Mercurial > repos > iuc > multigps
changeset 0:4aa531981208 draft
Uploaded
| author | iuc |
|---|---|
| date | Mon, 13 Mar 2017 13:25:01 -0400 |
| parents | |
| children | 7e0a12282c7f |
| files | .shed.yml README.rst macros.xml multigps.xml test-data/cntrl_hg19.scidx test-data/expt_hg19.scidx test-data/hg19_all_events_table1.tabular test-data/hg19_all_events_table2.tabular test-data/hg19_experiment_events1.tabular test-data/hg19_experiment_events2.tabular 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/all_fasta.loc.sample tool-data/tool_data_table_conf.xml.sample |
| diffstat | 16 files changed, 828 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/.shed.yml Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,13 @@ +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
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README.rst Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,17 @@ +MultiGPS wrapper for Galaxy +================================ + +* http://mahonylab.org/software/multigps/ + +MultiGPS performs significant EM optimization of binding events along the genome and across experimental +conditions, and it integrates motif-finding via MEME. The tool loads all data into memory, so the potential +exists for time and memory intensive analyses if running over many conditions or large datasets. + +Setting the memory allocation in Galaxy for this tool is handled using the <env id="_JAVA_OPTIONS"> tag for +a selected job runner in the job_conf.xml file. + +License +------- + +MIT +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,8 @@ +<?xml version='1.0' encoding='UTF-8'?> +<macros> + <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> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/multigps.xml Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,458 @@ +<tool id="multigps" name="MultiGPS" version="0.73.0"> + <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> + <command detect_errors="aggressive"> + <![CDATA[ + #set output_dir = $output_html.files_path + mkdir -p $output_dir && + multigps + ## General options + ## Append .txt extensions to events hrefs + ## in output dataset so files will render + ## in the browser. + --eventsaretxt + ## Do not run the parallel version of meme + ## since it is not yet available in conda. + --meme1proc + --expt '$expt' + --format $expt.ext + #if str($ctrl) != 'None': + --ctrl '$ctrl' + #end if + --threads \${GALAXY_SLOTS:-4} + --geninfo '$chromInfo' + ## Advanced options + #set aoc = $advanced_options_cond + #if str($aoc.advanced_options) == 'display': + #set bmsc = $aoc.binding_model_smoothing_cond + #set gmsc = $aoc.gauss_model_smoothing_cond + #set rbec = $aoc.report_binding_events_cond + #set rloc = $aoc.reads_limits_options_cond + #set sdc = $aoc.scale_data_cond + #set umc = $aoc.use_motif_cond + #if str($umc.use_motif) == 'yes': + #set rgc = $umc.reference_genome_cond + --seq + #if str($rgc.reference_genome_source) == 'cached': + '${rgc.reference_genome.fields.path}' + #else: + '${rgc.reference_genome}' + #end if + #end if + ## Limits on how many reads + #if str($rloc.reads_limits) == 'yes': + --fixedpb $rloc.fixedpb + --poissongausspb $rloc.poissongausspb + #if str($rloc.nonunique) == 'yes': + --nonunique + #end if + --mappability $rloc.mappability + #if str($rloc.nocache) == 'yes': + --nocache + #end if + #end if + ## Scaling data + #if str($sdc.scale_data) == 'yes': + #if str($sdc.scaling) == 'no': + --noscaling $sdc.scaling + #end if + #if str($sdc.medianscale) == 'yes': + --medianscale $sdc.medianscale + #end if + #if str($sdc.regressionscale) == 'yes': + --regressionscale $sdc.regressionscale + #end if + #if str($sdc.sesscale) == 'yes': + --sesscale $sdc.sesscale + #end if + #if $sdc.fixedscaling > 0: + ‒‒fixedscaling $sdc.fixedscaling + #end if + --scalewin $sdc.scalewin + #if str($sdc.plotscaling) == 