Mercurial > repos > iuc > macs2
diff macs2_callpeak.xml @ 0:9c157b556c33 draft
Uploaded
| author | iuc |
|---|---|
| date | Thu, 16 Jan 2014 13:31:17 -0500 |
| parents | |
| children | d202e3d663bb |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macs2_callpeak.xml Thu Jan 16 13:31:17 2014 -0500 @@ -0,0 +1,253 @@ +<tool id="macs2_callpeak" name="Call peaks" version="2.0.10.0"> + <description>from alignment results</description> + <requirements> + <requirement type="python-module">macs2</requirement> + <requirement type="python-module">numpy</requirement> + <requirement type="package" version="2.0.10.2">macs2</requirement> + <requirement type="package" version="1.7.1">numpy</requirement> + <!-- awk and R is missing --> + </requirements> + <command> + #set $temp_stderr = 'macs2_stderr' + macs2 callpeak + + --name "MACS2" + -t #echo ' '.join( map(str, $input_treatment_file) )# + + #if ' '.join( map(str, $input_control_file) ) != 'None': + -c #echo ' '.join( map(str, $input_control_file) )# + #end if + + #for $ifile in $input_treatment_file: + --format='$ifile.ext.upper()' + #end for + + #if $effective_genome_size_options.effective_genome_size_options_selector == 'user_defined': + --gsize $effective_genome_size_options.gsize + #else: + --gsize $effective_genome_size_options.effective_genome_size_options_selector + #end if + + --bw='$bw' + + ##advanced options + #if str( $advanced_options.advanced_options_selector ) == 'on': + --mfold $advanced_options.mfoldlo $advanced_options.mfoldhi + $advanced_options.nolambda + + #if str($advanced_options.broad_options.broad_options_selector) == '--broad': + #set $__options['broad'] = str( $advanced_options.broad_options.broad_options_selector ) + #set $__options['broad_cutoff'] = float( str( $advanced_options.broad_options.broad_cutoff ) ) + #end if + + #if str($advanced_options.broad_options.broad_options_selector) == '--broad': + --broad + --broad-cutoff='$advanced_options.broad_options.broad_cutoff' + #end if + + #else: + --mfold 10 30 + #end if + + $bdg + + ##pq value select options + #if str( $pq_options.pq_options_selector ) == 'qvalue': + --qvalue $pq_options.qvalue + #else: + --pvalue $pq_options.pvalue + #end if + + ##model options + #if str( $nomodel_type.nomodel_type_selector ) == 'nomodel': + --nomodel --shiftsize='$nomodel_type.shiftsize' + #end if + + 2> $temp_stderr; + ####################################################### + ## move files generated by callpeak command + + ## TODO + ## run R to create pdf from model script + ##if os.path.exists( os.path.join( tmp_dir, "MACS2_PREFIX_model.r" ) ): + ## cmdline = 'Rscript "MACS2_PREFIX_model.r" > "MACS2_PREFIX_model.r.log"' ) + ## proc = subprocess.Popen( args=cmdline, shell=True, cwd=tmp_dir ) + ## proc.wait() + + + ## move bed out to proper output file + ##set $file = os.path.join( $tmp_dir, "%s_peaks.bed" % $experiment_name ) + ##if os.path.exists( $file ): + ## mv $file $output_bed_file + ##end if + + ## OICR peak_xls file + ##set $file = os.path.join( $tmp_dir, "%s_peaks.xls" % $experiment_name ) + ##if os.path.exists( $file ): + ## mv $file output_peaks $output_peaks_file + ##end if + + ### peaks.encodepeaks (narrowpeaks) file + ##set $file = os.path.join ( $tmp_dir, "%s_peaks.encodePeak" % $experiment_name ) + ##if os.path.exists( $file ): + ## mv $file $output_narrowpeaks_file + + + ##parse xls files to interval files as needed + ##TODO is in working dir + #if 'peaks_interval' in str($outputs).split(','): + #set $file = os.path.join( $tmp_dir, 'MACS2_PREFIX_peaks.xls' ) + #if os.path.exists( $file ): + echo '#peaks file' > $output_xls_to_interval_peaks_file; + awk '$2-=1' $file >> $output_xls_to_interval_peaks_file; + ##xls_to_interval( create_peak_xls_file, output_xls_to_interval_peaks_file, header = 'peaks file' ) + #end if + #end