Mercurial > repos > yating-l > bedgraph_to_bigwig_340

changeset 0:3290b79cd9f3 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload
author yating-l
date Wed, 17 May 2017 16:28:29 -0400
parents
children
files bedgraph_to_bigwig.xml test-data/contigs.bedgraph test-data/contigs.bedgraph.bw test-data/contigs.bedgraph_advanced.bw test-data/contigs.bedgraph_clip.bw test-data/contigs.clip.bedgraph test-data/contigs_chromInfo.tab tool_dependencies.xml ucsc_macros.xml
diffstat 9 files changed, 287 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bedgraph_to_bigwig.xml	Wed May 17 16:28:29 2017 -0400
@@ -0,0 +1,128 @@
+<?xml version="1.0"?>
+<tool id="bedgraph_to_bigwig" name="bedGraphToBigWig" version="1.0">
+    <description>Converts a bedGraph file to bigWig format</description>
+
+    <macros>
+        <import>ucsc_macros.xml</import>
+    </macros>
+
+    <requirements>
+        <requirement type="package" version="340">ucsc_bigwig</requirement>
+        <requirement type="package" version="340">ucsc_bigbed</requirement>
+    </requirements>
+
+    <command detect_errors="exit_code">
+<![CDATA[
+    @OPTIONAL_PARAM_FUNC@
+
+    ## Allow UCSC track and browser lines in input file
+    awk '$0 !~ /^(track|browser) /' "${bedgraph_input}" |
+
+        #if str($bed_clip) == "bedClip":
+            bedClip -verbose=2
+                stdin "${chrominfo_input}" stdout |
+        #end if
+
+        sort -k 1,1 -k 2,2n  > "${bedgraph_input}".sorted &&
+
+        bedGraphToBigWig
+            $optional_param("-blockSize", $adv.block_size)
+            $optional_param("-itemsPerSlot", $adv.items_per_slot)
+            ${adv.no_compression}
+            "${bedgraph_input}".sorted "${chrominfo_input}" "${bw_output}"
+]]>
+    </command>
+
+    <expand macro="environment_LC_COLLATE" />
+
+    <inputs>
+        <param name="bedgraph_input" type="data" format="bedgraph"
+                label="bedGraph input file" />
+
+        <param name="chrominfo_input" type="data" format="tabular"
+                label="Chromosomes sizes file" />
+
+        <param name="bed_clip" type="boolean" checked="false"
+                truevalue="bedClip" falsevalue=""
+                label="Remove BED items that extend beyond the scaffolds"
+                help="bedClip" />
+
+        <section name="adv" title="Advanced options" expanded="false">
+            <param name="block_size" type="integer" label="Block size"
+                    min="1" optional="true"
+                    help="Number of items to bundle in r-tree" />
+
+            <param name="items_per_slot" type="integer" label="Items per slot"
+                    min="1" optional="true"
+                    help="Number of data points bundled at the lowest level" />
+
+            <param name="no_compression" type="boolean" checked="false"
+                    truevalue="-unc" falsevalue=""
+                    label="Do not use compression"
+                    help="-unc" />
+        </section>
+    </inputs>
+    <outputs>
+        <data name="bw_output" format="bigwig" />
+    </outputs>
+    <tests>
+        <test>
+            <!-- Test bedGraphToBigWig with default settings -->
+            <param name="bedgraph_input" value="contigs.bedgraph" ftype="bedgraph" />
+            <param name="chrominfo_input" value="contigs_chromInfo.tab" ftype="tabular" />
+            <output name="bw_output" file="contigs.bedgraph.bw" />
+        </test>
+        <test>
+            <!-- Test bedGraphToBigWig with advanced options -->
+            <param name="bedgraph_input" value="contigs.bedgraph" ftype="bedgraph" />
+            <param name="chrominfo_input" value="contigs_chromInfo.tab" ftype="tabular" />
+            <param name="block_size" value="200" />
+            <param name="items_per_slot" value="500" />
+            <param name="no_compression" value="-unc" />
+            <output name="bw_output" file="contigs.bedgraph_advanced.bw" />
+        </test>
+        <test>
+            <!-- Test bedGraphToBigWig with default settings -->
+            <param name="bedgraph_input" value="contigs.clip.bedGraph" ftype="bedgraph" />
+            <param name="chrominfo_input" value="contigs_chromInfo.tab" ftype="tabular" />
+            <param name="bed_clip" value="bedClip" />
+            <output name="bw_output" file="contigs.bedgraph_clip.bw" />
+        </test>
+    </tests>
+    <help>
+<![CDATA[
+**What it does**
+
+bedGraphToBigWig converts a `bedGraph <https://genome.ucsc.edu/goldenpath/help/bedgraph.html>`_ file
+to the `bigWig format <https://genome.ucsc.edu/goldenpath/help/bigWig.html>`_.
