
200 </tool>
|