if + + #if 'html' in str($outputs).split(','): + ## if output files exists, move them to the extra_files_path and create a html result page linking to them + count=`ls -1 MACS2* 2>/dev/null | wc -l`; + if [ \$count != 0 ]; + then + mkdir $output_extra_files.extra_files_path; + mv MACS2* $output_extra_files.extra_files_path; + python /home/bag/projects/github/galaxytools/macs2/dir2html.py $output_extra_files.extra_files_path $temp_stderr > $output_extra_files; + fi; + #end if + + cat $temp_stderr 2>&1 + + </command> + <inputs> + <param name="input_control_file" type="data" format="bam,sam,bed" multiple="True" optional="True" label="ChIP-Seq Control File" /> + <param name="input_treatment_file" type="data" format="bam,sam,bed" multiple="True" label="ChIP-Seq Treatment File" /> + + <conditional name="effective_genome_size_options"> + <param name="effective_genome_size_options_selector" type="select" label="Effective genome size" help="--gsize"> + <option value="3300000000">Human (3.300.000.000)</option> + <option value="3000000000">Mouse (3.000.000.000)</option> + <option value="190000000">Fly (190.000.000)</option> + <option value="130000000">Worm (130.000.000)</option> + <option value="user_defined">User defined</option> + </param> + <when value="user_defined"> + <param name="gsize" type="integer" size="12" label="Effective genome size" value=""/> + </when> + </conditional> + + <param name="bw" type="integer" label="Band width" value="300" help="(--bw)"/> + <param name="bdg" type="boolean" truevalue="-B" falsevalue="" checked="False" label="Save fragment pileup, control lambda, -log10pvalue/qvalue in bedGraph" help="Files are located in the html report."/> + + <conditional name="pq_options"> + <param name="pq_options_selector" type="select" label="Peak detection based on" help="default uses q-value"> + <option value="qvalue">q-value</option> + <option value="pvalue">p-value</option> + </param> + <when value="pvalue"> + <param name="pvalue" type="float" label="p-value cutoff for peak detection" value="1e-2" help="default: 1e-2 (--pvalue)"/> + </when> + <when value="qvalue"> + <param name="qvalue" type="float" label="q-value cutoff for peak detection" value="5e-2" help="default: 5e-2 (--qvalue)"/> + </when> + </conditional> + + <conditional name="nomodel_type"> + <param name="nomodel_type_selector" type="select" label="Build Model"> + <option value="nomodel">Do not build the shifting model (--nomodel)</option> + <option value="create_model" selected="true">Build the shifting model</option> + </param> + <when value="nomodel"> + <param name="shiftsize" type="integer" label="Arbitrary shift size in bp" value="100" help="(--shiftsize)"/> + </when> + </conditional> + + <param name="outputs" type="select" display="checkboxes" multiple="True" label="Outputs"> + <option value="peaks_bed" selected="True">Peaks as bed file</option> + <option value="html">Summary page (html)</option> + <option value="narrow">narrow Peaks</option> + <option value="broad">broad Peaks</option> + <option value="gapped">gapped Peaks</option> + <option value="summits" selected="true">summits</option> + <option value="peaks_interval">Peaks as interval file</option> + + <validator type="no_options" message="Please select at least one output file." /> + </param> + + <conditional name="advanced_options"> + <param name="advanced_options_selector" type="select" label="Advanced options"> + <option value="off">Hide advanced options</option> + <option value="on">Display advanced options</option> + </param> + <when value="on"> + <param name="mfoldlo" type="integer" label="Fold-enrichment lower limit" value="10" help="Select the regions with MFOLD high-confidence enrichment ratio against background to build model (--mfold)"/> + <param name="mfoldhi" type="integer" label="Fold-enrichment