Mercurial > repos > bgruening > hicexplorer_hicfindtads

comparison hicFindTADs.xml @ 2:a9c1d76b90c4 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/maxplanck-ie/HiCExplorer/tree/master/galaxy/wrapper/ commit 4d61b6bf2fed275ab38c226d0c4390b095a38251
author bgruening
date Thu, 02 Nov 2017 11:13:55 -0400
parents aab371aa615e
children 8b60271e7e54
comparison
equal deleted inserted replaced
1:72883c28fdcd 2:a9c1d76b90c4
3 <macros> 3 <macros>
4 <token name="@BINARY@">hicFindTADs</token> 4 <token name="@BINARY@">hicFindTADs</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><![CDATA[ 8 <command detect_errors="exit_code"><![CDATA[
9 #if $mode.mode_selector == 'TAD_score': 9
10 ln -s '$mode.matrix' matrix.npz.h5 && 10 hicFindTADs
11 #end if 11 --matrix '$matrix'
12
13 --delta $delta
12 14
13 #if $mode.mode_selector == 'find_TADs': 15 #if $minBoundaryDistance:
14 ln -s '$tad_score_zscore_matrix' ./tadScoreFile.tabular_zscore_matrix.h5 && 16 --minBoundaryDistance $minBoundaryDistance
15 #end if 17 #end if
16 18 --minDepth $minDepth
17 hicFindTADs 19 --maxDepth $maxDepth
18 $mode.mode_selector 20 --step $step
19 21 #if $multiple_comparison_conditional.multiple_comparison_selector == 'fdr':
20 #if $mode.mode_selector == 'find_TADs': 22 --correctForMultipleTesting fdr
21 --tadScoreFile '$tadScoreFile' 23 --threshold $multiple_comparison_conditional.threshold
22 --outPrefix galaxy_tad_prefix 24 #elif $multiple_comparison_conditional.multiple_comparison_selector == 'bonferroni':
23 ##--maxThreshold $mode.maxThreshold 25 --correctForMultipleTesting bonferroni
24 --delta $mode.delta 26 --threshold $multiple_comparison_conditional.threshold
25 --pvalue $mode.pvalue 27 #else:
26 #if $mode.minBoundaryDistance: 28 --multipleComparisons None
27 --minBoundaryDistance $mode.minBoundaryDistance
28 #end if 29 #end if
29 30
30 #else: 31 --numberOfProcessors @THREADS@
31 --matrix matrix.npz.h5 32 --outPrefix galaxy_tad_prefix
32 --maxDepth $mode.maxDepth
33 --minDepth $mode.minDepth
34 --outFileName ./tadScoreFile.tabular
35
36 --step $mode.step
37 #end if
38
39 ]]></command> 33 ]]></command>
40 <inputs> 34 <inputs>
35 <param argument="--matrix" type="data" format="h5" label="Corrected Hi-C matrix to use for the computations"/>
36 <param argument="--minDepth" type="integer" value="40000"
37 label="Minimum window length (in bp) to be considered to the left and to the right of each Hi-C bin."
38 help="This number should be at least 3 times as large as the bin size of the Hi-C matrix."/>
39 <param argument="--maxDepth" type="integer" value="100000"
40 label="Maximum window length (in bp) to be considered to the left and to the right of each Hi-C bin."
41 help="This number should around 6-10 times as large as the bin size of the Hi-C matrix."/>
42 <param argument="--step" type="integer" value="10000"
43 label="Step size when moving from minDepth to maxDepth"
44 help="The step size grows exponentially as maxDeph + (step * int(x)**1.5) for x in [0, 1, ...]
45 until it reaches maxDepth. For example, selecting step=10,000, minDepth=20,000
46 and maxDepth=150,000 will compute TAD-scores for window sizes:
47 20,000, 30,000, 40,000, 70,000 and 100,000"/>
48 <conditional name="multiple_comparison_conditional">
49 <param name="multiple_comparison_selector" type="select" label="Multiple Testing Corrections" >
50 <option value="fdr" selected="True">False discovery rate</option>
51 <option value="bonferroni">Bonferroni correction</option>
52 <option value="None">No correction</option>
53 </param>
54 <when value="fdr">
55 <param name="threshold" type="float" value="0.01" label="q-value" />
56 </when>
57 <when value="bonferroni">
58 <param name="threshold" type="float" value="0.01" label="p-value" />
59 </when>
60 <when value="None" />
61 </conditional>
62 <param argument="--delta" type="float" value="0.001" optional="True"
63 label="Minimum threshold of the difference between the TAD-separation score of a putative boundary and the mean of the TAD-sep. score of surrounding bins."