'yes': + --plotscaling $sdc.plotscaling + #end if + #end if + ## Running MultiGPS + #if str($aoc.readdistributionfile) != 'None': + --d '$aoc.readdistributionfile' + #end if + --r $aoc.maxtrainingrounds + #if str($aoc.nomodelupdate) == 'no': + --nomodelupdate + #end if + --minmodelupdateevents $aoc.minmodelupdateevents + #if str($bmsc.nomodelsmoothing) == 'no': + --nomodelsmoothing + #else: + --splinesmoothparam $bmsc.splinesmoothparam + #end if + #if str($gmsc.gaussmodelsmoothing) == 'yes': + --gaussmodelsmoothing + --gausssmoothparam $gmsc.gausssmoothparam + #end if + #if str($aoc.jointinmodel) == 'yes': + --jointinmodel + #end if + #if str($aoc.fixedmodelrange) == 'yes': + --fixedmodelrange + #end if + --prlogconf $aoc.prlogconf + #if $aoc.fixedalpha > 0: + --fixedalpha $aoc.fixedalpha + #end if + --alphascale $aoc.alphascale + #if str($aoc.mlconfignotshared) == 'no': + --mlconfignotshared + #end if + #if str($aoc.exclude) != 'None': + --exclude '$aoc.exclude' + #end if + ## MultiGPS priors + #if str($umc.use_motif) == 'yes': + #set mpc = $umc.multigps_priors_cond + #if str($mpc.multigps_priors) == 'yes': + #set bmc = $mpc.both_motifs_cond + #if str($mpc.noposprior) == 'no': + --noposprior + #end if + --probshared $mpc.probshared + #if str($bmc.nomotifs) == 'yes': + --memenmotifs $bmc.memenmotifs + --mememinw $bmc.mememinw + --mememaxw $bmc.mememaxw + #else: + #set mfoc = $bmc.nomotifprior_cond + --nomotifs + --nomotifprior $mfoc.nomotifprior + #if str($mfoc.nomotifprior) == 'yes': + --memenmotifs $mfoc.memenmotifs + --mememinw $mfoc.mememinw + --mememaxw $mfoc.mememaxw + #end if + #end if + #end if + #end if + ## Reporting binding events + #if str($rbec.report_binding_events) == 'yes': + --q $rbec.minqvalue + --minfold $rbec.minfold + #if str($rbec.nodifftests) == 'no': + --nodifftests + #end if + --edgerod $rbec.edgerod + --diffp $rbec.diffp + #end if + #end if + 2>&1 + --out '$output_html.files_path' + && cp $output_dir/*.events.txt '$experiment_events' || true + && mv $output_dir/*.html '$output_html' || true + && mv $output_dir/*.table.txt '$all_events_table' || true + && mv $output_dir/*.counts '$replicates_counts' || true + ]]> + </command> + <inputs> + <param name="expt" type="data" format="bam,bed,scidx" label="Run MultiGPS on"> + <validator type="unspecified_build" /> + </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"> + <option value="hide" selected="true">Hide</option> + <option value="display">Display</option> + </param> + <when value="display"> + <!-- Limits on how many reads --> + <conditional name="reads_limits_options_cond"> + <param name="reads_limits" type="select" label="Set limits on how many reads can have their 5′ end at the same position in each replicate?" help="Default behavior is to estimate a global per-base limit from a Poisson distribution parameterized by the number of reads divided by the number of mappable bases in the genome. The per-base limit is set as the count corresponding to the 10^-7 probability level from the Poisson."> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <when value="no" /> + <when value="yes"> + <param name="fixedpb" type="integer" value="0" min="0" label="Fixed per-base limit" help="Zero value estimates from background model"/> + <param name="poissongausspb" type="integer" value="0" min="0" label="Poisson threshold for filtering per base" help="Filter per base using the specified Poisson threshold parameterized by a local Gaussian sliding window" /> + <param name="nonunique" type="select" label="Use non-unique reads?"> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <param name="mappability" type="float" value="0.0" min="0.8" label="Fraction of the genome that is mappable for these experiments" /> + <param name="nocache" type="select" label="Turn off caching of the entire set of experiments?" help="Run slower with less memory" > + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + </when> + </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."> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <when value="yes"> + <param name="scaling" type="select" label="Use signal vs control scaling?"