Mercurial > repos > pjbriggs > ceas

changeset 0:8b25779ee261 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded initial version to test toolshed.
author pjbriggs
date Wed, 28 Jan 2015 04:50:01 -0500
parents
children d9032bb158b9
files README.markdown ceasbw_wrapper.sh ceasbw_wrapper.xml tool-data/ceas.loc.sample tool_data_table_conf.xml.sample tool_dependencies.xml
diffstat 6 files changed, 294 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/README.markdown	Wed Jan 28 04:50:01 2015 -0500
@@ -0,0 +1,39 @@
+CEASbw
+======
+
+XML and wrapper script for the Cistrome version of the CEAS package, which can be
+used to annotate intervals and scores with genome features.
+
+In addition to the `ceas` program, the Cistrome version of the package includes the
+`ceasBW` program which can handle
+
+The tool assumes that the `ceas` and `ceasBW` programs are on the Galaxy user's
+path. The official CEAS website is at
+
+<http://liulab.dfci.harvard.edu/CEAS/index.html>
+
+the Cistrome version can be found via
+
+<https://bitbucket.org/cistrome/cistrome-applications-harvard/overview>
+
+To add to Galaxy add the following to tool_conf.xml:
+
+    <tool file="ceas/ceasbw_wrapper.xml" />
+
+You also need to make a copy of the `ceas.loc` file (sample version is provided
+here) which points to the available GDB files for different genomes. The GDB files
+are essentially SQLite database files containing the RefSeq genes for the genome
+in question.
+
+A limited number of GDB files are available for download from the CEAS website; to
+make new ones, see the section "Build a sqlite3 file with a gene annotation table
+and genome background annotation for CEAS" in the CEAS manual:
+
+<http://liulab.dfci.harvard.edu/CEAS/usermanual.html>
+
+The `ceas.loc` file should be placed in the `tool-data` directory of your Galaxy
+installation.
+
+### Changes ###
+
+1.0.2-0: first version based on our original `ceas` tool.
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/ceasbw_wrapper.sh	Wed Jan 28 04:50:01 2015 -0500
@@ -0,0 +1,78 @@
+#!/bin/sh -e
+#
+# Wrapper script to run CEASbw as a Galaxy tool
+#
+# Usage: ceasbw_wrapper.sh $BED_IN $GDB_IN $EXTRA_BED_IN $LOG_OUT $PDF_OUT $XLS_OUT $DBKEY
+#
+# Process command line
+echo $*
+BED_IN=$1
+GDB_IN=$2
+EXTRA_BED_IN=$3
+LOG_OUT=$4
+PDF_OUT=$5
+XLS_OUT=$6
+#
+# Collect remaining args
+CEAS=ceas
+OPTIONS=
+while [ ! -z "$7" ] ; do
+    if [ "$7" == "--bigwig" ] ; then
+	CEAS=ceasBW
+    fi
+    OPTIONS="$OPTIONS $7"
+    shift
+done
+#
+# Convenience variables for local files
+base_name="ceas"
+log_file=${base_name}.log
+r_script=${base_name}.R
+pdf_report=${base_name}.pdf
+xls_file=${base_name}.xls
+#
+# Get CEAS version
+echo Running $CEAS
+$CEAS --version >$log_file 2>/dev/null
+#
+# Construct and run CEAS command line
+ceas_cmd="$CEAS --name $base_name $OPTIONS -g $GDB_IN -b $BED_IN"
+if [ "$EXTRA_BED_IN" != "None" ] ; then
+    ceas_cmd="$ceas_cmd -e $EXTRA_BED_IN"
+fi
+echo "Running $ceas_cmd"
+$ceas_cmd >>$log_file 2>&1
+#
+# Move outputs to final destination
+if [ -e $log_file ] ; then
+    echo "Moving $log_file to $LOG_OUT"
+    /bin/mv $log_file $LOG_OUT
+else
+    echo ERROR failed to make log file >&2
+    exit 1
+fi
+if [ -e $xls_file ] ; then
+    echo "Moving $xls_file to $XLS_OUT"
+    /bin/mv $xls_file $XLS_OUT
+else
+    echo ERROR failed to generate XLS file >&2
+    exit 1
+fi
+#
+# Run the R script to generate the PDF report
+if [ -e $r_script ] ; then
+    echo "Running $r_script to generate $pdf_report"
+    R --vanilla < $r_script
+    if [ -e $pdf_report ] ; then
+	echo "Moving $xls_file to $XLS_OUT"
+	/bin/mv $pdf_report $PDF_OUT
+    else
+	echo ERROR failed to generate PDF report >&2
+	exit 1
+    fi
+else
+    echo ERROR no R script to generate PDF report >&2
+    exit 1
+fi
+#
+# Done
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/ceasbw_wrapper.xml	Wed Jan 28 04:50:01 2015 -0500
@@ -0,0 +1,73 @@
+<tool id="ceasbw" name="CEAS" version="1.0.2-0">
+  <description>Annotate intervals and scores with genome features (cistrome CEAS)</description>
+  <command interpreter="bash">ceasbw_wrapper.sh $bed_file $gdb_file $extra_bed_file $log_output $pdf_report $xls_output
