Mercurial > repos > jetbrains > span

comparison span.xml @ 3:4130e95bd6c8 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Batch processing mode supported
author jetbrains
date Mon, 19 Nov 2018 08:24:04 -0500
parents 5b99943c4627
children d87ecbc477d8
comparison
equal deleted inserted replaced
2:5b99943c4627 3:4130e95bd6c8
7 <!-- Wrapper ensures anything other than zero is an error --> 7 <!-- Wrapper ensures anything other than zero is an error -->
8 <exit_code range="1:"/> 8 <exit_code range="1:"/>
9 <exit_code range=":-1"/> 9 <exit_code range=":-1"/>
10 </stdio> 10 </stdio>
11 <command interpreter="python"> 11 <command interpreter="python">
12 #import re
13 #set treatment_identifier = re.sub('[^\w\-\.]', '_', str($treatment_file.element_identifier))
14 #set genome_identifier = re.sub('[^\w\-\.]', '_', str($genome_file.element_identifier))
15
16 #if $control.control_selector
17 #set control_identifier = re.sub('[^\w\-\.]', '_', str($control.control_file.element_identifier))
18 #end if
19
20 #if str($action.action_selector) == "model" 12 #if str($action.action_selector) == "model"
21 #if $control.control_selector 13 #if str($control_file) != 'None':
22 span_wrapper.py model with_control 14 span_wrapper.py model_with_control
23 "${genome_identifier}" "${genome_file}" 15 "${genome_file.name}" "${genome_file}"
24 "${treatment_identifier}" "${treatment_file}" 16 "${treatment_file.name}" "${treatment_file}"
25 "${bin}" "${action.model_file}" 17 "${control_file.name}" "${control_file}"
26 "${control_identifier}" "${control.control_file}" 18 "${bin}"
27 #else 19 #else
28 span_wrapper.py model without_control 20 span_wrapper.py model_without_control
29 "${genome_identifier}" "${genome_file}" 21 "${genome_file.name}" "${genome_file}"
30 "${treatment_identifier}" "${treatment_file}" 22 "${treatment_file.name}" "${treatment_file}"
31 "${bin}" "${action.model_file}" 23 "${bin}"
32 #end if 24 #end if
33 #else 25 #else
34 #if $control.control_selector 26 #if str($control_file) != 'None':
35 span_wrapper.py peaks with_control 27 span_wrapper.py peaks_with_control
36 "${genome_identifier}" "${genome_file}" 28 "${genome_file.name}" "${genome_file}"
37 "${treatment_identifier}" "${treatment_file}" 29 "${treatment_file.name}" "${treatment_file}"
38 "${bin}" "${action.model_file}" 30 "${control_file.name}" "${control_file}"
39 "${control_identifier}" "${control.control_file}" 31 "${bin}"
40 "${action.fdr}" "${action.gap}" "${action.peaks_file}" 32 "${action.fdr}" "${action.gap}"
41 #else 33 #else
42 span_wrapper.py peaks without_control 34 span_wrapper.py peaks_without_control
43 "${genome_identifier}" "${genome_file}" 35 "${genome_file.name}" "${genome_file}"
44 "${treatment_identifier}" "${treatment_file}" 36 "${treatment_file.name}" "${treatment_file}"
45 "${bin}" "${action.model_file}" 37 "${bin}"
46 "${action.fdr}" "${action.gap}" "${action.peaks_file}" 38 "${action.fdr}" "${action.gap}"
47 #end if 39 #end if
48 #end if 40 #end if
49 </command> 41 </command>
50 <inputs> 42 <inputs>
51 <param name="treatment_file" type="data" format="bam" label="Treatment BAM" 43 <param name="treatment_file" type="data" format="bam" label="Treatment BAM"
52 description="Treatment BAM reads to process" argument="--treatment" 44 description="Treatment BAM reads to process" argument="--treatment"
53 help="Treatment BAM reads to process"/> 45 help="Treatment BAM reads to process"/>
46
47 <param name="control_file" type="data" format="BAM" label="Control BAM" optional="True"
48 argument="--control" help="Control BAM reads to process"/>
49
54 <param name="genome_file" type="data" format="chrom.sizes" label="Genome chrom.sizes" 50 <param name="genome_file" type="data" format="chrom.sizes" label="Genome chrom.sizes"
55 description="Genome build chrom.sizes file" argument="--chrom.sizes" 51 description="Genome build chrom.sizes file" argument="--chrom.sizes"
56 help="Genome build chrom.sizes file"/> 52 help="Genome build chrom.sizes file"/>
57
58 <conditional name="control">
59 <param name="control_selector" type="boolean" label="Control available" value="false"/>
60 <when value="true">
61 <param name="control_file" type="data" format="bam" label="Control BAM"
62 description="Control BAM reads to process" argument="--control"
63 help="Control BAM reads to process"/>
64 </when>
65 </conditional>
66 53
67 <conditional name="action"> 54 <conditional name="action">
68 <param name="action_selector" type="select" label="Action"> 55 <param name="action_selector" type="select" label="Action">
69 <option value="model">Compute SPAN model</option> 56 <option value="model">Compute SPAN model</option>
70 <option value="peaks">Compute SPAN model and produce peaks file</option> 57 <option value="peaks">Compute SPAN model and produce peaks file</option>
71 </param> 58 </param>
72 <when value="model">
73 <param name="model_file" type="text" value="model.span" label="Model name"
74 help="Trained model file in binary format, which can be visualized directly in JBR Genome Browser
75 and used in integrated peak calling pipeline"/>
76 </when>
77 <when value="peaks"> 59 <when value="peaks">
78 <param name="model_file" type="text" value="model.span" label="Model file name"
79 help="Trained model file in binary format, which can be visualized directly in JBR Genome Browser
80 and used in integrated peak calling pipeline"/>
81 <param name="fdr" size="5" type="float" value="0.0001" label="FDR" argument="--fdr" 60 <param name="fdr" size="5" type="float" value="0.0001" label="FDR" argument="--fdr"
82 help="Minimum FDR cutoff to call significant regions, default value is 1.0E-6. 61 help="Minimum FDR cutoff to call significant regions, default value is 1.0E-6.