> + <option value="yes" selected="True">Yes</option> + <option value="no">No</option> + </param> + <param name="medianscale" type="select" label="Use the median signal/control ratio as the scaling factor?"> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <param name="regressionscale" type="select" label="Use scaling by regression on binned tag counts?"> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <param name="sesscale" type="select" label="Estimate scaling factor by SES?" help="SES: Diaz, et al. Stat Appl Genet Mol Biol. 2012"> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <param name="fixedscaling" type="float" value="0.0" min="0.0" label="Multiply control counts by total tag count ratio and then by this factor" help="Set as 0 to skip" /> + <param name="scalewin" type="integer" min="0" value="500" label="Window size for estimating scaling ratios" help="The value is the number of base pairs. Use something much smaller than the default if scaling via SES (e.g. 200)." /> + <param name="plotscaling" type="select" label="Plot diagnostic information for the chosen scaling method?"> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + </when> + <when value="no" /> + </conditional> + <!-- Running MultiGPS --> + <param name="readdistributionfile" type="data" optional="True" format="tabular" label="Optional binding event read distribution file for initializing models" help="A default initial distribution appropriate for ChIP-seq data is used if this option is not specified." /> + <param name="maxtrainingrounds" type="integer" value="3" min="0" label="Maximum number of training rounds for updating binding event read distributions" /> + <param name="nomodelupdate" type="select" label="Perform binding model updates?"> + <option value="yes" selected="True">Yes</option> + <option value="no">No</option> + </param> + <param name="minmodelupdateevents" type="integer" value="500" min="0" label="Minimum number of events to support an update of the read distribution" /> + <conditional name="binding_model_smoothing_cond"> + <param name="nomodelsmoothing" type="select" label="Perform binding model smoothing?" help="Smoothing performed with a cubic spline."> + <option value="yes" selected="True">Yes</option> + <option value="no">No</option> + </param> + <when value="yes"> + <param name="splinesmoothparam" type="integer" value="30" min="0" label="Spline smoothing parameter" /> + </when> + <when value="no" /> + </conditional> + <conditional name="gauss_model_smoothing_cond"> + <param name="gaussmodelsmoothing" type="select" label="Use Gaussian model smoothing?" help="Select No to smooth with a cubic spline."> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <when value="no" /> + <when value="yes"> + <param name="gausssmoothparam" type="integer" value="3" min="0" label="Smoothing factor" help="Gaussian smoothing standard deviation." /> + </when> + </conditional> + <param name="jointinmodel" type="select" label="Allow joint events in model updates?"> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <param name="fixedmodelrange" type="select" label="Keep binding model range fixed to inital size?" help="Select No to vary automatically"> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <param name="prlogconf" type="integer" value="-6" label="Poisson log threshold for potential region scanning" /> + <param name="fixedalpha" type="integer" value="0" min="0" label="Impose this alpha" help="This is a sparse prior on binding events in the MultiGPS model. It can be interpreted as a minimum number of reads that each binding event must be responsible for in the model. A zero value will estimate the alpha automatically." /> + <param name="alphascale" type="float" value="1.0" min="0" label="Alpha scaling factor" /> + <param name="mlconfignotshared" type="select" label="Share component configs in the ML step?" help="Mainly affects the quantification of binding levels for binding events that are not shared but are located at nearby locations across experiments."