64 help="The delta value reduces spurious boundaries that are shallow, which usually
65 occur at the center of large TADs when the TAD-sep. score is flat. Higher
66 delta threshold values produce more conservative boundary estimations. By
67 default, multiple delta thresholds are saved for the following delta
68 values: 0.001, 0.01, 0.03, 0.05, 0.1. Other single or multiple values
69 can be given."/>
41 70
42 <conditional name="mode"> 71 <param argument="--minBoundaryDistance" type="integer" value="" optional="True"
43 <param name="mode_selector" type="select" label="Range restriction (in bp)" argument="--range"> 72 label="Minimum distance between boundaries (in bp)."
44 <option value="find_TADs">find TADs</option> 73 help="This parameter can be used to reduce spurious boundaries caused by noise. "/>
45 <option value="TAD_score">TAD score</option>
46 </param>
47 <when value="find_TADs">
48 <param argument="--tadScoreFile" type="data" format="tabular" label="TAD score file"/>
49 <param name="tad_score_zscore_matrix" type="data" format="h5" label="TAD score Matrix file"/>
50
51 <param argument="--delta" type="float" value="0.001" optional="True"
52 label="Minimum threshold of the difference between the TAD-separation score of a putative boundary and the mean of the TAD-sep. score of surrounding bins."
53 help="The delta value reduces spurious boundaries that are shallow, which usually
54 occur at the center of large TADs when the TAD-sep. score is flat. Higher
55 delta threshold values produce more conservative boundary estimations. By
56 default, multiple delta thresholds are saved for the following delta
57 values: 0.001, 0.01, 0.03, 0.05, 0.1. Other single or multiple values
58 can be given."/> <param argument="--pvalue" type="float" value="0.01"
59 label="P-value threshold"
60 help="The probability of a local minima to be a boundary is estimated by comparing the distribution (Wilcoxon ranksum) of the
61 zscores between the left and right regions (diamond) at the local minimum with the matrix zscores for a diamond at
62 --minDepth to the left and a diamond --minDepth to the right.
63 The reported pvalue is the Bonferroni correction all pvalues."/>
64 <param argument="--minBoundaryDistance" type="integer" value="" optional="True"
65 label="Minimum distance between boundaries (in bp)."
66 help="This parameter can be used to reduce spurious boundaries caused by noise. "/>
67
68 </when>
69 <when value="TAD_score">
70
71 <param argument="--matrix" type="data" format="h5" label="Corrected Hi-C matrix to use for the computations"/>
72 <param argument="--minDepth" type="integer" value="30000"
73 label="Minimum window length (in bp) to be considered to the left and to the right of each Hi-C bin."
74 help="This number should be at least 3 times as large as the bin size of the Hi-C matrix."/>
75 <param argument="--maxDepth" type="integer" value="100000"
76 label="Maximum window length (in bp) to be considered to the left and to the right of each Hi-C bin."
77 help="This number should around 6-10 times as large as the bin size of the Hi-C matrix."/>
78 <param argument="--step" type="integer" value="10000"
79 label="Step size when moving from minDepth to maxDepth"
80 help="The step size grows exponentially as `maxDeph + (step * int(x)**1.5) for x in [0, 1, ...]`
81 until it reaches `maxDepth`. For example, selecting step=10,000, minDepth=20,000
82 and maxDepth=150,000 will compute TAD-scores for window sizes:
83 20,000, 30,000, 40,000, 70,000 and 100,000"/>
84 </when>
85 </conditional>
86
87 74
88 </inputs> 75 </inputs>
89 <outputs> 76 <outputs>
90 <data name="outFileName" from_work_dir="tadScoreFile.tabular" format="tabular"> 77
91 <filter>mode['mode_selector'] == "TAD_score"</filter>
92 </data>
93 <data name="tad_score_zscore_matrix" from_work_dir="tadScoreFile.tabular_zscore_matrix.h5" format="h5">
94 <filter>mode['mode_selector'] == "TAD_score"</filter>
95 </data>
96 <data name="boundaries" from_work_dir="galaxy_tad_prefix_boundaries.bed" format="bed" 78 <data name="boundaries" from_work_dir="galaxy_tad_prefix_boundaries.bed" format="bed"
