|
1
|
1 <tool id="mixmodel4repeated_measures" name="mixmodel" version="3.1.0" profile="19.01">
|
|
|
2 <description>ANOVA for repeated measures statistics</description>
|
|
|
3
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="1.1_27">r-lme4</requirement>
|
|
|
6 <requirement type="package" version="3.1_3">r-lmertest</requirement>
|
|
|
7 <requirement type="package" version="3.2_0">r-ggplot2</requirement>
|
|
|
8 <requirement type="package" version="2.3">r-gridExtra</requirement>
|
|
|
9 <requirement type="package" version="2.40.0">bioconductor-multtest</requirement>
|
|
|
10 </requirements>
|
|
|
11
|
|
|
12 <command detect_errors="exit_code"><![CDATA[
|
|
|
13 Rscript '$__tool_directory__/mixmodel_wrapper.R'
|
|
|
14
|
|
|
15 dataMatrix_in '$dataMatrix_in'
|
|
|
16 sampleMetadata_in '$sampleMetadata_in'
|
|
|
17 variableMetadata_in '$variableMetadata_in'
|
|
|
18
|
|
|
19 fixfact '$fixfact'
|
|
|
20 time '$time'
|
|
|
21 subject '$subject'
|
|
|
22 adjC '$adjC'
|
|
|
23 trf '$trf'
|
|
|
24 thrN '$thrN'
|
|
|
25 diaR '$diaR'
|
|
|
26 dff '$dff'
|
|
|
27 rounding '${roundchoice.rounding}'
|
|
|
28 #if $roundchoice.rounding == 'yes' :
|
|
|
29 decplaces '${roundchoice.decplaces}'
|
|
|
30 #end if
|
|
|
31
|
|
|
32 variableMetadata_out '$variableMetadata_out'
|
|
|
33 out_graph_pdf '$out_graph_pdf'
|
|
|
34 out_estim_pdf '$out_estim_pdf'
|
|
|
35 information '$information'
|
|
|
36
|
|
|
37 ]]></command>
|
|
|
38
|
|
|
39 <inputs>
|
|
|
40 <param name="dataMatrix_in" label="Data matrix file" type="data" format="tabular" help="variable x sample, decimal: '.', missing: NA, mode: numerical, sep: tabular" />
|
|
|
41 <param name="sampleMetadata_in" label="Sample metadata file" type="data" format="tabular" help="sample x metadata, decimal: '.', missing: NA, mode: character and numerical, sep: tabular" />
|
|
|
42 <param name="variableMetadata_in" label="Variable metadata file" type="data" format="tabular" help="variable x metadata, decimal: '.', missing: NA, mode: character and numerical, sep: tabular" />
|
|
|
43 <param name="fixfact" label="Fixed Factor of interest" type="text" help="Name of sample metadata column corresponding to the fixed factor (use none if only time factor"/>
|
|
|
44 <param name="time" label="Repeated factor (time)" type="text" help="Name of the column of the sample metadata table corresponding to the repeated factor"/>
|
|
|
45 <param name="subject" label="Subject factor" type="text" help="Name of the column of the sample metadata table corresponding to the subject factor"/>
|
|
|
46 <param name="dff" label="Degrees of freedom method for the F-tests" type="select" help="">
|
|
|
47 <option value="Satt">Satterthwaite</option>
|
|
|
48 <option value="KenR">Kenward-Roger</option>
|
|
|
49 </param>
|
|
|
50 <param name="adjC" label="Method for multiple testing correction" type="select" help="">
|
|
|
51 <option value="fdr">fdr</option>
|
|
|
52 <option value="BH">BH</option>
|
|
|
53 <option value="bonferroni">bonferroni</option>
|
|
|
54 <option value="BY">BY</option>
|
|
|
55 <option value="hochberg">hochberg</option>
|
|
|
56 <option value="holm">holm</option>
|
|
|
57 <option value="hommel">hommel</option>
|
|
|
58 <option value="none">none</option>
|
|
|
59 </param>
|
|
|
60 <param name="trf" label="Log transform of raw data" type="select" help="Transformation of raw data">
|
|
|
61 <option value="none">none</option>
|
|
|
62 <option value="log10">log10</option>