> + <option value="yes" selected="True">Yes</option> + <option value="no">No</option> + </param> + <param name="exclude" type="data" optional="True" format="txt" label="Optional file containing a set of regions to ignore during MultiGPS training" help="Ideally exclude the mitochondrial genome and other blacklisted regions that contain artifactual accumulations of reads in both ChIP-seq and control experiments." /> + <!-- MultiGPS priors --> + <conditional name="use_motif_cond"> + <param name="use_motif" type="select" label="Perform motif-finding or use a motif-prior?"> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <when value="yes"> + <!-- Specifying the genome --> + <conditional name="reference_genome_cond"> + <param name="reference_genome_source" type="select" label="Choose the source for the reference genome"> + <option value="cached">locally cached</option> + <option value="history">from history</option> + </param> + <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"/> + </options> + <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/> + </param> + </when> + <when value="history"> + <param name="reference_genome" type="data" format="fasta" label="Using reference genome"> + <options> + <filter type="data_meta" key="dbkey" ref="expt"/> + </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> + </when> + </conditional> + <!-- MultiGPS priors options --> + <conditional name="multigps_priors_cond"> + <param name="multigps_priors" type="select" label="Specify MultiGPS priors options?"> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <when value="no" /> + <when value="yes"> + <param name="noposprior" type="select" label="Perform inter-experiment positional prior?"> + <option value="yes" selected="True">Yes</option> + <option value="no">No</option> + </param> + <param name="probshared" type="float" value="0.9" min="0.0" label="Probability that events are shared across conditions" /> + <conditional name="both_motifs_cond"> + <param name="nomotifs" type="select" label="Perform both motif-finding and motif priors?"> + <option value="yes" selected="True">Yes</option> + <option value="no">No</option> + </param> + <when value="yes"> + <expand macro="motif_finding_params" /> + </when> + <when value="no"> + <conditional name="nomotifprior_cond"> + <param name="nomotifprior" type="select" label="Perform motif-finding only?" help="Selecting Yes turns off motif priors."> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <when value="no" /> + <when value="yes"> + <expand macro="motif_finding_params" /> + </when> + </conditional> + </when> + </conditional> + </when> + </conditional> + </when> + <when value="no" /> + </conditional> + <!-- Reporting binding events --> + <conditional name="report_binding_events_cond"> + <param name="report_binding_events" type="select" label="Report binding events?"> + <option value="no" selected="True">No</option> + <option value="yes">Yes</option> + </param> + <when value="no" /> + <when value="yes"> + <param name="minqvalue" type="float" min="0" value="0.001" label="Minimum Q-value (corrected p-value) of reported binding events" /> + <param name="minfold" type="float" min="0" value="1.5" label="Minimum event fold-change vs scaled control" /> + <param name="nodifftests" type="select" label="Run differential enrichment tests?"