Mercurial > repos > iuc > multigps
changeset 2:028fafca04fa draft default tip
"planemo upload commit 9e4d2776d6b3276e2849943439799b82d989bc3b"
| author | iuc |
|---|---|
| date | Sun, 22 Dec 2019 12:11:33 -0500 |
| parents | 7e0a12282c7f |
| children | |
| files | .shed.yml macros.xml multigps.xml test-data/hg19_all_events_table1.tabular test-data/hg19_all_events_table2.tabular test-data/hg19_output_bed1.bed test-data/hg19_output_bed2.bed test-data/hg19_output_html1.html test-data/hg19_output_html2.html test-data/hg19_replicates_counts1.tabular test-data/hg19_replicates_counts2.tabular tool-data/hg19.len |
| diffstat | 12 files changed, 171 insertions(+), 71 deletions(-) [+] |
line wrap: on
line diff
--- a/.shed.yml Tue Mar 28 12:24:56 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,13 +0,0 @@ -name: multigps -owner: iuc -description: Analyzes collections of multi-condition ChIP-seq data. -homepage_url: http://mahonylab.org/software/multigps/ -long_description: | - Contains a tool that runs MultiGPS, a framework for analyzing collections of multi-condition ChIP-seq - datasets and characterizing differential binding events between conditions. MultiGPS encourages consistency - in the reported binding event locations across conditions and provides accurate estimation of ChIP enrichment - levels at each event. MultiGPS loads all data to memory, so you will need a lot of available memory if you - are running analysis over many conditions or large datasets. -type: unrestricted -categories: -- ChIP-seq
--- a/macros.xml Tue Mar 28 12:24:56 2017 -0400 +++ b/macros.xml Sun Dec 22 12:11:33 2019 -0500 @@ -1,8 +1,33 @@ <?xml version='1.0' encoding='UTF-8'?> <macros> + <xml name="cond_fixedreadcount"> + <conditional name="fixedreadcount_cond"> + <param name="fixedreadcount_select" type="select" label="Set fixed per-base read count limit for this replicate?" help="Selecting No uses a global per-base limit that is estimated from a Poisson distribution."> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <when value="no"/> + <when value="yes"> + <param name="fixedreadcount" type="integer" value="0" min="0" label="Fixed per-base read count limit"/> + </when> + </conditional> + </xml> + <xml name="param_experiment_type"> + <param name="experiment_type" type="select" display="radio" label="Experiment type for this replicate"> + <option value="chipseq" selected="True">ChIP-seq</option> + <option value="chipexo">ChIP-exo</option> + </param> + </xml> <xml name="motif_finding_params"> <param name="memenmotifs" type="integer" min="0" value="3" label="Number of motifs MEME should find for each condition" /> <param name="mememinw" type="integer" min="0" value="6" label="Minimum motif width for MEME" /> <param name="mememaxw" type="integer" min="0" value="16" label="Maximum motif width for MEME" /> </xml> + <xml name="requirements"> + <requirements> + <requirement type="package" version="1">fonts-conda-ecosystem</requirement> + <requirement type="package" version="0.74">multigps</requirement> + <yield/> + </requirements> + </xml> </macros>
--- a/multigps.xml Tue Mar 28 12:24:56 2017 -0400 +++ b/multigps.xml Sun Dec 22 12:11:33 2019 -0500 @@ -1,31 +1,28 @@ -<tool id="multigps" name="MultiGPS" version="0.73.0"> +<tool id="multigps" name="MultiGPS" version="0.74.0"> <description>analyzes collections of multi-condition ChIP-seq data</description> <macros> <import>macros.xml</import> </macros> - <requirements> - <requirement type="package" version="0.73">multigps</requirement> - </requirements> + <expand macro="requirements" /> <command detect_errors="aggressive"> <![CDATA[ #set output_dir = $output_html.files_path mkdir -p $output_dir && multigps ## General options + --design '$build_design_file' ## Append .txt extensions to events hrefs ## in output dataset so files will render ## in the browser. --eventsaretxt - ## Do not run the parallel version of meme - ## since it is not yet available in conda. + ## Do not run the parallel version of meme. --meme1proc - --expt '$expt' - --format $expt.ext - #if str($ctrl) != 'None': - --ctrl '$ctrl' + --threads \${GALAXY_SLOTS:-4} + #if str($in_test_mode) == "no": + --geninfo '$chromInfo' + #else: + --geninfo '$__tool_directory__/tool-data/hg19.len' #end if - --threads \${GALAXY_SLOTS:-4} - --geninfo '$chromInfo' ## Advanced options #set aoc = $advanced_options_cond #if str($aoc.advanced_options) == 'display': @@ -39,9 +36,9 @@ #set rgc = $umc.reference_genome_cond --seq #if str($rgc.reference_genome_source) == 'cached': - '${rgc.reference_genome.fields.path}' + '${rgc.reference_genome.fields.path}' #else: - '${rgc.reference_genome}' + '${rgc.reference_genome}' #end if #end if ## Limits on how many reads @@ -80,9 +77,9 @@ #end if ## Running MultiGPS #if str($aoc.readdistributionfile) != 'None': - --d '$aoc.readdistributionfile' + --readdistributionfile '$aoc.readdistributionfile' #end if - --r $aoc.maxtrainingrounds + --maxtrainingrounds $aoc.maxtrainingrounds #if str($aoc.nomodelupdate) == 'no': --nomodelupdate #end if @@ -127,20 +124,20 @@ --mememinw $bmc.mememinw --mememaxw $bmc.mememaxw #else: - #set mfoc = $bmc.nomotifprior_cond + #set nmpc = $bmc.nomotifprior_cond --nomotifs - --nomotifprior $mfoc.nomotifprior - #if str($mfoc.nomotifprior) == 'yes': - --memenmotifs $mfoc.memenmotifs - --mememinw $mfoc.mememinw - --mememaxw $mfoc.mememaxw + #if str($nmpc.nomotifprior) == 'yes': + --nomotifprior + --memenmotifs $nmpc.memenmotifs + --mememinw $nmpc.mememinw + --mememaxw $nmpc.mememaxw #end if #end if #end if #end if ## Reporting binding events #if str($rbec.report_binding_events) == 'yes': - --q $rbec.minqvalue + --minqvalue $rbec.minqvalue --minfold $rbec.minfold #if str($rbec.nodifftests) == 'no': --nodifftests @@ -151,17 +148,76 @@ #end if 2>&1 --out '$output_html.files_path' - && cp $output_dir/*.events.txt '$experiment_events' + #if str($save_design_file) == 'yes': + && cp '$build_design_file' '$output_design_file' + #end if + && mv $output_dir/*.counts '$replicates_counts' + && mv $output_dir/*.bed '$output_bed' && mv $output_dir/*.html '$output_html' && mv $output_dir/*.table.txt '$all_events_table' - && mv $output_dir/*.counts '$replicates_counts' ]]> </command> + <configfiles> + <configfile name="build_design_file"><![CDATA[#for $condition_items in $condition_repeat: + #for $signal_items in $condition_items.signal_repeat: + #if str($signal_items.fixedreadcount_cond.fixedreadcount_select) == 'yes': + #set $frc = $signal_items.fixedreadcount_cond.fixedreadcount + #else: + #set $frc = '' + #end if +${signal_items.signal} Signal ${signal_items.signal.ext.upper()} ${condition_items.condition_name} ${signal_items.replicate_name} ${condition_items.experiment_type} ${frc} + #end for + #for $control_items in $condition_items.control_repeat: + #if str($control_items.specify_replicate_name_cond.specify_replicate_name) == 'yes': + #set $rn = $control_items.specify_replicate_name_cond.replicate_name + #else: + #set $rn = '' + #end if + #if str($control_items.fixedreadcount_cond.fixedreadcount_select) == 'yes': + #set $frc = $control_items.fixedreadcount_cond.fixedreadcount + #else: + #set $frc = '' + #end if +${control_items.control} Control ${control_items.control.ext.upper()} ${condition_items.condition_name} ${rn} ${condition_items.experiment_type} ${frc} + #end for +#end for ]]></configfile> + </configfiles> <inputs> - <param