Mercurial > repos > iuc > mothur_chimera_pintail

comparison chimera.pintail.xml @ 0:1e243f796db9 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/mothur commit a9d1e0debcd357d8080a1c6c5f1d206dd45a7a4d
author iuc
date Fri, 19 May 2017 05:17:01 -0400
parents
children a037860aad0b
comparison
equal deleted inserted replaced
-1:000000000000 0:1e243f796db9
1 <tool profile="16.07" id="mothur_chimera_pintail" name="Chimera.pintail" version="@WRAPPER_VERSION@.0">
2 <description>Find putative chimeras using pintail</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements"/>
7 <expand macro="stdio"/>
8 <expand macro="version_command"/>
9 <command><![CDATA[
10 @SHELL_OPTIONS@
11
12 ## create symlinks to input datasets
13 ln -s "$fasta" fasta.dat &&
14 ln -s "$alignment.template" alignment.template.dat &&
15 ln -s "$conservation" conservation.dat &&
16 ln -s "$quantile" quantile.dat &&
17 #if $mask.source2 == "history":
18 ln -s "$mask.input" mask.input.dat &&
19 #end if
20
21 echo 'chimera.pintail(
22 fasta=fasta.dat,
23 reference=alignment.template.dat,
24 filter=$filter,
25 #if $mask.source2 == "default":
26 mask=default,
27 #elif $mask.source2 == "history":
28 mask=mask.input.dat,
29 #end if
30 #if $conservation:
31 conservation=conservation.dat,
32 #end if
33 #if $quantile:
34 quantile=quantile.dat,
35 #end if
36 #if int($window) > 0:
37 window=$window,
38 #end if
39 #if int($increment) > 0:
40 increment=$increment,
41 #end if
42 processors='\${GALAXY_SLOTS:-8}'
43 )'
44 | sed 's/ //g' ## mothur trips over whitespace
45 | mothur
46 | tee mothur.out.log
47 ]]></command>
48 <inputs>
49 <param name="fasta" type="data" format="fasta" label="fasta - Candiate Sequences"/>
50 <conditional name="alignment">
51 <param name="source" type="select" label="Select Reference Template from" help="">
52 <option value="hist">History</option>
53 <option value="ref">Cached Reference</option>
54 </param>
55 <when value="ref">
56 <param name="template" type="select" label="reference - Select an alignment database" help="">
57 <options from_data_table="mothur_aligndb"/>
58 </param>
59 </when>
60 <when value="hist">
61 <param name="template" type="data" format="fasta" label="reference - Reference to align with" help=""/>
62 </when>
63 </conditional>
64 <param name="filter" type="boolean" falsevalue="false" truevalue="true" checked="false" label="filter - Apply a 50% soft vertical filter"/>
65 <conditional name="mask">
66 <param name="source2" type="select" label="Mask option">
67 <option value="">None</option>
68 <option value="default">default ecoli mask</option>
69 <option value="history">From your history</option>
70 </param>
71 <when value="history">
72 <param name="input" type="data" format="mothur.filter" label="Mask for the template file" help=""/>
73 </when>
74 <when value=""/>
75 <when value="default"/>
76 </conditional>
77 <param name="conservation" type="data" format="mothur.freq" optional="true" label="conservation - Template Conserved frequencies" help="a file containing the frequency information for your template file to increase speed. Mothur will generate this for you but it takes a long time."/>
78 <param name="quantile" type="data" format="mothur.quan" optional="true" label="quantile - Template quantile information" help=" file containing the quantiles information for your template file to increase speed. Mothur can generate this for you but it takes a VERY long time. Note that when you use the filter, mask or mask and filter you need to select the appropriate quantile file. The filter parameter makes the quantile file generated specific to the query set you are analyzing."/>
79 <param name="window" type="integer" value="300" label="window - Length of sequence you want in each window analyzed (uses default if &lt; 1)" help="Default is set to 300. Note, changing the window size will require new quantile files to be made."/>
80 <param name="increment" type="integer" value="25" label="increment - Increment for window slide on each iteration (uses default if &lt; 1)" help="Default is 25. Note, changing the increment will require new quantile files to be made."/>
81 </inputs>
82 <outputs>
83 <expand macro="logfile-output"/>
84 <data name="out_file" format="txt" from_work_dir="fasta.*pintail.chimeras" label="${tool.name} on ${on_string}: pintail.chimeras"/>
85 <data name="out_accnos" format="mothur.accnos" from_work_dir="fasta.*pintail.accnos" label="${tool.name} on ${on_string}: pintail.accnos"/>
86 <data name="out_freq" format="mothur.freq" from_work_dir="alignment.template.freq" label="${tool.name} on ${on_string}: pintail.freq">