> + <option value="yes" selected="True">Yes</option> + <option value="no">No</option> + </param> + <param name="edgerod" type="float" min="0" value="0.15" label="EdgeR over-dispersion parameter value" /> + <param name="diffp" type="float" min="0" value="0.01" label="Minimum p-value for reporting differential enrichment" /> + </when> + </conditional> + </when> + <when value="hide" /> + </conditional> + </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}"/> + </outputs> + <tests> + <test> + <param name="expt" value="expt_hg19.scidx" ftype="scidx" dbkey="hg19" /> + <param name="advanced_options_cond" value="hide" /> + <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="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" /> + <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="all_events_table" file="hg19_all_events_table2.tabular" ftype="tabular"/> + <output name="replicates_counts" file="hg19_replicates_counts2.tabular" ftype="tabular"/> + </test> + </tests> + <help> + +**What it does** + +MultiGPS is 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 performs significant EM optimization of binding events along the genome and across experimental +conditions, and it integrates motif-finding via MEME. The tool loads all data into memory, so the potential +exists for time and memory intensive analyses if running over many conditions or large datasets. + +----- + +**Options** + +* **Loading data:** + + - **Optional file containing reads from a control experiment** - must be same format as input 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. + - **Fraction of the genome that is mappable for these experiments** - Fraction of the genome that is mappable for these experiments + - **Turn off caching of the entire set of experiments?** - Flag to turn off caching of the entire set of experiments (i.e. run slower with less memory). + +* **Scaling control vs signal counts:** + + - **Use signal vs control scaling?** - Flag to turn off auto estimation of signal vs control scaling factor + - **Use the median signal/control ratio as the scaling factor?** - Flag to use scaling by median ratio (default = scaling by NCIS). + - **Use scaling by regression on binned tag counts?** - Flag to use scaling by regression (default = scaling by NCIS). + - **Estimate scaling factor by SES?** - Specify whether to estimate scaling factor by SES. + - **Multiply control counts by total tag count ratio and then by this factor** - Multiply control counts by total tag count ratio and then by this factor (default: NCIS). + - **Window size for estimating scaling ratios** - Window size in base pairs for estimating scaling ratios + - **Plot diagnostic information for the chosen scaling method?** - Flag to plot diagnostic information for the chosen scaling method. + +* **Running MultiGPS:** + + - **Optional binding event read distribution file** - Binding event read distribution file for initializing models. The true distribution of reads around binding events is estimated during MultiGPS training. A default initial distribution appropriate for ChIP-seq data is used if this option is not specified. + - **Maximum number of training rounds for updating binding event read distributions** - Maximum number of training rounds for updating binding event read distributions. + - **Perform binding model updates?** - Perform binding model updates? + - **Minimum number of events to support an update of the read distribution** - Minimum number of events to support an update of the read distribution + - **Perform binding model smoothing?** - Smooth with a cubic spline using a specified smoothing factor. + - **Spline smoothing parameter** - Smoothing parameter for smoothing cubic spline. + - **Perform Gaussian model smoothing?** - Select "Yes" to use Gaussian model smoothing using a specified smoothing factor if binding model smoothing is not performed. + - **Allow joint events in model updates?