name="expt" type="data" format="bam,bed,scidx" label="Run MultiGPS on"> - <validator type="unspecified_build" /> + <repeat name="condition_repeat" title="Condition" min="1"> + <param name="condition_name" type="text" value="cond" label="Condition name"> + <validator type="empty_field" /> + </param> + <expand macro="param_experiment_type" /> + <repeat name="signal_repeat" title="Signal" min="1"> + <param name="signal" type="data" format="bam,bed,scidx" label="Select signal" help="Supported formats are bam, bed and scidx"> + <validator type="unspecified_build" /> + </param> + <param name="replicate_name" type="text" value="1" label="Replicate name"> + <validator type="empty_field" /> + </param> + <expand macro="cond_fixedreadcount" /> + </repeat> + <repeat name="control_repeat" title="Control" min="0"> + <param name="control" type="data" format="bam,bed,scidx" label="Select control" help="Optional, supported formats are bam, bed and scidx"> + <validator type="unspecified_build" /> + </param> + <conditional name="specify_replicate_name_cond"> + <param name="specify_replicate_name" type="select" label="Specify replicate name?" help="Optional for control. If used, the control will only be used for the corresponding named signal replicate"> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <when value="yes"> + <param name="replicate_name" type="text" optional="true" label="Replicate name"/> + </when> + <when value="no" /> + </conditional> + <expand macro="cond_fixedreadcount" /> + </repeat> + </repeat> + <param name="save_design_file" type="select" display="radio" label="Output design file?"> + <option value="no" selected="true">No</option> + <option value="yes">Yes</option> </param> - <param name="ctrl" type="data" format="bam,bed,scidx" optional="True" label="Optional file containing reads from a control experiment" help="Must be same forat as the input above" /> <!-- Advanced options --> <conditional name="advanced_options_cond"> <param name="advanced_options" type="select" label="Advanced options"> @@ -192,7 +248,7 @@ </conditional> <!-- Scaling data --> <conditional name="scale_data_cond"> - <param name="scale_data" type="select" label="Set data scaling parameters?" help="Default behavior is to scale signal to corresponding controls using regression on the set of signal/control ratios in 10Kbp windows."> + <param name="scale_data" type="select" label="Set data scaling parameters?" help="Default behavior is to scale signal to corresponding controls using the Normalization of ChIP-seq (NCIS) method.[2]"> <option value="no" selected="True">No</option> <option value="yes">Yes</option> </param> @@ -282,7 +338,7 @@ <when value="cached"> <param name="reference_genome" type="select" label="Using reference genome"> <options from_data_table="all_fasta"> - <filter type="data_meta" key="dbkey" ref="expt" column="1"/> + <!-- <filter type="data_meta" key="dbkey" ref="expt" column="1"/> does not yet work in a repeat...--> </options> <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> </param> @@ -290,7 +346,7 @@ <when value="history"> <param name="reference_genome" type="data" format="fasta" label="Using reference genome"> <options> - <filter type="data_meta" key="dbkey" ref="expt"/> + <!-- <filter type="data_meta" key="dbkey" ref="expt"/> does not yet work in a repeat...--> </options> <validator type="no_options" message="The current history does not include a fasta dataset with the build associated with the selected input file"/> </param> @@ -356,28 +412,45 @@ </when> <when value="hide" /> </conditional> + <!