87 <filter>conservation == None</filter>
88 </data>
89 <data name="out_quantile" format="mothur.quan" from_work_dir="*.quan" label="${tool.name} on ${on_string}: pintail.quan">
90 <filter>quantile == None</filter>
91 </data>
92 </outputs>
93 <tests>
94 <test>
95 <param name="fasta" value="Mock_S280_L001_R1_001_small.trim.contigs.good.align_head"/>
96 <param name="source" value="hist"/>
97 <param name="template" value="HMP_MOCK.v35.align"/>
98 <param name="quantile" value="HMP_MOCK.v35.pintail.quan"/>
99 <param name="window" value="200"/>
100 <output name="out_file" md5="644fe23ee459a76de7b225e530361865" ftype="txt"/>
101 <output name="out_accnos" file="Mock_S280_L001_R1_001_small.trim.contigs.good.pintail.accnos" ftype="mothur.accnos"/>
102 <expand macro="logfile-test"/>
103 </test>
104 <test>
105 <param name="fasta" value="Mock_S280_L001_R1_001_small.trim.contigs.good.align_head"/>
106 <param name="source" value="hist"/>
107 <param name="template" value="HMP_MOCK.v35.align"/>
108 <param name="source2" value="default"/>
109 <param name="window" value="200"/>
110 <output name="out_file" ftype="txt">
111 <assert_contents>
112 <has_text text="Observed"/>
113 <has_text text="Expected"/>
114 </assert_contents>
115 </output>
116 <output name="out_quantile" md5="23a665c9bace6b73efaae1ecf6d88c59" ftype="mothur.quan"/>
117 <output name="out_freq" md5="0381c5adade485cc4341a0ef5674f4d8" ftype="mothur.freq"/>
118 <expand macro="logfile-test"/>
119 </test>
120 </tests>
121 <help>
122 <![CDATA[
123
124 @MOTHUR_OVERVIEW@
125
126 **Command Documentation**
127
128 The chimera.pintail_ command identifies putative chimeras using the pintail approach. It looks at the variation between the expected differences and the observed differences in the query sequence over several windows.
129
130 This method was written using the algorithms described in the paper_ "At Least 1 in 20 16S rRNA Sequence Records Currently Held in the Public Repositories is Estimated To Contain Substantial Anomalies" by Kevin E. Ashelford 1, Nadia A. Chuzhanova 3, John C. Fry 1, Antonia J. Jones 2 and Andrew J. Weightman 1.
131
132 The Pintail algorithm is a technique for determining whether a 16S rDNA sequence is anomalous. It is based on the idea that the extent of local base differences between two aligned 16S rDNA sequences should be roughly the same along the length of the alignment (having allowed for the underlying pattern of hypervariable and conserved regions known to exist within the 16S rRNA gene). In other words, evolutionary distance between two reliable sequences should be constant along the length of the gene.
133
134 In contrast, if an error-free sequence is compared with an anomalous sequence, evolutionary distance along the alignment is unlikely to be constant, especially if the anomaly in question is a chimera and formed from phylogenetically different parental sequences.
135
136 The Pintail algorithm is designed to detect and quantify such local variations and in doing so generates the Deviation from Expectation (DE) statistic. The higher the DE value, the greater the likelihood that the query is anomalous.
137
138 The algorithm works as follows
139
140 The sequence to be checked (the query) is first globally aligned with a phylogenetically similar sequence known to be error-free (the subject). At regular intervals along the resulting alignment, the local evolutionary distance between query and subject is estimated by recording percentage base mismatches within a sampling window of fixed length. The resulting array of percentages (observed percentage differences) reflects variations in evolutionary distance between the query and subject along the length of the 16S rRNA gene. Subtracting observed percentage differences from an equivalent array of expected percentage differences (predicted values for error-free sequences), we obtain a set of deviations, the standard deviation of which (Deviation from Expectation, DE) summarises the variation between observed and expected datasets. The greater the DE value, the greater the disparity there is between observed and expected percentage differences, and the more likely it is that the query sequence is anomalous.
141
142
143 .. _paper: http://www.ncbi.nlm.nih.gov/pubmed/16332745
144 .. _chimera.pintail: https://www.mothur.org/wiki/Chimera.pintail
145
146 ]]>
147 </help>
148 <expand macro="citations">
149 <citation type="doi">10.1128/AEM.71.12.7724-7736.2005</citation>
150 </expand>
151 </tool>