** - Specify whether to allow joint events in model updates. + - **Keep binding model range fixed to inital size?** - Flag to keep binding model range fixed to inital size (default: vary automatically) + - **Poisson log threshold for potential region scanning** - Poisson log threshold for potential region scanning. + - **Alpha scaling factor** - Alpha scaling factor. Increasing this parameter results in stricter binding event calls. + - **Impose this alpha** - The alpha parameter is a sparse prior on binding events in the MultiGPS model. It can be interpreted as a minimum number of reads that each binding event must be responsible for in the model. Default: estimate alpha automatically. + - **Share component configs in the ML step?** - Flag to not share component configs in the ML step + - **Optional file containing a set of regions to ignore during MultiGPS training** - File containing a set of regions to ignore during MultiGPS training. It’s a good idea to exclude the mitochondrial genome and other ‘blacklisted’ regions that contain artifactual accumulations of reads in both ChIP-seq and control experiments. MultiGPS will waste time trying to model binding events in these regions, even though they will not typically appear significantly enriched over the control (and thus will not be reported to the user). + +* **MultiGPS priors:** + + - **Perform inter-experiment positional prior?** - Flag to turn off inter-experiment positional prior (default=on). + - **Probability that events are shared across conditions** - Probability that events are shared across conditions. + - **Perform both motif-finding and motif priors?** - Flag to turn off motif-finding and motif priors. + - **Perform motif-finding only?** - Flag to turn off motif priors only. + - **Number of motifs MEME should find for each condition** - Number of motifs MEME should find for each condition. + - **Minimum motif width for MEME** - minw arg for MEME. + - **Maximum motif width for MEME** - maxw arg for MEME. + +* **Reporting binding events:** + + - **Minimum Q-value (corrected p-value) of reported binding events** - Minimum Q-value (corrected p-value) of reported binding events. + - **Minimum event fold-change vs scaled control** - Minimum event fold-change vs scaled control. + - **Run differential enrichment tests?** - Choose whether to run differential enrichment tests. + - **EdgeR over-dispersion parameter value** - EdgeR over-dispersion parameter value. + - **Minimum p-value for reporting differential enrichment** - Minimum p-value for reporting differential enrichment. + + </help> + <citations> + <citation type="doi">10.1371/journal.pcbi.1003501</citation> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/cntrl_hg19.scidx Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,20 @@ +#2016-11-04 08:39:36.449;localbam.bam;READ1 +chrom index forward reverse value +chr1 13038 1 0 1 +chr1 16604 0 1 1 +chr1 19215 1 0 1 +chr1 20151 0 1 1 +chr1 48908 1 0 1 +chr1 49489 1 0 1 +chr1 55105 1 0 1 +chr1 57499 0 1 1 +chr1 66636 1 0 1 +chr1 67393 0 1 1 +chr1 72875 0 1 1 +chr1 73954 0 1 1 +chr1 82146 1 0 1 +chr1 85089 0 1 1 +chr1 101405 1 0 1 +chr1 106851 0 1 1 +chr1 108358 0 1 1 +chr1 113877 0 1 1
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/expt_hg19.scidx Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,101 @@ +#2016-11-04 08:39:36.449;localbam.bam;READ1 +chrom index forward reverse value +chr1 13038 1 0 1 +chr1 16604 0 1 1 +chr1 19215 1 0 1 +chr1 20151 0 1 1 +chr1 48908 1 0 1 +chr1 49489 1 0 1 +chr1 55105 1 0 1 +chr1 57499 0 1 1 +chr1 66636 1 0 1 +chr1 67393 0 1 1 +chr1 72875 0 1 1 +chr1 73954 0 1 1 +chr1 82146 1 0 1 +chr1 85089 0 1 1 +chr1 101405 1 0 1 +chr1 106851 0 1 1 +chr1 108358 0 1 1 +chr1 113877 0 1 1 +chr1 122833 1 0 1 +chr1 123101 0 1 1 +chr1 124863 1 0 1 +chr1 125216 0 1 