+
+----
+
+**The bedGraph format**
+
+The first three columns of the bedGraph file are the same as the
+`BED format <https://genome.ucsc.edu/FAQ/FAQformat.html#format1>`_, and it uses
+a `zero-start, half-open <http://genome.ucsc.edu/blog/the-ucsc-genome-browser-coordinate-counting-systems/>`_
+coordinate system. The fourth column of the bedGraph file contains the data values::
+
+    chromA chromStartA chromEndA dataValueA
+    chromB chromStartB chromEndB dataValueB
+
+----
+
+.. class:: infomark
+
+**Chromosomes sizes file**
+
+This tool requires a chromosomes sizes (``chrom.sizes``) file, which lists the size of
+each scaffold within an assembly. For genome assemblies that are hosted by UCSC,
+the ``chrom.sizes`` file is available through the
+`Sequence and Annotation Downloads <http://hgdownload.cse.ucsc.edu/downloads.html>`_ page.
+The `twoBitInfo <https://genome.ucsc.edu/goldenpath/help/twoBit.html>`_ tool
+can be used to generate the ``chrom.sizes`` for the genome assemblies that are not hosted
+by UCSC.
+
+    ]]></help>
+
+    <expand macro="citations" />
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/contigs.bedgraph	Wed May 17 16:28:29 2017 -0400
@@ -0,0 +1,51 @@
+track name="bedGraph" description="bedGraph"
+contig10	0	173	0
+contig10	173	188	1
+contig10	188	206	2
+contig10	206	208	1
+contig10	208	221	2
+contig10	221	223	1
+contig10	223	248	2
+contig10	248	275	3
+contig10	275	279	2
+contig10	279	281	1
+contig10	281	286	2
+contig10	286	290	3
+contig10	290	350	2
+contig10	350	366	1
+contig10	1002	1008	8
+contig10	1008	1009	7
+contig10	1009	1010	8
+contig10	1010	1028	9
+contig10	1028	1032	10
+contig10	1032	1040	9
+contig10	1040	1041	7
+contig10	1041	1042	8
+contig10	1042	1059	10
+contig10	1059	1074	9
+contig10	1074	1075	4
+contig10	1075	1078	3
+contig10	1078	1082	2
+contig10	1082	1095	3
+contig10	1095	1102	2
+contig10	1102	1131	1
+contig10	4843	4846	4
+contig10	4846	4855	5
+contig10	4855	4856	6
+contig10	4856	4858	7
+contig10	4858	4863	8
+contig10	4863	4864	9
+contig12	40351	40352	149
+contig12	40352	40353	151
+contig12	40353	40354	153
+contig12	40354	40355	155
+contig12	40355	40356	156
+contig12	40356	40357	160
+contig12	40357	40358	163
+contig12	40358	40359	169
+contig12	40359	40360	175
+contig12	40360	40361	176
+contig12	54693	54694	8
+contig12	54694	54985	0
+contig12	54985	55008	1
+contig12	55008	55085	2
Binary file test-data/contigs.bedgraph.bw has changed
Binary file test-data/contigs.bedgraph_advanced.bw has changed
Binary file test-data/contigs.bedgraph_clip.bw has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/contigs.clip.bedgraph	Wed May 17 16:28:29 2017 -0400
@@ -0,0 +1,53 @@
+track name="bedGraph" description="bedGraph"
+contig10	0	173	0
+contig10	173	188	1
+contig10	188	206	2
+contig10	206	208	1
+contig10	208	221	2
+contig10	221	223	1
+contig10	223	248	2
+contig10	248	275	3
+contig10	275	279	2
+contig10	279	281	1
+contig10	281	286	2
+contig10	286	290	3
+contig10	290	350	2
+contig10	350	366	1
+contig10	1002	1008	8
+contig10	1008	1009	7
+contig10	1009	1010	8