-- Functional testing --> + <param name="in_test_mode" type="hidden" value="no" /> </inputs> <outputs> - <data name="replicates_counts" format="tabular" label="${tool.name} replicates counts on ${on_string}"/> - <data name="all_events_table" format="tabular" label="${tool.name} all events table on ${on_string}"/> - <data name="experiment_events" format="tabular" label="${tool.name} experiment events on ${on_string}"/> - <data name="output_html" format="html" label="${tool.name} on ${on_string}"/> + <data name="output_design_file" format="tabular" label="${tool.name} (design file) on ${on_string}"> + <filter>save_design_file == 'yes'</filter> + </data> + <data name="output_bed" format="bed" label="${tool.name} (bed) on ${on_string}"/> + <data name="output_html" format="html" label="${tool.name} (html) on ${on_string}"/> + <data name="replicates_counts" format="tabular" label="${tool.name} (replicates counts) on ${on_string}"/> + <data name="all_events_table" format="tabular" label="${tool.name} (all events table) on ${on_string}"/> </outputs> <tests> <test> - <param name="expt" value="expt_hg19.scidx" ftype="scidx" dbkey="hg19" /> - <param name="advanced_options_cond" value="hide" /> + <repeat name="condition_repeat"> + <repeat name="signal_repeat"> + <param name="signal" value="expt_hg19.scidx" ftype="scidx" dbkey="hg19" /> + </repeat> + </repeat> + <param name="advanced_options" value="hide" /> + <param name="in_test_mode" value="yes" /> <output name="output_html" file="hg19_output_html1.html" ftype="html" compare="contains"/> - <output name="experiment_events" file="hg19_experiment_events1.tabular" ftype="tabular"/> + <output name="output_bed" file="hg19_output_bed1.bed" ftype="bed"/> <output name="all_events_table" file="hg19_all_events_table1.tabular" ftype="tabular"/> <output name="replicates_counts" file="hg19_replicates_counts1.tabular" ftype="tabular"/> </test> <test> - <param name="expt" value="expt_hg19.scidx" ftype="scidx" dbkey="hg19" /> - <param name="ctrl" value="cntrl_hg19.scidx" ftype="scidx" dbkey="hg19" /> - <param name="advanced_options_cond" value="display" /> + <repeat name="condition_repeat"> + <repeat name="signal_repeat"> + <param name="signal" value="expt_hg19.scidx" ftype="scidx" dbkey="hg19" /> + </repeat> + <repeat name="control_repeat"> + <param name="control" value="cntrl_hg19.scidx" ftype="scidx" dbkey="hg19" /> + </repeat> + </repeat> + <param name="advanced_options" value="display" /> + <param name="in_test_mode" value="yes" /> <output name="output_html" file="hg19_output_html2.html" ftype="html" compare="contains"/> - <output name="experiment_events" file="hg19_experiment_events2.tabular" ftype="tabular"/> + <output name="output_bed" file="hg19_output_bed2.bed" ftype="bed"/> <output name="all_events_table" file="hg19_all_events_table2.tabular" ftype="tabular"/> <output name="replicates_counts" file="hg19_replicates_counts2.tabular" ftype="tabular"/> </test> @@ -399,7 +472,7 @@ * **Loading data:** - - **Optional file containing reads from a control experiment** - must be same format as input experiment + - **Optional file containing reads from a control experiment** - file containing reads from a control experiment - **Fixed per-base limit** - Fixed per-base limit (default: estimated from background model). - **Poisson threshold for filtering per base** - Look at neighboring positions to decide what the per-base limit should be. - **Use non-unique reads** - Use non-unique reads. @@ -456,3 +529,4 @@ <citation type="doi">10.1371/journal.pcbi.1003501</citation> </citations> </tool> +