1 +chr1 139373 0 1 1 +chr1 150551 1 0 1 +chr1 158113 1 0 1 +chr1 160681 1 0 1 +chr1 167381 1 0 1 +chr1 173325 0 1 1 +chr1 234394 1 0 1 +chr1 234434 0 1 1 +chr1 235111 1 0 1 +chr1 236086 0 1 1 +chr1 236159 1 0 1 +chr1 237302 0 1 1 +chr1 237648 1 0 1 +chr1 237735 1 0 1 +chr1 238867 0 1 1 +chr1 240339 1 0 1 +chr1 250472 1 0 1 +chr1 250560 0 1 1 +chr1 252828 1 0 1 +chr1 255896 1 0 1 +chr1 258157 1 0 1 +chr1 354230 0 1 1 +chr1 521482 0 1 1 +chr1 523810 0 1 1 +chr1 526070 0 1 1 +chr1 526303 1 0 1 +chr1 526406 1 0 1 +chr1 527103 0 1 1 +chr1 527586 1 0 1 +chr1 527590 1 0 1 +chr1 527599 1 0 1 +chr1 530330 1 0 1 +chr1 532712 0 1 1 +chr1 534863 0 1 1 +chr1 535107 1 0 1 +chr1 535662 1 0 1 +chr1 535998 1 0 1 +chr1 537647 0 1 1 +chr1 539496 1 0 1 +chr1 540024 0 1 1 +chr1 540628 1 0 1 +chr1 542424 1 0 1 +chr1 544024 0 1 1 +chr1 546672 1 0 1 +chr1 549581 0 1 1 +chr1 562709 1 0 1 +chr1 563545 0 1 1 +chr1 566222 0 1 1 +chr1 566375 0 1 1 +chr1 566736 1 0 1 +chr1 566863 1 0 1 +chr1 566974 1 0 1 +chr1 568430 0 1 1 +chr1 568570 1 0 1 +chr1 569236 0 1 1 +chr1 569310 0 1 1 +chr1 569499 1 0 1 +chr1 569640 1 0 1 +chr1 569752 1 0 1 +chr1 569823 1 0 1 +chr1 569890 1 0 1 +chr1 569902 1 0 1 +chr1 569912 1 0 1 +chr1 569914 1 0 1 +chr1 569917 1 0 1 +chr1 569931 0 1 1 +chr1 569942 0 1 1 +chr1 569954 0 1 1 +chr1 569960 0 1 1 +chr1 569961 0 1 1 +chr1 569963 0 1 1 +chr1 570032 0 1 1 +chr1 570109 1 0 1 +chr1 570164 0 1 1 +chr1 570169 1 0 1 +chr1 570177 0 1 1 +chr1 570226 0 1 1
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hg19_all_events_table1.tabular Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,31 @@ +### MultiGPS output +#Condition Name Index TotalSigCount SignalFraction +#Condition experiment 0 99.0 0.555 +#Replicate ParentCond Name Index SigCount CtrlCount SigCtrlScaling SignalFraction +#Replicate experiment experiment:rep1 0 99.0 0 1 0.56 +# +#Point experiment_Sig experiment_Ctrl experiment_log2Fold experiment_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 +chr1:534819 1.0 0.0 0.014 -1.348 1 +chr1:539540 1.0 0.0 0.024 -1.281 1 +chr1:539980 1.0 0.0 0.024 -1.211 1 +chr1:125172 1.0 0.0 0.033 -1.137 1 +chr1:49533 1.0 0.0 0.036 -1.059 1 +chr1:67349 1.0 0.0 0.041 -0.976 1 +chr1:563501 1.0 0.0 0.043 -0.889 1 +chr1:20107 1.0 0.0 0.046 -0.796 1 +chr1:568610 1.8 0.0 0.853 -0.696 1 +chr1:237754 2.0 0.0 1.015 -0.626 1 +chr1:236192 2.0 0.0 0.973 -0.589 1 +chr1:569214 2.0 0.0 0.989 -0.474 1 +chr1:569652 2.0 0.0 1.016 -0.433 1 +chr1:566215 2.0 0.0 0.991 -0.348 1 +chr1:234414 2.0 0.0 1.020 -0.211 1 +chr1:122967 2.0 0.0 0.996 -0.211 1 +chr1:570152 4.6 0.0 2.207 -0.100 1 +chr1:250516 2.0 0.0 0.998 -0.059 1 +chr1:527636 3.0 0.0 1.608 0.000 1 +chr1:566984 2.9 0.0 1.560 0.000 1 +chr1:526421 2.0 0.0 1.021 0.000 1
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hg19_all_events_table2.tabular Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,31 @@ +### MultiGPS output +#Condition Name Index TotalSigCount SignalFraction +#Condition experiment 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 +# +#Point experiment_Sig experiment_Ctrl experiment_log2Fold experiment_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 +chr1:534819 1.0 0.0 0.014 -1.137 1 +chr1:539540 1.0 0.0 0.024 -1.059 1 +chr1:539980 1.0 0.0 0.024 -0.976 1 +chr1:125172 1.0 0.0 0.033 -0.889 1 +chr1:563501 1.0 0.0 0.043 -0.796 1 +chr1:568610 1.8 0.0 0.853 -0.696 1 +chr1:237754 2.0 0.0 1.015 -0.626 1 +chr1:236192 2.0 0.0 0.973 -0.589 1 +chr1:569214 2.0 0.0 0.989 -0.474 1 +chr1:569652 2.0 0.0 1.016 -0.433 1 +chr1:566215 2.0 0.0 0.991 -0.348 1 +chr1:234414 2.0 0.0 1.020 -0.211 1 +chr1:122967 2.0 0.0 0.996 -0.211 1 +chr1:570152 4.6 0.0 2.207 -0.100 1 +chr1:250516 2.0 0.0 0.998 -0.059 1 +chr1:49533 1.0 1.0 -2.000 -0.006 1 +chr1:527636 3.0 0.0 1.608 0.000 1 +chr1:566984 2.9 0.0 1.560 0.000 1 +chr1:526421 2.0 0.0 1.021 0.000 1 +chr1:20107 1.0 1.0 -2.000 0.000 1 +chr1:67349 1.0 1.0 -2.000 0.000 1