|
|
|
63 <option value="log2">log2</option>
|
|
|
64 </param>
|
|
|
65 <param name="thrN" type="float" value="0.05" label="(Corrected) p-value significance threshold" help="Must be between 0 and 1"/>
|
|
|
66 <param name="diaR" label="Perform diagnostic of the residuals" type="select" help=" Used to assess the quality of models considering distribution of residuals ">
|
|
|
67 <option value="yes">yes</option>
|
|
|
68 <option value="no">no</option>
|
|
|
69 </param>
|
|
|
70 <conditional name="roundchoice">
|
|
|
71 <param name="rounding" type="select" label="Rounding the result's numerical columns" help="Should the numerical values generated by this tool be rounded to a chosen number of decimal places?">
|
|
|
72 <option value="no">No</option>
|
|
|
73 <option value="yes">Yes</option>
|
|
|
74 </param>
|
|
|
75 <when value="yes">
|
|
|
76 <param argument="decplaces" type="integer" value="6" label="Number of decimal places for rounding" help="Positive interger" />
|
|
|
77 </when>
|
|
|
78 <when value="no">
|
|
|
79 </when>
|
|
|
80 </conditional>
|
|
|
81 </inputs>
|
|
|
82
|
|
|
83 <outputs>
|
|
|
84 <data name="variableMetadata_out" label="${tool.name}_${variableMetadata_in.name}" format="tabular"/>
|
|
|
85 <data name="information" label="${tool.name}_information.txt" format="txt"/>
|
|
|
86 <data name="out_estim_pdf" label="${tool.name}_Estimates" format="pdf"/>
|
|
|
87 <data name="out_graph_pdf" label="${tool.name}_diagResiduals" format="pdf">
|
|
|
88 <filter>diaR == 'yes'</filter>
|
|
|
89 </data>
|
|
|
90 </outputs>
|
|
|
91
|
|
|
92 <tests>
|
|
|
93 <test expect_num_outputs="4">
|
|
|
94 <param name="dataMatrix_in" value="TwoFactor_dataMatrix.txt" />
|
|
|
95 <param name="sampleMetadata_in" value="TwoFactor_sampleMetadata.txt" />
|
|
|
96 <param name="variableMetadata_in" value="TwoFactor_variableMetadata.txt" />
|
|
|
97 <param name="fixfact" value="phenotype" />
|
|
|
98 <param name="time" value="time" />
|
|
|
99 <param name="subject" value="sujet" />
|
|
|
100 <param name="adjC" value = "none"/>
|
|
|
101 <param name="trf" value = "log10"/>
|
|
|
102 <param name="thrN" value = "0.01"/>
|
|
|
103 <param name="dff" value = "Satt"/>
|
|
|
104 <param name="rounding" value = "yes"/>
|
|
|
105 <param name="decplaces" value = "6"/>
|
|
|
106 <output name="variableMetadata_out" value="mixmodel_TwoFactor_variableMetadata.txt" />
|
|
|
107 </test>
|
|
|
108 </tests>
|
|
|
109
|
|
|
110 <help><![CDATA[
|
|
|
111 .. class:: infomark
|
|
|
112
|
|
|
113 **Tool update: See the 'NEWS' section at the bottom of the page**
|
|
|
114
|
|
|
115 .. class:: infomark
|
|
|
116
|
|
|
117 **Authors** Natacha Lenuzza and Jean-Francois Martin wrote this wrapper of R repeated measure anova statistical tests.
|
|
|
118 **Maintainers** Melanie Petera and Marie Tremblay-Franco (INRAE-MetaboHUB)
|
|
|
119
|
|
|
120 MetaboHUB: The French National Infrastructure for Metabolomics and Fluxomics (https://www.metabohub.fr/home.html)
|
|
|
121
|
|
|
122 .. class:: infomark
|
|
|
123
|
|
|
124 **Please cite**
|
|
|
125
|
|
|
126 R Core Team (2013). R: A language and Environment for Statistical Computing. http://www.r-project.org
|
|
|
127
|
|
|
128 .. class:: infomark
|
|
|
129
|
|
|
130 **References**
|
|
|
131 Kuznetsova A. Brockhoff PB. and Christensen RHB (2017). lmerTest Package: Tests in Linear Mixed Effects Models. Journal of Statistical Software, 82(13), pp. 1–26. doi: 10.18637/jss.v082.i13.