83 SPAN reports p- and q- values for the null hypothesis that a given bin is not enriched with a histone modification. 62 SPAN reports p- and q- values for the null hypothesis that a given bin is not enriched with a histone modification.
84 Peaks are formed from a list of truly (in the FDR sense) enriched bins for the analyzed biological condition by thresholding the 63 Peaks are formed from a list of truly (in the FDR sense) enriched bins for the analyzed biological condition by thresholding the
85 Q-value with a cutoff FDR and merging spatially close peaks using GAP option to broad ones. This is equivalent to controlling FDR. 64 Q-value with a cutoff FDR and merging spatially close peaks using GAP option to broad ones. This is equivalent to controlling FDR.
86 q-values are are calculated from p-values using Benjamini-Hochberg procedure."/> 65 q-values are are calculated from p-values using Benjamini-Hochberg procedure."/>
87 <param name="gap" size="5" type="integer" value="5" label="GAP" argument="--gap" 66 <param name="gap" size="5" type="integer" value="5" label="GAP" argument="--gap"
88 help="Gap size to merge spatially close peaks. Useful for wide histone modifications. 67 help="Gap size to merge spatially close peaks. Useful for wide histone modifications.
89 Default value is 5, i.e. peaks separated by 5*BIN distance or less are merged."/> 68 Default value is 5, i.e. peaks separated by 5*BIN distance or less are merged."/>
90 <param name="peaks_file" type="text" value="result.peak" label="Peaks file name" argument="--peaks"/>
91 </when> 69 </when>
92 </conditional> 70 </conditional>
93 71
94 <param name="bin" size="5" type="integer" value="200" label="Bin size" argument="--bin" 72 <param name="bin" size="5" type="integer" value="200" label="Bin size" argument="--bin"
95 help="Peak analysis is performed on read coverage tiled into consequent bins, with size being configurable. 73 help="Peak analysis is performed on read coverage tiled into consequent bins, with size being configurable.
96 Default value is 200bp, approximately the length of one nucleosome."/> 74 Default value is 200bp, approximately the length of one nucleosome."/>
97 </inputs> 75 </inputs>
98 <outputs> 76 <outputs>
99 <data name="SPAN model file" format="span" from_work_dir="*.span" label="SPAN model file ${action.model_file} on ${on_string}"/> 77 <data name="model.span" format="span" from_work_dir="*.span"
100 <data name="SPAN peaks file" format="bed" from_work_dir="*.peak" label="SPAN peaks file ${action.peaks_file} on ${on_string}"> 78 label="SPAN model on ${on_string} (${treatment_file.name}#if str($control_file) != 'None' then '_{}'.format($control_file.name) else '' #_${bin})"/>
79 <data name="result.peak" format="bed" from_work_dir="*.peak"
80 label="SPAN peaks on ${on_string} (${treatment_file.name}#if str($control_file) != 'None' then '_{}'.format($control_file.name) else '' #_${bin}_${action.fdr}_${action.gap})">
101 <filter>action['action_selector'] == "peaks"</filter> 81 <filter>action['action_selector'] == "peaks"</filter>
102 </data> 82 </data>
103 <data name="SPAN log file" format="txt" from_work_dir="*.log" label="SPAN log file on ${on_string}"/> 83 <data name="span.log" format="txt" from_work_dir="*.log" label="SPAN logs on ${on_string}"/>
104 </outputs> 84 </outputs>
105 <help><![CDATA[ 85 <help><![CDATA[
106 .. class:: infomark 86 .. class:: infomark
107 87
108 **What it does** 88 **What it does**
132 112
133 ----- 113 -----
134 114
135 **Outputs** 115 **Outputs**
136 116
137 This tool produces a SPAN binary model file and/or peaks in ENCODE broadPeak (BED 6+3) format. 117 This tool produces a SPAN binary model file (can be visualized in JBR Genome Browser and used in semi-supervised peak calling) and/or peaks in ENCODE broadPeak (BED 6+3) format.
138 118
139 Peak file columns contain the following data: 119 Peak file columns contain the following data:
140 120
141 * **1st**: chromosome name 121 * **1st**: chromosome name
142 * **2nd**: start position of peak 122 * **2nd**: start position of peak