Mercurial > repos > bgruening > hicexplorer_hiccorrectmatrix

comparison hicCorrectMatrix.xml @ 13:9949f055db84 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/hicexplorer commit 3b41d687ff30583540d055f6995de00530cca81d-dirty"
author bgruening
date Mon, 16 Dec 2019 14:31:21 -0500
parents 92fc291ceb1a
children 1e622e371512
comparison
equal deleted inserted replaced
12:ccb35fd640b9 13:9949f055db84
4 <token name="@BINARY@">hicCorrectMatrix</token> 4 <token name="@BINARY@">hicCorrectMatrix</token>
5 <import>macros.xml</import> 5 <import>macros.xml</import>
6 </macros> 6 </macros>
7 <expand macro="requirements" /> 7 <expand macro="requirements" />
8 <command detect_errors="exit_code"><![CDATA[ 8 <command detect_errors="exit_code"><![CDATA[
9 9 ln -s '$matrix_h5_cooler' 'matrix.$matrix_h5_cooler.ext' &&
10 hicCorrectMatrix 10
11 @BINARY@
11 $mode.mode_selector 12 $mode.mode_selector
12 --matrix '$matrix_h5_cooler' 13 --matrix 'matrix.$matrix_h5_cooler.ext'
13 14
14 ## special: --chromosomes is optional, but if given needs at least one argument 15 ## special: --chromosomes is optional, but if given needs at least one argument
15 #set chroms = '" "'.join([ str($var.chromosome) for $var in $chromosomes ]) 16 #set chroms = ' '.join([ '\'' + str($var.chromosome) + '\'' for $var in $chromosomes ])
16 #if chroms 17 #if chroms
17 --chromosomes "$chroms" 18 --chromosomes $chroms
18 #end if 19 #end if
19 20
20 #if $mode.mode_selector == 'correct': 21 #if $mode.mode_selector == 'correct':
21 22 #if $mode.correctionMethod.correctionMethod_selector == 'ice':
22 --iterNum $mode.iterNum 23 --correctionMethod ICE
23 --outFileName matrix.$mode.outputFormat 24 --iterNum $mode.correctionMethod.iterNum
24 25
25 #if $mode.filterThreshold_low and $mode.filterThreshold_large: 26
26 --filterThreshold $mode.filterThreshold_low $mode.filterThreshold_large 27 #if $mode.correctionMethod.filterThreshold_low and $mode.correctionMethod.filterThreshold_large:
28 --filterThreshold $mode.correctionMethod.filterThreshold_low $mode.correctionMethod.filterThreshold_large
29 #end if
30
31 #if $mode.correctionMethod.inflationCutoff:
32 --inflationCutoff $mode.correctionMethod.inflationCutoff
33 #end if
34
35 #if $mode.correctionMethod.transCutoff:
36 --transCutoff $mode.correctionMethod.transCutoff
37 #end if
38
39 #if $mode.correctionMethod.sequencedCountCutoff:
40 --sequencedCountCutoff $mode.correctionMethod.sequencedCountCutoff
41 #end if
42
43 $mode.correctionMethod.skipDiagonal
44 $mode.correctionMethod.perchr
45 #else:
46 --correctionMethod KR
27 #end if 47 #end if
28 48 --outFileName matrix.$matrix_h5_cooler.ext
29 #if $mode.inflationCutoff: 49 #elif $mode.mode_selector == 'diagnostic_plot':
30 --inflationCutoff $mode.inflationCutoff
31 #end if
32
33 #if $mode.transCutoff:
34 --transCutoff $mode.transCutoff
35 #end if
36
37 #if $mode.sequencedCountCutoff:
38 --sequencedCountCutoff $mode.sequencedCountCutoff
39 #end if
40
41 $mode.skipDiagonal
42 $mode.perchr
43
44 #elif $mode.mode_selector == 'merge_failed':
45 --plotName diagnostic_plot.png 50 --plotName diagnostic_plot.png
46 --outMatrixFile corrected_matrix.npz.h5 51 ##--outMatrixFile corrected_matrix.npz.h5
47 #if $mode.xMax: 52 #if $mode.xMax:
48 --xMax $mode.xMax 53 --xMax $mode.xMax
49 #end if 54 #end if
50 #if $mode.filterThreshold_low and $mode.filterThreshold_large: 55 $mode.perchr
51 --filterThreshold '$mode.filterThreshold_low' '$mode.filterThreshold_large'
52 #end if
53 #else:
54 --plotName diagnostic_plot.png
55 #if $mode.xMax:
56 --xMax $mode.xMax
57 #end if
58 #end if 56 #end if
