Mercurial > repos > bgruening > hicexplorer_hicbuildmatrix

comparison hicBuildMatrix.xml @ 21:ed2cca6b5de4 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 07802a6bd441d9da888cfb8283f8c2135704f7c9
author iuc
date Wed, 18 Oct 2023 10:48:01 +0000
parents 9edf8894a22d
children a4c13ddcc8ee
comparison
equal deleted inserted replaced
20:29f66c353bcb 21:ed2cca6b5de4
50 #if $outBam: 50 #if $outBam:
51 $outBam ./unsorted.bam 51 $outBam ./unsorted.bam
52 #end if 52 #end if
53 53
54 $keepSelfCircles 54 $keepSelfCircles
55 $removeSelfLigation 55 $keepSelfLigation
56 $skipDuplicationCheck 56 $skipDuplicationCheck
57 57
58 #if $minMappingQuality and $minMappingQuality is not None: 58 #if $minMappingQuality and $minMappingQuality is not None:
59 --minMappingQuality $minMappingQuality 59 --minMappingQuality $minMappingQuality
60 #end if 60 #end if
94 <param argument="--maxLibraryInsertSize" type="integer" optional="true" value="" label="Maximum library insert size defines different cut offs based on the maximum expected library size" help="*This is not the average fragment size* but the higher end of the fragment size distribution (obtained using for example Fragment Analyzer) 94 <param argument="--maxLibraryInsertSize" type="integer" optional="true" value="" label="Maximum library insert size defines different cut offs based on the maximum expected library size" help="*This is not the average fragment size* but the higher end of the fragment size distribution (obtained using for example Fragment Analyzer)
95 which usually is between 800 to 1500 bp. If this value if not known use the default of 1000. The insert value is used to decide if two mates 95 which usually is between 800 to 1500 bp. If this value if not known use the default of 1000. The insert value is used to decide if two mates
96 belong to the same fragment (by checking if they are within this max insert size) and to decide if a mate 96 belong to the same fragment (by checking if they are within this max insert size) and to decide if a mate
97 is too far away from the nearest restriction site." /> 97 is too far away from the nearest restriction site." />
98 98
99 <repeat name='binSizes' title='Bin size in bp' min="1" help="If used, the restriction cut places (if given) are used to only consider reads that are in the vicinity of the resctriction sites. 99 <repeat name="binSizes" title="Bin size in bp" min="1" help="If used, the restriction cut places (if given) are used to only consider reads that are in the vicinity of the resctriction sites.
100 Otherwise all reads in the interval are considered. Use multiple ones to create a mcool file."> 100 Otherwise all reads in the interval are considered. Use multiple ones to create a mcool file.">
101 <param argument="--binSize" type="integer" optional="true" value="" label="Bin size in bp" /> 101 <param argument="--binSize" type="integer" optional="true" value="" label="Bin size in bp" />
102 </repeat> 102 </repeat>
103 103
104 <expand macro="region" /> 104 <expand macro="region" />
105 <param argument="--keepSelfCircles" type="boolean" truevalue="--keepSelfCircles" falsevalue="" label="Keep self circles" help="If set, outward facing reads without any restriction fragment (self circles) are kept. They will be counted and shown in the QC plots." /> 105 <param argument="--keepSelfCircles" type="boolean" truevalue="--keepSelfCircles" falsevalue="" label="Keep self circles" help="If set, outward facing reads without any restriction fragment (self circles) are kept. They will be counted and shown in the QC plots." />
106 <param argument="--removeSelfLigation" type="boolean" truevalue="--removeSelfLigation" falsevalue="" label="remove self ligation" help="If set, inward facing reads less than 1000 bp apart and having a restriction site in between are removed. Although this reads do not contribute to any distant contact, they are useful to account for bias in the data" /> 106 <param argument="--keepSelfLigation" type="boolean" truevalue="--keepSelfLigation" falsevalue="" label="Keep self ligation" help="If set, inward facing reads less than 1000 bp apart and having a restriction site in between are kept. Although this reads do not contribute to any distant contact, they are useful to account for bias in the data." />
107 <expand macro="minMappingQuality" /> 107 <expand macro="minMappingQuality" />
108 <param argument="--skipDuplicationCheck" type="boolean" truevalue="--skipDuplicationCheck" falsevalue="" label="Skip duplication check" help="Identification of duplicated read pairs is memory consuming. Thus, in case of memory errors this check can be skipped." /> 108 <param argument="--skipDuplicationCheck" type="boolean" truevalue="--skipDuplicationCheck" falsevalue="" label="Skip duplication check" help="Identification of duplicated read pairs is memory consuming. Thus, in case of memory errors this check can be skipped." />
109 <param argument="--chromosomeSizes" type="data" format="tabular" optional="true" label="Chromosome sizes for your genome" help="File with the chromosome sizes for your genome. A tab-delimited two column layout 'chr_name size' is expected 109 <param argument="--chromosomeSizes" type="data" format="tabular" optional="true" label="Chromosome sizes for your genome" help="File with the chromosome sizes for your genome. A tab-delimited two column layout 'chr_name size' is expected
110 Usually the sizes can be determined from the SAM/BAM input files, however, 110 Usually the sizes can be determined from the SAM/BAM input files, however,
111 for cHi-C or scHi-C it can be that at the start or end no data is present. 111 for cHi-C or scHi-C it can be that at the start or end no data is present.
