comparison ffp_phylogeny.xml @ 1:d1c88b118a3f draft

Uploaded
author damion
date Fri, 13 Mar 2015 20:59:28 -0400
parents eb6e5e78a066
children 671667722d3d
comparison
equal deleted inserted replaced
0:eb6e5e78a066 1:d1c88b118a3f
1 <tool id="ffp_phylogeny" name="Feature Frequency Profile Phylogeny" version="0.1.00"> 1 <tool id="ffp_phylogeny" name="Feature Frequency Profile Phylogeny" version="0.1.02">
2 <description>An alignment free comparison tool for phylogenetic analysis and text comparison</description> 2 <description>An alignment free comparison tool for phylogenetic analysis and text comparison</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="0.3.19_d4382db015acec0e5cc43d6c1ac80ae12cb7e6b3">ffp-phylogeny</requirement> 4 <requirement type="package" version="0.3.19_d4382db015acec0e5cc43d6c1ac80ae12cb7e6b3">ffp-phylogeny</requirement>
5 </requirements> 5 </requirements>
6 6
20 #end for 20 #end for
21 " 21 "
22 -t "$(sequence.file_type.split('-')[0])" 22 -t "$(sequence.file_type.split('-')[0])"
23 -l "$length" 23 -l "$length"
24 -o "$info" 24 -o "$info"
25 ##if $normalize: 25 ##if $normalize
26 ## -n 26 ## -n
27 ##end if 27 ##end if
28 #if $sequence.file_type != 'text': 28 #if $sequence.file_type != 'text'
29 #if $sequence.file_type.find('multi') > 0: 29 #if $sequence.file_type == 'amino-multi' or $sequence.file_type == 'nucleotide-multi'
30 -m 30 -m
31 #end if 31 #end if
32 #if $sequence.grouping: 32 #if $sequence.groupings
33 #pass
34 #else
33 -d 35 -d
34 #end if 36 #end if
35 #if $metric: 37 #if $metric
36 -M "$metric" 38 -M "$metric"
37 #end if 39 #end if
38 #if $similarity: 40 #if $similarity
39 -s 41 -s
40 #end if 42 #end if
41 #if $abbreviate: 43 #if $abbreviate
42 -a 44 -a
43 #end if 45 #end if
44 #end if 46 #end if
45 #if $phylogeny.phylo_type == 'filter': 47 #if $phylogeny.phylo_type == 'filter'
46 -f "$phylogeny.filt.filter_type" 48 -f "$phylogeny.filt.filter_type"
47 -L "$phylogeny.filt.lower" 49 -L "$phylogeny.filt.lower"
48 -U "$phylogeny.filt.upper" 50 -U "$phylogeny.filt.upper"
49 #end if 51 #end if
50 #if $tree: 52 #if $tree
51 -T 53 -T
52 #end if 54 #end if
53
54 ##ffpjsd -n FLOAT , --normval=FLOAT 55 ##ffpjsd -n FLOAT , --normval=FLOAT
55 ## For option -e, --euclid, change the n-norm distance (Default is n=2) to any other value where n > 1 56 ## For option -e, --euclid, change the n-norm distance (Default is n=2) to any other value where n > 1
56 57
57 ]]></command> 58 ]]></command>
58 <expand macro="stdio" /> 59 <expand macro="stdio" />
64 <param name="length" type="integer" min="1" max="25" label="l-mer length" value="6" help="String of valid characters of this length will be counted. Synonyms: feature, k-mer, n-gram, k-tuple" size="2"/> 65 <param name="length" type="integer" min="1" max="25" label="l-mer length" value="6" help="String of valid characters of this length will be counted. Synonyms: feature, k-mer, n-gram, k-tuple" size="2"/>
65 <!-- 66 <!--
66 <param name="normalize" label="Normalize counts into relative frequency" type="boolean" checked="true" help="" /> 67 <param name="normalize" label="Normalize counts into relative frequency" type="boolean" checked="true" help="" />
67 --> 68 -->
68 <conditional name="sequence"> 69 <conditional name="sequence">
69 <param type="select" name="file_type" label="File type" help="Note: For phylogeny display, at least three profiles are required, as files or fasta sequences within a file."> 70 <param type="select" name="file_type" label="File type" help="Note: For phylogeny display, at least three profiles are required.">