|
|
|
132 Benjamini Y. and Hochberg Y. (1995). Controlling the false discovery rate: a practical and powerful approach for multiple testing. Journal of the Royal Statistical Society. Series B (Methodological), 57:289-300.
|
|
|
133
|
|
|
134
|
|
|
135 =============
|
|
|
136 Mixed models
|
|
|
137 =============
|
|
|
138
|
|
|
139 -----------
|
|
|
140 Description
|
|
|
141 -----------
|
|
|
142
|
|
|
143 The module performs analysis of variance for repeated measures using mixed model
|
|
|
144
|
|
|
145
|
|
|
146 -----------
|
|
|
147 Input files
|
|
|
148 -----------
|
|
|
149
|
|
|
150 +---------------------------+------------+
|
|
|
151 | File | Format |
|
|
|
152 +===========================+============+
|
|
|
153 | 1 : Data matrix | tabular |
|
|
|
154 +---------------------------+------------+
|
|
|
155 | 2 : Sample metadatx | tabular |
|
|
|
156 +---------------------------+------------+
|
|
|
157 | 3 : Variable metadata | tabular |
|
|
|
158 +---------------------------+------------+
|
|
|
159
|
|
|
160
|
|
|
161 ----------
|
|
|
162 Parameters
|
|
|
163 ----------
|
|
|
164
|
|
|
165 Data matrix file
|
|
|
166 | variable x sample **dataMatrix** tabular separated file of the numeric data matrix, with . as decimal, and NA for missing values; the table must not contain metadata apart from row and column names; the row and column names must be identical to the rownames of the sample and variable metadata, respectively (see below)
|
|
|
167 |
|
|
|
168
|
|
|
169 Sample metadata file
|
|
|
170 | sample x metadata **sampleMetadata** tabular separated file of the numeric and/or character sample metadata, with . as decimal and NA for missing values
|
|
|
171 |
|
|
|
172
|
|
|
173 Variable metadata file
|
|
|
174 | variable x metadata **variableMetadata** tabular separated file of the numeric and/or character variable metadata, with . as decimal and NA for missing values
|
|
|
175 |
|
|
|
176
|
|
|
177
|
|
|
178 Treatment
|
|
|
179 | Name of the fixed factor in the sample metadata file. Use "none" if you have only a time factor
|
|
|
180 |
|
|
|
181
|
|
|
182 Time
|
|
|
183 | Name of the repeated (time) factor in the sample metadata file
|
|
|
184 |
|
|
|
185
|
|
|
186 Subject
|
|
|
187 | Name of the subject (on which the repeated measurement id done) in the sample metadata file
|
|
|
188 |
|
|
|
189
|
|
|
190 Degrees of freedom
|
|
|
191 | Method to use for degrees of freedom computation
|
|
|
192 |
|
|
|
193
|
|
|
194 Method for multiple testing correction
|
|
|
195 | The 7 methods implemented in the 'p.adjust' R function are available and documented as follows:
|
|
|
196 | "The adjustment methods include the Bonferroni correction ("bonferroni") in which the p-values are multiplied by the number of comparisons. Less conservative corrections are also included by Holm (1979) ("holm"), Hochberg (1988) ("hochberg"), Hommel (1988) ("hommel"), Benjamini and Hochberg (1995) ("BH" or its alias "fdr"), and Benjamini and Yekutieli (2001) ("BY"), respectively. A pass-through option ("none") is also included. The set of methods are contained in the p.adjust.methods vector for the benefit of methods that need to have the method as an option and pass it on to p.adjust. The first four methods are designed to give strong control of the family-wise error rate. There seems no reason to use the unmodified Bonferroni correction because it is dominated by Holm's method, which is also valid under arbitrary assumptions. Hochberg's and Hommel's methods are valid when the hypothesis tests are independent or when they are non-negatively associated (Sarkar, 1998; Sarkar and Chang, 1997). Hommel's method is more powerful than Hochberg's, but the difference is usually small and the Hochberg p-values are faster to compute. The "BH" (aka "fdr") and "BY" method of Benjamini, Hochberg, and Yekutieli control the false discovery rate, the expected proportion of false discoveries amongst the rejected hypotheses. The false discovery rate is a less stringent condition than the family-wise error rate, so these methods are more powerful than the others."