112 Please consider that this option causes that only reads are considered which are on the listed chromosomes. 112 Please consider that this option causes that only reads are considered which are on the listed chromosomes.
113 Use this option to guarantee fixed sizes. An example file is available via UCSC: 113 Use this option to guarantee fixed sizes. An example file is available via UCSC:
114 http://hgdownload.soe.ucsc.edu/goldenPath/dm3/bigZips/dm3.chrom.sizes" /> 114 http://hgdownload.soe.ucsc.edu/goldenPath/dm3/bigZips/dm3.chrom.sizes" />
115 115
116 <param argument='--outBam' type='boolean' truevalue='--outBam' falsevalue="" checked="false" label="Save valid Hi-C reads in BAM file" help="A bam 116 <param argument="--outBam" type="boolean" truevalue="--outBam" falsevalue="" checked="false" label="Save valid Hi-C reads in BAM file" help="A bam
117 file containing all valid Hi-C reads can be created 117 file containing all valid Hi-C reads can be created
118 using this option. This bam file could be useful to 118 using this option. This bam file could be useful to
119 inspect the distribution of valid Hi-C reads pairs or 119 inspect the distribution of valid Hi-C reads pairs or
120 for other downstream analyses, but is not used by any 120 for other downstream analyses, but is not used by any
121 HiCExplorer tool. Computation will be significantly 121 HiCExplorer tool. Computation will be significantly
122 longer if this option is set." /> 122 longer if this option is set." />
123 123
124 <param name='outputFormat' type='select' label="Output file format"> 124 <param name="outputFormat" type="select" label="Output file format">
125 <option value='h5'>HiCExplorer format</option> 125 <option value="h5">HiCExplorer format</option>
126 <option value="cool">cool</option> 126 <option value="cool">cool</option>
127 </param> 127 </param>
128 </inputs> 128 </inputs>
129 <outputs> 129 <outputs>
130 <data name="outfileBam" from_work_dir="sorted.bam" format="bam" label="${tool.name} BAM file on ${on_string}"> 130 <data name="outfileBam" from_work_dir="sorted.bam" format="bam" label="${tool.name} BAM file on ${on_string}">
134 <change_format> 134 <change_format>
135 <when input="outputFormat" value="cool" format="cool" /> 135 <when input="outputFormat" value="cool" format="cool" />
136 </change_format> 136 </change_format>
137 </data> 137 </data>
138 <data name="qc" format="html" label="${tool.name} QC on ${on_string}" /> 138 <data name="qc" format="html" label="${tool.name} QC on ${on_string}" />
139 <data name="raw_qc" from_work_dir='raw_qc' format='txt' label="${tool.name} raw QC on ${on_string}" /> 139 <data name="raw_qc" from_work_dir="raw_qc" format="txt" label="${tool.name} raw QC on ${on_string}" />
140 </outputs> 140 </outputs>
141 <tests> 141 <tests>
142 <test expect_num_outputs="4"> 142 <test expect_num_outputs="4">
143 <repeat name="samFiles"> 143 <repeat name="samFiles">
144 <param name="samFile" value="small_test_R1_unsorted.sam" dbkey="hg38" /> 144 <param name="samFile" value="small_test_R1_unsorted.sam" dbkey="hg38" />
145 </repeat> 145 </repeat>
146 <repeat name="samFiles"> 146 <repeat name="samFiles">
147 <param name="samFile" value="small_test_R2_unsorted.sam" dbkey="hg38" /> 147 <param name="samFile" value="small_test_R2_unsorted.sam" dbkey="hg38" />
148 </repeat> 148 </repeat>