59 #if $mode.mode_selector == 'correct': 57 #if $mode.mode_selector == 'correct':
60 && mv matrix.$mode.outputFormat matrix 58 && mv matrix.$matrix_h5_cooler.ext matrix
61 #end if 59 #end if
62 ]]> 60 ]]>
63 </command> 61 </command>
64 <inputs> 62 <inputs>
65 <expand macro='matrix_h5_cooler_macro' /> 63 <expand macro='matrix_h5_cooler_macro' />
68 <option value="diagnostic_plot">Diagnostic plot</option> 66 <option value="diagnostic_plot">Diagnostic plot</option>
69 <option value="correct">Correct matrix</option> 67 <option value="correct">Correct matrix</option>
70 </param> 68 </param>
71 <when value="diagnostic_plot"> 69 <when value="diagnostic_plot">
72 <expand macro="xMax" /> 70 <expand macro="xMax" />
71 <param argument="--perchr" name="perchr" type="boolean" truevalue="--perchr" falsevalue="" checked="false"
72 label="Compute statistics for each chromosome separately" />
73 </when> 73 </when>
74 <when value="correct"> 74 <when value="correct">
75 <param argument="--iterNum" name="iterNum" type="integer" optional="true" value="500" 75 <conditional name='correctionMethod'>
76 label="Number of iterations" /> 76 <param name='correctionMethod_selector' type='select' label='Correction method'>
77 77 <option value='ice'>Iterative_correction (Imakaev)</option>
78 <param argument="--inflationCutoff" name="inflationCutoff" type="float" optional="true" 78 <option value='kr'>Knights-Ruiz</option>
79 label="Inflation cutoff" value="" 79 </param>
80 help="Value corresponding to the maximum number of times a bin can be scaled up during the iterative correction. 80
81 For example, a inflationCutoff of 3 will filter out all bins that were expanded 3 times or more during the iterative correction."/> 81 <when value='ice'>
82 82 <param argument="--iterNum" name="iterNum" type="integer" optional="true" value="500"
83 <param argument="--transCutoff" name="transCutoff" type="float" optional="true" 83 label="Number of iterations" />
84 label="Trans region cutoff" value="" 84
85 help="Clip high counts in the top -transcut trans regions (i.e. between chromosomes). A usual value is 0.05."/> 85 <param argument="--inflationCutoff" name="inflationCutoff" type="float" optional="true"
86 86 label="Inflation cutoff" value=""
87 <param argument="--sequencedCountCutoff" name="sequencedCountCutoff" optional="true" type="float" 87 help="Value corresponding to the maximum number of times a bin can be scaled up during the iterative correction.
88 label="Sequenced count cutoff" 88 For example, a inflationCutoff of 3 will filter out all bins that were expanded 3 times or more during the iterative correction."/>
89 help="Each bin receives a value indicating the fraction that is covered by reads. 89
90 A cutoff of 0.5 will discard all those bins that have less than half of the bin covered."/> 90 <param argument="--transCutoff" name="transCutoff" type="float" optional="true"
91 91 label="Trans region cutoff" value=""
92 <param argument="--skipDiagonal" name="skipDiagonal" type="boolean" truevalue="--skipDiagonal" falsevalue="" checked="false" 92 help="Clip high counts in the top -transcut trans regions (i.e. between chromosomes). A usual value is 0.05."/>
93 label="Skip diagonal counts"/> 93
94 94 <param argument="--sequencedCountCutoff" name="sequencedCountCutoff" optional="true" type="float"
95 <param argument="--perchr" name="perchr" type="boolean" truevalue="--perchr" falsevalue="" checked="false" 95 label="Sequenced count cutoff"
96 label="Normalize each chromosome separately" /> 96 help="Each bin receives a value indicating the fraction that is covered by reads.