+  #if (str($wig_file.ext) == 'bigwig')
+    --bigwig $wig_file
+    --length $GALAXY_DATA_INDEX_DIR/shared/ucsc/chrom/${bed_file.dbkey}.len
+  # else
+    --wig $wig_file
+  #end if
+  #if (str($span) and int(str($span)) > 0)
+    --span $span
+  #end if
+  --sizes $sizes_lower,$sizes_middle,$sizes_upper
+  --bisizes $bisizes_lower,$bisizes_upper
+  --pf-res $profiling_resolution
+  --rel-dist $relative_distance</command>
+  <requirements>
+    <requirement type="package" version="1.2.5">python_mysqldb</requirement>
+    <requirement type="package" version="0.7.1">bx_python</requirement>
+    <requirement type="package" version="1.0.2.d8c0751">cistrome_ceas</requirement>
+  </requirements>
+  <inputs>
+    <param name="bed_file" type="data" format="bed" label="BED file with ChIP regions" />
+    <param name="wig_file" type="data" format="wig,bigwig" label="WIG or BIGWIG file for wig profiling or genome background annotation" optional="true" />
+    <param name="extra_bed_file" type="data" format="bed" label="BED file with extra regions of interest (e.g. non-coding regions)" optional="true" />
+    <param name="gdb_file" type="select" label="Gene annotation table">
+      <options from_data_table="ceas_annotations">
+	<filter name="dbkey" type="data_meta" ref="bed_file" key="dbkey" column="0" />
+        <validator type="no_options" message="No tables are available for the selected input"/>
+      </options>
+    </param>
+    <param name="span" type="integer" label="Span from TSS and TTS in the gene-centered annotation (bp)" help="ChIP regions within this range from TSS and TTS are considered when calculating the coverage rates of promoter and downstream by ChIP regions" value="3000" />
+    <param name="sizes_lower" type="integer" label="Lower interval for promoter/downstream sizes for ChIP region annotation (bp)" value="1000" />
+    <param name="sizes_middle" type="integer" label="Middle interval for promoter/downstream sizes (bp)" value="2000" help="Values > 10000bp are automatically fixed to 10000bp" />
+    <param name="sizes_upper" type="integer" label="Upper interval for promoter/downstream sizes (bp)" value="3000" help="Values > 10000bp are automatically fixed to 10000bp" />
+    <param name="bisizes_lower" type="integer" label="Lower interval for bidirectional-promoter sizes for ChIP region annotation (bp)" value="2500" />
+    <param name="bisizes_upper" type="integer" label="Upper interval for bidirectional-promoter sizes (bp)" value="5000" help="Values > 20000bp are automatically fixed to 20000bp" />
+    <param name="profiling_resolution" type="integer" label="Wig profiling resolution (bp)" value="50" help="Warning: a number smaller than the wig interval (resolution) may cause aliasing error" />
+    <param name="relative_distance" type="integer" label="Relative distance to TSS/TTS in wig profiling (bp)" value="3000" />
+  </inputs>
+  <outputs>
+    <data name="log_output" format="txt" label="CEAS on ${on_string} (log output)" />
+    <data name="pdf_report" format="pdf" label="CEAS on ${on_string} (PDF report)" />
+    <data name="xls_output" format="interval" label="CEAS on ${on_string} (XLS output)" />
+  </outputs>
+  <help>
+**What it does**
+
+CEAS (Cis-regulatory Element Annotation System) is a tool for characterizing genome-wide
+protein-DNA interaction patterns from ChIP-chip and ChIP-Seq of both sharp and broad
+binding factors. It provides statistics on ChIP enrichment at important genome features
+such as specific chromosome, promoters, gene bodies, or exons, and infers genes most
+likely to be regulated by a binding factor.
+
+CEAS also enables biologists to visualize the average ChIP enrichment signals over
+specific genomic features, allowing continuous and broad ChIP enrichment to be perceived
+which might be too subtle to detect from ChIP peaks alone.
+
+This tool is compatible with the ceasBW version of CEAS from the Cistrome package
+obtained from
+
+https://bitbucket.org/cistrome/cistrome-applications-harvard/overview
+
+(commit id d8c0751, datestamp 20140929). The CEAS code is under the
+published-packages/CEAS/ subdirectory.