70 <option value="amino">Amino Acids, one sequence per file</option> 71 <option value="amino">Amino Acids, one profile per file</option>
71 <option value="amino-multi">Amino Acids, multiple fasta sequences per file</option> 72 <option value="amino-multi">Amino Acids, one profile per fasta sequence in file</option>
72 <option value="nucleotide">Nucleic acids, one sequence per file</option> 73 <option value="nucleotide">Nucleic acids, one profile per file</option>
73 <option value="nucleotide-multi">Nucleic acids, multiple fasta sequences per file</option> 74 <option value="nucleotide-multi">Nucleic acids, one profile per fasta sequence in file</option>
74 <option value="text">Text, single file</option> 75 <option value="text">Text, single file</option>
75 </param> 76 </param>
76 77
77 <when value="amino"><!-- ffpaa --> 78 <when value="amino"><!-- ffpaa -->
78 <param name="filesin" type="data" label="Select input file(s)" format="fasta" multiple="true" /> 79 <param name="filesin" type="data" label="Select input file(s)" format="fasta" multiple="true" />
79 <param name="grouping" label="Enable amino acid grouping" type="boolean" checked="true" help="Counts amino acids in groups rather than individually (usually advantageous, see below)." /> 80 <param name="groupings" label="Enable amino acid grouping" type="boolean" checked="true" help="Counts amino acids in groups rather than individually (usually advantageous, see below)." />
80 </when> 81 </when>
81 82
82 <when value="amino-multi"> 83 <when value="amino-multi">
83 <param name="filesin" type="data" label="Select input file(s)" format="fasta" multiple="true" /> 84 <param name="filesin" type="data" label="Select input file(s)" format="fasta" multiple="true" />
84 <param name="grouping" label="Enable amino acid grouping" type="boolean" checked="true" help="Counts amino acids in groups rather than individually (usually advantageous, see below)." /> 85 <param name="groupings" label="Enable amino acid grouping" type="boolean" checked="true" help="Counts amino acids in groups rather than individually (usually advantageous, see below)." />
85 </when> 86 </when>
86 87
87 <when value="nucleotide"><!-- ffpry --> 88 <when value="nucleotide"><!-- ffpry -->
88 <param name="filesin" type="data" label="Select input file(s)" format="fasta" multiple="true" /> 89 <param name="filesin" type="data" label="Select input file(s)" format="fasta" multiple="true" />
89 <param name="grouping" label="Enable purine / pyrimidine grouping" type="boolean" checked="true" help="Counts each nucleotide as a purine(R) or pyrimidine(Y) rather than individually (usually advantageous)." /> 90 <param name="groupings" label="Enable purine / pyrimidine grouping" type="boolean" checked="true" help="Counts each nucleotide as a purine(R) or pyrimidine(Y) rather than individually (usually advantageous)." />
90 </when> 91 </when>
91 92
92 <when value="nucleotide-multi"> 93 <when value="nucleotide-multi">
93 <param name="filesin" type="data" label="Select input file(s)" format="fasta" multiple="true" /> 94 <param name="filesin" type="data" label="Select input file(s)" format="fasta" multiple="true" />
94 <param name="grouping" label="Enable purine / pyrimidine grouping" type="boolean" checked="true" help="Counts each nucleotide as a purine(R) or pyrimidine(Y) rather than individually (usually advantageous)." /> 95 <param name="groupings" label="Enable purine / pyrimidine grouping" type="boolean" checked="true" help="Counts each nucleotide as a purine(R) or pyrimidine(Y) rather than individually (usually advantageous)." />
95 </when> 96 </when>
96 97