97 <expand macro="filterThreshold" /> 97 A cutoff of 0.5 will discard all those bins that have less than half of the bin covered."/>
98 <param name='outputFormat' type='select' label="Output file format"> 98
99 <option value='h5'>HiCExplorer format</option> 99 <param argument="--skipDiagonal" name="skipDiagonal" type="boolean" truevalue="--skipDiagonal" falsevalue="" checked="false"
100 <option value="cool">cool</option> 100 label="Skip diagonal counts"/>
101 </param> 101
102 <param argument="--perchr" name="perchr" type="boolean" truevalue="--perchr" falsevalue="" checked="false"
103 label="Normalize each chromosome separately" />
104 <expand macro="filterThreshold" />
105 </when>
106 <when value='kr'>
107 </when>
108 </conditional>
102 </when> 109 </when>
103 </conditional> 110 </conditional>
104 111
105 <repeat name="chromosomes" min="0" 112 <repeat name="chromosomes" min="0"
106 title="Include chromosomes" help="List of chromosomes to be included in the iterative correction. 113 title="Include chromosomes" help="List of chromosomes to be included in the iterative correction.
110 </param> 117 </param>
111 </repeat> 118 </repeat>
112 119
113 </inputs> 120 </inputs>
114 <outputs> 121 <outputs>
115 <data name="outFileName" from_work_dir="matrix" format="h5"> 122 <data name="outFileName" from_work_dir="matrix" format="cool">
116 <change_format> 123 <change_format>
117 <when input="mode.outputFormat" value="cool" format="cool" /> 124 <when input_dataset="matrix_h5_cooler" attribute="ext" value="h5" format="h5"/>
118 </change_format> 125 </change_format>
119 <filter>mode['mode_selector'] == "correct"</filter> 126 <filter>mode['mode_selector'] == "correct"</filter>
120 127
121 </data> 128 </data>
122 129
128 <tests> 135 <tests>
129 <test> 136 <test>
130 <param name="matrix_h5_cooler" value="small_test_matrix.h5"/> 137 <param name="matrix_h5_cooler" value="small_test_matrix.h5"/>
131 138
132 <param name="mode_selector" value="correct"/> 139 <param name="mode_selector" value="correct"/>
140 <param name='correctionMethod_selector' value='ice'/>
133 <repeat name="chromosomes"> 141 <repeat name="chromosomes">
134 <param name="chromosome" value="chrUextra"/> 142 <param name="chromosome" value="chrUextra"/>
135 </repeat> 143 </repeat>
136 <repeat name="chromosomes"> 144 <repeat name="chromosomes">
137 <param name="chromosome" value="chr3LHet"/> 145 <param name="chromosome" value="chr3LHet"/>
138 </repeat> 146 </repeat>
139 <param name='outputFormat' value='h5'/>
140 <param name='filterThreshold_low' value='-2.0' /> 147 <param name='filterThreshold_low' value='-2.0' />
141 <param name='filterThreshold_large' value='4' /> 148 <param name='filterThreshold_large' value='4' />
142 <output name="outFileName" file="hicCorrectMatrix_result1.npz.h5" ftype="h5" compare="sim_size"/> 149 <output name="outFileName" ftype="h5">
150 <assert_contents>
151 <has_h5_keys keys='correction_factors,intervals,matrix,nan_bins'/>
152 </assert_contents>
153 </output>
154 </test>
155 <test>
156 <param name="matrix_h5_cooler" value="small_test_matrix.h5"/>
157
158 <param name="mode_selector" value="correct"/>
159 <param name='correctionMethod_selector' value='kr'/>
160
161 <output name="outFileName" ftype="h5">
162 <assert_contents>
163 <has_h5_keys keys='correction_factors,intervals,matrix'/>
164 </assert_contents>
165 </output>
166 </test>
167 <test>
168 <param name="matrix_h5_cooler" value="small_test_matrix.cool"/>
169
170 <param name="mode_selector" value="correct"/>