+contig10	1010	1028	9
+contig10	1028	1032	10
+contig10	1032	1040	9
+contig10	1040	1041	7
+contig10	1041	1042	8
+contig10	1042	1059	10
+contig10	1059	1074	9
+contig10	1074	1075	4
+contig10	1075	1078	3
+contig10	1078	1082	2
+contig10	1082	1095	3
+contig10	1095	1102	2
+contig10	1102	1131	1
+contig10	4843	4846	4
+contig10	4846	4855	5
+contig10	4855	4856	6
+contig10	4856	4858	7
+contig10	4858	4863	8
+contig10	4863	4864	9
+contig10	43000	43200	10
+contig12	40351	40352	149
+contig12	40352	40353	151
+contig12	40353	40354	153
+contig12	40354	40355	155
+contig12	40355	40356	156
+contig12	40356	40357	160
+contig12	40357	40358	163
+contig12	40358	40359	169
+contig12	40359	40360	175
+contig12	40360	40361	176
+contig12	54693	54694	8
+contig12	54694	54985	0
+contig12	54985	55008	1
+contig12	55008	55085	2
+contig12	56000	56100	2
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/contigs_chromInfo.tab	Wed May 17 16:28:29 2017 -0400
@@ -0,0 +1,2 @@
+contig10	43013
+contig12	56019
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Wed May 17 16:28:29 2017 -0400
@@ -0,0 +1,9 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="ucsc_bigwig" version="340">
+        <repository changeset_revision="06411298fa7d" name="package_ucsc_bigwig_340" owner="yating-l" toolshed="https://testtoolshed.g2.bx.psu.edu" />
+    </package>
+    <package name="ucsc_bigbed" version="340">
+        <repository changeset_revision="dd9b230c079d" name="package_ucsc_bigbed_340" owner="yating-l" toolshed="https://testtoolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/ucsc_macros.xml	Wed May 17 16:28:29 2017 -0400
@@ -0,0 +1,44 @@
+<macros>
+    <xml name="requirements_twobit">
+        <requirements>
+            <requirement type="package" version="340">ucsc_twobit</requirement>
+            <yield />
+        </requirements>
+    </xml>
+    <xml name="environment_LC_COLLATE">
+        <environment_variables>
+            <!-- Sort uppercase letters before lowercase (required by UCSC tools) -->
+            <environment_variable name="LC_COLLATE">C</environment_variable>
+            <yield />
+        </environment_variables>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="bibtex">
+        @article{Kent01062002,
+author = {Kent, W. James and Sugnet, Charles W. and Furey, Terrence S. and Roskin, Krishna M. and Pringle, Tom H. and Zahler, Alan M. and Haussler,  and David},
+title = {The Human Genome Browser at UCSC},
+volume = {12},
+number = {6},
+pages = {996-1006},
+year = {2002},
+doi = {10.1101/gr.229102},
+URL = {http://genome.cshlp.org/content/12/6/996.abstract},
+eprint = {http://genome.cshlp.org/content/12/6/996.full.pdf+html},
+journal = {Genome Research}
+}
+            </citation>
+            <yield />
+        </citations>
+    </xml>
+
+    <token name="@OPTIONAL_PARAM_FUNC@">
+<![CDATA[
+        #def optional_param($_flag, $_flag_value, $_sep="=")
+            #if str($_flag_value) and str($_flag_value).strip():
+                ${_flag}${_sep}${_flag_value}
+            #end if
+        #end def
+]]>
+    </token>
+</macros>