97 <when value="text"><!-- ffptxt --> 98 <when value="text"><!-- ffptxt -->
98 <param name="filesin" type="data" multiple="true"/> 99 <param name="filesin" type="data" multiple="true"/>
99 </when> 100 </when>
198 199
199 <tests> 200 <tests>
200 <test> 201 <test>
201 <param name="length" value="1"/> 202 <param name="length" value="1"/>
202 <param name="tree" value="0"/> 203 <param name="tree" value="0"/>
203 <param name="grouping" value="true"/> 204 <param name="groupings" value="false"/>
204 <param name="file_type" value="nucleotide"/> 205 <param name="file_type" value="nucleotide"/>
205 <param name="filesin" value="genome1,genome2"/> 206 <param name="filesin" value="genome1,genome2"/>
206 <output name="info" file="test_length_1_output.tabular"/> 207 <output name="info" file="test_length_1_output.tabular"/>
207 </test> 208 </test>
208 <test> 209 <test>
209 <param name="length" value="2"/> 210 <param name="length" value="2"/>
210 <param name="tree" value="0"/> 211 <param name="tree" value="0"/>
211 <param name="grouping" value="true"/> 212 <param name="groupings" value="false"/>
212 <param name="file_type" value="nucleotide"/> 213 <param name="file_type" value="nucleotide"/>
213 <param name="filesin" value="genome1,genome2"/> 214 <param name="filesin" value="genome1,genome2"/>
214 <output name="info" file="test_length_2_output.tabular"/> 215 <output name="info" file="test_length_2_output.tabular"/>
215 </test> 216 </test>
217 <test>
218 <param name="length" value="2"/>
219 <param name="tree" value="0"/>
220 <param name="groupings" value="true"/>
221 <param name="file_type" value="nucleotide-multi"/>
222 <param name="filesin" value="genome1,genome2"/>
223 <output name="info" file="test_length_2b_output.tabular"/>
224 </test>
216 </tests> 225 </tests>
217 226
218 <help><![CDATA[ 227 <help><![CDATA[
219 228
220 .. class:: infomark 229 .. class:: infomark
222 231
223 **What it does** 232 **What it does**
224 233
225 FFP (Feature frequency profile) is an alignment free comparison tool for phylogenetic analysis and text comparison. It can be applied to nucleotide sequences, complete genomes, proteomes and even used for text comparison. 234 FFP (Feature frequency profile) is an alignment free comparison tool for phylogenetic analysis and text comparison. It can be applied to nucleotide sequences, complete genomes, proteomes and even used for text comparison.
226 235
227 This galaxy tool prepares a mini-pipeline consisting of **[ffpry | ffpaa | ffptxt] &gt; [ ffpfilt | ffpcol &gt; ffprwn] &gt; ffpjsd &gt; ffptree** . The last step is optional - by deselecting the "Generate Tree Phylogeny" checkbox, the tool will output a distance matrix rather than a Newick (.nhx) formatted tree file. 236 This galaxy tool prepares a mini-pipeline consisting of **[ffpry | ffpaa | ffptxt] > [ ffpfilt | ffpcol > ffprwn] > ffpjsd > ffptree** . The last step is optional - by deselecting the "Generate Tree Phylogeny" checkbox, the tool will output only the precursor distance matrix file rather than a Newick (.nhx) formatted tree file.
228 237
229 Each sequence or text file has a profile containing tallies of each feature found. A feature is a string of valid characters of given length. 238 Each sequence or text file has a profile containing tallies of each feature found. A feature is a string of valid characters of given length.
230 239
231 For nucleotide data, by default each character (ATGC) is grouped as either purine(R) or pyrmidine(Y) before being counted. 240 For nucleotide data, by default each character (ATGC) is grouped as either purine(R) or pyrmidine(Y) before being counted.
232 241