+
+Cistrome data files and documentation can be found at
+
+http://liulab.dfci.harvard.edu/CEAS/index.html
+
+The CEAS user manual is available at http://liulab.dfci.harvard.edu/CEAS/usermanual.html
+  </help>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/ceas.loc.sample	Wed Jan 28 04:50:01 2015 -0500
@@ -0,0 +1,17 @@
+#This is a sample file distributed with Galaxy that is used by the
+#ceas tool. The ceas.loc file has this format (white space 
+#characters are TAB characters):
+#
+#<dbkey> <Description>	<PathToGdbFile>
+#
+#For example:
+#
+#hg18	Human (hg18)	/home/galaxy/genomes/ceaslib/GeneTable/hg18
+#mm9	Mouse (mm9)	/home/galaxy/genomes/ceaslib/GeneTable/mm9
+#...etc...
+#
+# The GDB files are sqlite databases containing the RefSeq genes for
+# the organism in question
+#
+#This file should be placed in galaxy's tool-data directory when the
+#ceas tool is installed.
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Wed Jan 28 04:50:01 2015 -0500
@@ -0,0 +1,6 @@
+<tables>
+    <table name="ceas_annotations" comment_char="#">
+        <columns>dbkey, name, value</columns>
+        <file path="tool-data/ceas.loc" />
+    </table>
+</tables>
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Wed Jan 28 04:50:01 2015 -0500
@@ -0,0 +1,81 @@
+<?xml version="1.0"?>
+<tool_dependency>
+  <package name="python_mysqldb" version="1.2.5">
+    <install version="1.0">
+      <actions>
+	<action type="download_by_url">https://pypi.python.org/packages/source/M/MySQL-python/MySQL-python-1.2.5.zip</action>
+        <action type="make_directory">$INSTALL_DIR/lib/python</action>
+        <action type="shell_command">
+          export PYTHONPATH=$PYTHONPATH:$INSTALL_DIR/lib/python &amp;&amp; 
+          python setup.py install --install-lib $INSTALL_DIR/lib/python --install-scripts $INSTALL_DIR/bin
+        </action>
+        <action type="set_environment">
+          <environment_variable action="prepend_to" name="PYTHONPATH">$INSTALL_DIR/lib/python</environment_variable>
+          <environment_variable action="prepend_to" name="PATH">$INSTALL_DIR/bin</environment_variable>
+        </action>
+      </actions>
+    </install>
+    <readme>Installs Python module MySQLdb 1.2.5</readme>
+  </package>
+  <!-- bx_python
+       This is cribbed from devteam's 'package_bx_python_0_7' in the main
+       toolshed:
+       https://toolshed.g2.bx.psu.edu/view/devteam/package_bx_python_0_7
+  -->
+  <package name="bx_python" version="0.7.1">
+    <install version="1.0">
+      <actions>
+        <action type="setup_virtualenv">
+numpy==1.7.1
+bx-python==0.7.1
+        </action>
+        <action type="set_environment">
+          <environment_variable action="set_to" name="BX_PYTHON_PATH">$INSTALL_DIR</environment_variable>
+        </action>
+      </actions>
+    </install>
+    <readme>
+      Installation of bx-python 0.7.1 along with numpy 1.7.1. The installation can be
+      accessed via BX_PYTHON_PATH.
+    </readme>
+  </package>
+  <!-- cistrome_ceas
+       Installs the version of CEAS package found in the Cistrome
+       distribution:
+       https://bitbucket.org/cistrome/cistrome-applications-harvard/overview
+  -->
+  <package name="cistrome_ceas" version="1.0.2.d8c0751">
+    <install version="1.0">
+      <actions>
+	<action type="shell_command">
+	  hg clone https://bitbucket.org/cistrome/cistrome-applications-harvard cistrome_ceas
+	</action>
+	<action type="shell_command">
+	  hg update d8c0751
+	</action>
+        <action type="make_directory">$INSTALL_DIR/lib/python</action>
+        <action type="shell_command">
+	  cd published-packages/CEAS/
+          export PYTHONPATH=$PYTHONPATH:$INSTALL_DIR/lib/python &amp;&amp; 
+          python setup.py install --install-lib $INSTALL_DIR/lib/python --install-scripts $INSTALL_DIR/bin
+        </action>
+        <action type="set_environment">
+          <environment_variable action="prepend_to" name="PYTHONPATH">$INSTALL_DIR/lib/python</environment_variable>
+          <environment_variable action="prepend_to" name="PATH">$INSTALL_DIR/bin</environment_variable>
+        </action>
+      </actions>
+    </install>
+    <readme>Installs version 1.0.2 of CEAS from cistrome (commit id d8c0751,
+    datestamp 20140929), which includes ceasBW (a version of ceas which can
+    handle bigWig file input from MACS2.
+
+    Cistrome code is at
+    https://bitbucket.org/cistrome/cistrome-applications-harvard/overview
+      
+    The CEAS code is under the published-packages/CEAS/ subdirectory
+
+    Cistrome data files and documentation can be found at
+    http://liulab.dfci.harvard.edu/CEAS/index.html
+    </readme>
+  </package>
+</tool_dependency>