--- a/test-data/hg19_all_events_table1.tabular Tue Mar 28 12:24:56 2017 -0400 +++ b/test-data/hg19_all_events_table1.tabular Sun Dec 22 12:11:33 2019 -0500 @@ -1,10 +1,10 @@ ### MultiGPS output #Condition Name Index TotalSigCount SignalFraction -#Condition experiment 0 99.0 0.555 +#Condition cond 0 99.0 0.555 #Replicate ParentCond Name Index SigCount CtrlCount SigCtrlScaling SignalFraction -#Replicate experiment experiment:rep1 0 99.0 0 1 0.56 +#Replicate cond cond:1 0 99.0 0 1 0.56 # -#Point experiment_Sig experiment_Ctrl experiment_log2Fold experiment_log2P ActiveConds +#Point cond_Sig cond_Ctrl cond_log2Fold cond_log2P ActiveConds chr1:569927 14.3 0.0 3.838 -6.470 1 chr1:536042 1.0 0.0 0.014 -1.474 1 chr1:535151 1.0 0.0 0.014 -1.413 1
--- a/test-data/hg19_all_events_table2.tabular Tue Mar 28 12:24:56 2017 -0400 +++ b/test-data/hg19_all_events_table2.tabular Sun Dec 22 12:11:33 2019 -0500 @@ -1,10 +1,10 @@ ### MultiGPS output #Condition Name Index TotalSigCount SignalFraction -#Condition experiment 0 99.0 0.555 +#Condition cond 0 99.0 0.555 #Replicate ParentCond Name Index SigCount CtrlCount SigCtrlScaling SignalFraction -#Replicate experiment experiment:rep1 0 99.0 18.0 4.00 0.555 +#Replicate cond cond:1 0 99.0 18.0 4.00 0.555 # -#Point experiment_Sig experiment_Ctrl experiment_log2Fold experiment_log2P ActiveConds +#Point cond_Sig cond_Ctrl cond_log2Fold cond_log2P ActiveConds chr1:569927 14.3 0.0 3.838 -6.470 1 chr1:536042 1.0 0.0 0.014 -1.281 1 chr1:535151 1.0 0.0 0.014 -1.211 1
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hg19_output_bed1.bed Sun Dec 22 12:11:33 2019 -0500 @@ -0,0 +1,1 @@ +track name=multiGPS-cond description=multiGPS events cond
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hg19_output_bed2.bed Sun Dec 22 12:11:33 2019 -0500 @@ -0,0 +1,1 @@ +track name=multiGPS-cond description=multiGPS events cond
--- a/test-data/hg19_output_html1.html Tue Mar 28 12:24:56 2017 -0400 +++ b/test-data/hg19_output_html1.html Sun Dec 22 12:11:33 2019 -0500 @@ -1,13 +1,12 @@ <html> <body> -</p> <h2>Binding events</h2> <table> <tr> <th>Condition</th> <th>Events</th> <th>File</th> </tr> - <tr> <td>experiment</td> + <tr> <td>cond</td> <td>0</td> </tr> </table> @@ -19,7 +18,7 @@ <th>SignalFraction</th> <th>ReadDistributionModel</th> </tr> - <tr> <td>experiment rep1</td> + <tr> <td>cond 1</td> <td>99.0</td> <td>NA</td> <td>0.555</td>
--- a/test-data/hg19_output_html2.html Tue Mar 28 12:24:56 2017 -0400 +++ b/test-data/hg19_output_html2.html Sun Dec 22 12:11:33 2019 -0500 @@ -1,13 +1,11 @@ <html> - <body> -</p> <h2>Binding events</h2> <table> <tr> <th>Condition</th> <th>Events</th> <th>File</th> </tr> - <tr> <td>experiment</td> + <tr> <td>cond</td> <td>0</td> </tr> </table> @@ -19,7 +17,7 @@ <th>SignalFraction</th> <th>ReadDistributionModel</th> </tr> - <tr> <td>experiment rep1</td> + <tr> <td>cond 1</td> <td>99.0</td> <td>4.000</td> <td>0.555</td>
--- a/test-data/hg19_replicates_counts1.tabular Tue Mar 28 12:24:56 2017 -0400 +++ b/test-data/hg19_replicates_counts1.tabular Sun Dec 22 12:11:33 2019 -0500 @@ -1,4 +1,4 @@ -Point experiment:rep1 +Point cond:1 chr1:569927 14 chr1:536042 1 chr1:535151 1
--- a/test-data/hg19_replicates_counts2.tabular Tue Mar 28 12:24:56 2017 -0400 +++ b/test-data/hg19_replicates_counts2.tabular Sun Dec 22 12:11:33 2019 -0500 @@ -1,4 +1,4 @@ -Point experiment:rep1 +Point cond:1 chr1:569927 14 chr1:536042 1 chr1:535151 1
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/hg19.len Sun Dec 22 12:11:33 2019 -0500 @@ -0,0 +1,15 @@ +chr1 249250621 +chr1_jh636052_fix 7283150 +chr1_jh636053_fix 1676126 +chr1_jh636054_fix 758378 +chr1_gl000192_random 547496 +chr1_gl383520_alt 366579 +chr1_gl383518_alt 182439 +chr1_gl949741_fix 151551 +chr1_gl383519_alt 110268 +chr1_gl000191_random 106433 +chr1_gl383517_fix 49352 +chr1_gl383516_fix 49316 +chr1_jh806575_fix 47409 +chr1_jh806573_fix 24680 +chr1_jh806574_fix 22982