|
|
|
197
|
|
|
198
|
|
|
199 (Corrected) p-value significance threshold
|
|
|
200 |
|
|
|
201 |
|
|
|
202
|
|
|
203 Rounding the result's numerical columns
|
|
|
204 | This parameter enables the choice of a given number of decimal places to be used to display results' values in the output columns of the variableMetadata that are generated by the tool.
|
|
|
205 | If set to "Yes", you can indicate the number of decimal places wanted, and all the results' values will be rounded according to this number.
|
|
|
206 |
|
|
|
207
|
|
|
208 ------------
|
|
|
209 Output files
|
|
|
210 ------------
|
|
|
211
|
|
|
212 variableMetadata_out.tabular
|
|
|
213 | **variableMetadata** file identical to the file given as argument plus
|
|
|
214 | pvalue of Shapiro normality test of the residuals
|
|
|
215 | pvalues of the main effects and interaction
|
|
|
216 | PostHoc test with difference between levels and pvalues of these difference
|
|
|
217 |
|
|
|
218
|
|
|
219 mixedmodel_Estimates
|
|
|
220 | A pdf file is created with a graphical representation of differences among levels of factors with a color code for significance and an error bar.
|
|
|
221 | Plots are only provided for features with at least one significant factor.
|
|
|
222
|
|
|
223
|
|
|
224 mixedmodel_diagResiduals
|
|
|
225 | if Perform diagnostic of the residuals" is set to yes(default) a pdf file is created with a a serie of
|
|
|
226 | graphics outputed in order to assess the distribution of residuals to check the adjustment.
|
|
|
227 | Plots are only provided for features with at least one factor being significant based on the non-corrected p-values.
|
|
|
228
|
|
|
229 information.txt
|
|
|
230 | File with all messages and warnings generated during the computation
|
|
|
231 | The list of variables with name and a tag if it is significant for at least fixed or repeated factor.
|
|
|
232
|
|
|
233
|
|
|
234
|
|
|
235 ---------------------------------------------------
|
|
|
236
|
|
|
237 Changelog/News
|
|
|
238 --------------
|
|
|
239
|
|
|
240 **Version 3.1.0 - April 2022**
|
|
|
241
|
|
|
242 - NEW FEATURE: the tool now can be used without fixed factor by specify "none" in the concerned parameter field.
|
|
|
243
|
|
|
244 - NEW FEATURE: addition of the possibility to choose the degrees of freedom computation method (previously using only the Satterthwaite method).
|
|
|
245
|
|
|
246 - NEW FEATURE: addition of the possibility to choose the number of decimal places in the variable-metadata numerical columns' output.
|
|
|
247
|
|
|
248
|
|
|
249 ]]></help>
|
|
|
250
|
|
|
251 <citations>
|
|
|
252 <citation type="doi">10.18637/jss.v082.i13.</citation>
|
|
|
253 <citation type="bibtex">@ARTICLE{fisher,
|
|
|
254 author = {Benjamini Y. and Hochberg Y.,
|
|
|
255 title = {Controlling the false discovery rate: a practical and powerful approach for multiple testing. Journal of the Royal Statistical Society},
|
|
|
256 journal = {Series B (Methodological)},
|
|
|
257 year = {1995},
|
|
|
258 volume = {57},
|
|
|
259 pages = {289-300}
|
|
|
260 }</citation>
|
|
|
261 <citation type="doi">10.1093/bioinformatics/btu813</citation>
|
|
|
262 </citations>
|
|
|
263
|
|
|
264 </tool>
|