149 <param name='outputFormat' value='h5' /> 149 <param name="outputFormat" value="h5" />
150 <repeat name='binSizes'> 150 <repeat name="binSizes">
151 <param name="binSize" value="5000" /> 151 <param name="binSize" value="5000" />
152 </repeat> 152 </repeat>
153 <param name='restrictionCutFile' value='DpnII_10k.bed' /> 153 <param name="restrictionCutFile" value="DpnII_10k.bed" />
154 <param name='restrictionSequence' value='GATC' /> 154 <param name="restrictionSequence" value="GATC" />
155 <param name='danglingSequence' value='GATC' /> 155 <param name="danglingSequence" value="GATC" />
156 <param name='outBam' value="True" /> 156 <param name="outBam" value="True" />
157 <output name="outfileBam" file="small_test_matrix_result_sorted.bam" ftype="bam" /> 157 <output name="outfileBam" file="small_test_matrix_result_sorted.bam" ftype="bam" />
158 <output name="outFileName" ftype="h5"> 158 <output name="outFileName" ftype="h5">
159 <assert_contents> 159 <assert_contents>
160 <has_h5_keys keys='intervals,matrix' /> 160 <has_h5_keys keys="intervals,matrix" />
161 </assert_contents> 161 </assert_contents>
162 </output> 162 </output>
163 <output name="raw_qc" file='raw_qc_report' compare='diff' lines_diff='2' /> 163 <output name="raw_qc" file="raw_qc_report" compare="diff" lines_diff="2" />
164 </test> 164 </test>
165 <test expect_num_outputs="4"> 165 <test expect_num_outputs="4">
166 <repeat name="samFiles"> 166 <repeat name="samFiles">
167 <param name="samFile" value="small_test_R1_unsorted.sam" dbkey="hg38" /> 167 <param name="samFile" value="small_test_R1_unsorted.sam" dbkey="hg38" />
168 </repeat> 168 </repeat>
169 <repeat name="samFiles"> 169 <repeat name="samFiles">
170 <param name="samFile" value="small_test_R2_unsorted.sam" dbkey="hg38" /> 170 <param name="samFile" value="small_test_R2_unsorted.sam" dbkey="hg38" />
171 </repeat> 171 </repeat>
172 <repeat name='binSizes'> 172 <repeat name="binSizes">
173 <param name="binSize" value="5000" /> 173 <param name="binSize" value="5000" />
174 </repeat> 174 </repeat>
175 <param name='restrictionCutFile' value='DpnII_10k.bed' /> 175 <param name="restrictionCutFile" value="DpnII_10k.bed" />
176 <param name='restrictionSequence' value='GATC' /> 176 <param name="restrictionSequence" value="GATC" />
177 <param name='danglingSequence' value='GATC' /> 177 <param name="danglingSequence" value="GATC" />
178 <param name='outputFormat' value='cool' /> 178 <param name="outputFormat" value="cool" />
179 <param name='outBam' value="True" /> 179 <param name="outBam" value="True" />
180 <output name="outfileBam" file="small_test_matrix_result_sorted.bam" ftype="bam" /> 180 <output name="outfileBam" file="small_test_matrix_result_sorted.bam" ftype="bam" />
181 <output name="outFileName" ftype="cool"> 181 <output name="outFileName" ftype="cool">
182 <assert_contents> 182 <assert_contents>
183 <has_h5_keys keys='bins,chroms,indexes,pixels' /> 183 <has_h5_keys keys="bins,chroms,indexes,pixels" />
184 </assert_contents> 184 </assert_contents>
185 </output> 185 </output>
186 <output name="raw_qc" file='raw_qc_report' compare='diff' lines_diff='2' /> 186 <output name="raw_qc" file="raw_qc_report" compare="diff" lines_diff="2" />
187 </test> 187 </test>
188 </tests> 188 </tests>
189 <help><![CDATA[ 189 <help><![CDATA[
190 190
191 Creation of the contact matrix 191 Creation of the contact matrix