upper-limit" value="30" help="Select the regions with MFOLD high-confidence enrichment ratio against background to build model (--mfold)"/> + <param name="nolambda" label="Use fixed background lambda as local lambda for every peak region" type="boolean" truevalue="--nolambda" falsevalue="" checked="False" help="up to 9X more time consuming (--nolambda)"/> + <conditional name="broad_options"> + <param name="broad_options_selector" type="select" label="Composite broad regions" help="by putting nearby highly enriched regions into a broad region with loose cutoff (--broad)"> + <option value="">No broad regions</option> + <option value="--broad">broad regions</option> + </param> + <when value="--broad"> + <param name="broad_cutoff" type="float" label="Cutoff for broad region" value="0.1" help="value is either p-value or q-value as specified above (--broad-cutoff)"/> + </when> + </conditional> + </when> + <when value="off" /> + </conditional> + + </inputs> + <outputs> + <!--callpeaks output--> + <data name="output_bed" format="tabular" from_work_dir="MACS2_PREFIX_peaks.xls" label="${tool.name} on ${on_string} (peaks: xls)"> + <filter>'peaks_bed' in outputs</filter> + </data> + <data name="output_narrowpeaks" format="tabular" from_work_dir="MACS2_PREFIX_peaks.narrowPeak" label="${tool.name} on ${on_string} (narrow Peaks)"> + <filter>'narrow' in outputs</filter> + </data> + <data name="output_broadpeaks" format="tabular" from_work_dir="MACS2_PREFIX_peaks.broadPeak" label="${tool.name} on ${on_string} (broad Peaks)"> + <filter>'broad' in outputs</filter> + </data> + <data name="output_gappedpeaks" format="tabular" from_work_dir="MACS2_PREFIX_peaks.gappedPeak" label="${tool.name} on ${on_string} (gapped Peaks)"> + <filter>'gapped' in outputs</filter> + </data> + <data name="output_summits" format="bed" from_work_dir="MACS2_PREFIX_summits.bed" label="${tool.name} on ${on_string} (summits)"> + <filter>'summits' in outputs</filter> + </data> + <data name="output_xls_to_interval_peaks_file" format="interval" label="${tool.name} on ${on_string} (peaks: interval)"> + <filter>'peaks_interval' in outputs</filter> + </data> + <data name="output_extra_files" format="html" label="${tool.name} on ${on_string} (html report)"> + <filter>'html' in outputs</filter> + </data> + </outputs> + <tests> + <!--none yet for macs2--> + </tests> + <help> +**What it does** + +With the improvement of sequencing techniques, chromatin immunoprecipitation followed by high throughput sequencing (ChIP-Seq) +is getting popular to study genome-wide protein-DNA interactions. To address the lack of powerful ChIP-Seq analysis method, we present a novel algorithm, named Model-based Analysis of ChIP-Seq (MACS), for +identifying transcript factor binding sites. MACS captures the influence of genome complexity to evaluate the significance of enriched ChIP regions, and MACS improves the spatial resolution of +binding sites through combining the information of both sequencing tag position and orientation. MACS can be easily used for ChIP-Seq data alone, or with control sample with the increase of specificity. + +View the original MACS2 documentation: https://github.com/taoliu/MACS/blob/master/README + +------ + +**Usage** + +**Peak Calling**: Main MACS2 Function to Call peaks from alignment results. + +**Compare .bdg files**: Deduct noise by comparing two signal tracks in bedGraph. + + +------ + +**Citation** + +For the underlying tool, please cite Zhang Y, Liu T, Meyer CA, Eeckhoute J, Johnson DS, Bernstein BE, Nusbaum C, Myers RM, Brown M, Li W, Liu XS. Model-based analysis of ChIP-Seq (MACS). Genome Biol. 2008;9(9):R137. + +Integration of MACS2 with Galaxy performed by Ziru Zhou ( ziruzhou@gmail.com ). Please send your comments/questions to modENCODE DCC at help@modencode.org. + </help> +</tool>