171 <param name='correctionMethod_selector' value='kr'/>
172
173 <output name="outFileName" ftype="cool">
174 <assert_contents>
175 <has_h5_keys keys='bins,chroms,indexes,pixels'/>
176 </assert_contents>
177 </output>
178 </test>
179 <test>
180 <param name="matrix_h5_cooler" value="small_test_matrix.h5"/>
181
182 <param name="mode_selector" value="correct"/>
183 <param name='correctionMethod_selector' value='ice'/>
184 <repeat name="chromosomes">
185 <param name="chromosome" value="chrUextra"/>
186 </repeat>
187 <repeat name="chromosomes">
188 <param name="chromosome" value="chr3LHet"/>
189 </repeat>
190 <param name='filterThreshold_low' value='-2.0' />
191 <param name='filterThreshold_large' value='4' />
192 <output name="outFileName" ftype="h5">
193 <assert_contents>
194 <has_h5_keys keys='correction_factors,intervals,matrix,nan_bins'/>
195 </assert_contents>
196 </output>
143 </test> 197 </test>
144 <test> 198 <test>
145 <param name="matrix_h5_cooler" value="small_test_matrix.h5"/> 199 <param name="matrix_h5_cooler" value="small_test_matrix.h5"/>
146 <param name="mode_selector" value="diagnostic_plot"/> 200 <param name="mode_selector" value="diagnostic_plot"/>
147 <repeat name="chromosomes"> 201 <repeat name="chromosomes">
148 <param name="chromosome" value="chrUextra"/> 202 <param name="chromosome" value="chrUextra"/>
149 </repeat> 203 </repeat>
150 <repeat name="chromosomes"> 204 <repeat name="chromosomes">
151 <param name="chromosome" value="chr3LHet"/> 205 <param name="chromosome" value="chr3LHet"/>
152 </repeat> 206 </repeat>
153 <output name="diagnostic_plot" file="diagnostic_plot.png" ftype="png" compare="sim_size"/> 207 <output name="diagnostic_plot" file="hicCorrectMatrix/diagnostic_plot.png" ftype="png" compare="sim_size"/>
154 </test> 208 </test>
155 </tests> 209 </tests>
156 <help><![CDATA[ 210 <help><![CDATA[
157 211
158 Hi-C contact matrix correction 212 Hi-C contact matrix correction
209 On the example plot above, a user can then use the lower threshold defined by the Median Absolute Deviation (MAD) method (black bold bar), or define its own threshold based on the contacts distribution. 263 On the example plot above, a user can then use the lower threshold defined by the Median Absolute Deviation (MAD) method (black bold bar), or define its own threshold based on the contacts distribution.
210 264
211 Correct 265 Correct
212 _______ 266 _______
213 267
214 Run the iterative correction and outputs the corrected matrix. This matrix can then be used with all downstream analysis tools such as ``hicPlotMatrix``, ``hicPlotTADs``, ``hicPlotViewpoint``, ``hicAggregateContacts`` for **visualization of Hi-C data**, ``hicCorrelate``, ``hicPlotDistVsCounts``, ``hicTransform``, ``hicFindTADs``, ``hicPCA`` **for data and scores computation on Hi-C data**. 268 Run the iterative correction and outputs the corrected matrix. This matrix can then be used with all downstream analysis tools such as ``hicPlotMatrix``, ``pyGenomeTracks``, ``hicPlotViewpoint``, ``hicAggregateContacts`` for **visualization of Hi-C data**, ``hicCorrelate``, ``hicPlotDistVsCounts``, ``hicTransform``, ``hicFindTADs``, ``hicPCA`` **for data and scores computation on Hi-C data**.
215 269
216 It is noteworthy that ``hicSumMatrices`` and ``hicMergeMatrixBins`` **must be performed on uncorrected matrices**. 270 It is noteworthy that ``hicSumMatrices`` and ``hicMergeMatrixBins`` **must be performed on uncorrected matrices**.
217 271
218 _________________ 272 _________________
219 273