97 label="${tool.name} on ${on_string}: Boundary positions"> 79 label="${tool.name} on ${on_string}: Boundary positions" />
98 <filter>mode['mode_selector'] == "find_TADs"</filter> 80
99 </data>
100 <data name="score" from_work_dir="galaxy_tad_prefix_score.bedgraph" format="bedgraph" 81 <data name="score" from_work_dir="galaxy_tad_prefix_score.bedgraph" format="bedgraph"
101 label="${tool.name} on ${on_string}: Matrix with multi-scale TAD scores"> 82 label="${tool.name} on ${on_string}: Matrix with multi-scale TAD scores" />
102 <filter>mode['mode_selector'] == "find_TADs"</filter>
103 </data>
104 <data name="domains" from_work_dir="galaxy_tad_prefix_domains.bed" format="bed" 83 <data name="domains" from_work_dir="galaxy_tad_prefix_domains.bed" format="bed"
105 label="${tool.name} on ${on_string}: TAD domains"> 84 label="${tool.name} on ${on_string}: TAD domains" />
106 <filter>mode['mode_selector'] == "find_TADs"</filter>
107 </data>
108 <data name="boundaries_bin" from_work_dir="galaxy_tad_prefix_boundaries.gff" 85 <data name="boundaries_bin" from_work_dir="galaxy_tad_prefix_boundaries.gff"
109 format="bed" label="${tool.name} on ${on_string}: Boundary information plus score"> 86 format="gff" label="${tool.name} on ${on_string}: Boundary information plus score" />
110 <filter>mode['mode_selector'] == "find_TADs"</filter> 87
111 </data> 88 <data name="tad_score" from_work_dir="galaxy_tad_prefix_tad_score.bm"
89 format="bedgraph" label="${tool.name} on ${on_string}: TAD information in bm file" />
90
91 <data name="matrix_output" from_work_dir="galaxy_tad_prefix_zscore_matrix.h5"
92 format="h5" label="${tool.name} on ${on_string}: Z-score matrix in h5" />
112 </outputs> 93 </outputs>
113 <tests> 94 <tests>
114 <!--test> 95 <test>
115 <param name="matrix" value="hicBuildMatrix_result1.h5" ftype="h5"/> 96 <param name="matrix" value="small_test_matrix.h5" ftype="h5" />
116 <param name="mode_selector" value="TAD_score"/> 97 <param name="minDepth" value="60000"/>
117 <param name="minDepth" value="20000"/> 98 <param name="maxDepth" value="180000"/>
118 <param name="maxDepth" value="60000"/> 99 <param name="step" value="20000"/>
119 <param name="step" value="100000"/> 100 <param name="minBoundaryDistance" value="20000" />
120 <output name="outFileName" file="hicFindTADs_TAD_score.tabular" ftype="tabular"/> 101 <conditional name="multiple_comparison_conditional">
121 <output name="tad_score_zscore_matrix" file="tadScoreFile.tabular_zscore_matrix.h5" ftype="h5" compare="sim_size"/> 102 <param name="multiple_comparison_selector" value="fdr"/>
103 <param name="threshold" value="0.1" />
104 </conditional>
105 <output name="boundaries" file="find_TADs/multiFDR_boundaries.bed" ftype="bed" compare="sim_size" delta="35000" />
106 <output name="boundaries_bin" file="find_TADs/multiFDR_boundaries.gff" ftype="gff" compare="sim_size" delta="35000" />
107 <output name="domains" file="find_TADs/multiFDR_domains.bed" ftype="bed" compare="sim_size" delta="35000" />
108 <output name="score" file="find_TADs/multiFDR_score.bedgraph" ftype="bedgraph" compare="sim_size" delta="35000" />
109 <output name="tad_score" file="find_TADs/multiFDR_tad_score.bm" ftype="bedgraph" compare="sim_size" delta="35000" />
110 <output name="matrix_output" file="find_TADs/multiFDR_zscore_matrix.h5" ftype="h5" compare="sim_size" delta="50000" />
122 </test> 111 </test>
123 <test>
124 <param name="tadScoreFile" value="hicFindTADs_TAD_score.tabular" ftype="tabular"/>
125 <param name="tad_score_zscore_matrix" value="tadScoreFile.tabular_zscore_matrix.h5" ftype="h5"/>
126 <param name="mode_selector" value="find_TADs"/>
127 <param name="delta" value="0.002"/>
128 <param name="pvalue" value="0.01"/>
129
130 <output name="boundaries" file="hicFindTADs_find_boundaries.bed" ftype="bed"/>
131 <output name="score" file="hicFindTADs_find_score.bedgraph" ftype="bedgraph"/>
132 <output name="domains" file="hicFindTADs_find_domains.bed" ftype="bed"/>
133 <output name="boundaries_bin" file="hicFindTADs_find_boundaries.gff" ftype="gff"/>
134 </test-->
135 </tests> 112 </tests>
136 <help><![CDATA[ 113 <help><![CDATA[
137 114
138 **What it does** 115 **What it does**
139 116