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hg19_experiment_events1.tabular Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,7 @@ +### MultiGPS output +#Condition Name Index TotalSigCount SignalFraction +#Condition experiment 0 99.0 0.555 +#Replicate ParentCond Name Index SigCount CtrlCount CtrlScaling SignalFraction +#Replicate experiment experiment:rep1 0 99.0 0 1 0.555 +# +#Point experiment_Sig experiment_Ctrl experiment_log2Fold experiment_log2P Sequence MotifScore
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hg19_experiment_events2.tabular Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,7 @@ +### MultiGPS output +#Condition Name Index TotalSigCount SignalFraction +#Condition experiment 0 99.0 0.555 +#Replicate ParentCond Name Index SigCount CtrlCount CtrlScaling SignalFraction +#Replicate experiment experiment:rep1 0 99.0 18.0 4.000 0.555 +# +#Point experiment_Sig experiment_Ctrl experiment_log2Fold experiment_log2P Sequence MotifScore
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hg19_output_html1.html Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,30 @@ +<html> + <body> +</p> + <h2>Binding events</h2> + <table> + <tr> <th>Condition</th> + <th>Events</th> + <th>File</th> + </tr> + <tr> <td>experiment</td> + <td>0</td> + </tr> + </table> + <h2>Input data</h2> + <table> + <tr> <th>Replicate</th> + <th>ReadCount</th> + <th>CtrlScaling</th> + <th>SignalFraction</th> + <th>ReadDistributionModel</th> + </tr> + <tr> <td>experiment rep1</td> + <td>99.0</td> + <td>NA</td> + <td>0.555</td> + </tr> + </table> + <h2>Miscellaneous files</h2> + </body> +</html>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hg19_output_html2.html Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,30 @@ +<html> + <body> +</p> + <h2>Binding events</h2> + <table> + <tr> <th>Condition</th> + <th>Events</th> + <th>File</th> + </tr> + <tr> <td>experiment</td> + <td>0</td> + </tr> + </table> + <h2>Input data</h2> + <table> + <tr> <th>Replicate</th> + <th>ReadCount</th> + <th>CtrlScaling</th> + <th>SignalFraction</th> + <th>ReadDistributionModel</th> + </tr> + <tr> <td>experiment rep1</td> + <td>99.0</td> + <td>4.000</td> + <td>0.555</td> + </tr> + </table> + <h2>Miscellaneous files</h2> + </body> +</html>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hg19_replicates_counts1.tabular Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,25 @@ +Point experiment:rep1 +chr1:569927 14 +chr1:536042 1 +chr1:535151 1 +chr1:534819 1 +chr1:539540 1 +chr1:539980 1 +chr1:125172 1 +chr1:49533 1 +chr1:67349 1 +chr1:563501 1 +chr1:20107 1 +chr1:568610 2 +chr1:237754 2 +chr1:236192 2 +chr1:569214 2 +chr1:569652 2 +chr1:566215 2 +chr1:234414 2 +chr1:122967 2 +chr1:570152 5 +chr1:250516 2 +chr1:527636 3 +chr1:566984 3 +chr1:526421 2
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hg19_replicates_counts2.tabular Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,25 @@ +Point experiment:rep1 +chr1:569927 14 +chr1:536042 1 +chr1:535151 1 +chr1:534819 1 +chr1:539540 1 +chr1:539980 1 +chr1:125172 1 +chr1:563501 1 +chr1:568610 2 +chr1:237754 2 +chr1:236192 2 +chr1:569214 2 +chr1:569652 2 +chr1:566215 2 +chr1:234414 2 +chr1:122967 2 +chr1:570152 5 +chr1:250516 2 +chr1:49533 1 +chr1:527636 3 +chr1:566984 3 +chr1:526421 2 +chr1:20107 1 +chr1:67349 1
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/all_fasta.loc.sample Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,18 @@ +#This file lists the locations and dbkeys of all the fasta files +#under the "genome" directory (a directory that contains a directory +#for each build). The script extract_fasta.py will generate the file +#all_fasta.loc. This file has the format (white space characters are +#TAB characters): +# +#<unique_build_id> <dbkey> <display_name> <file_path> +# +#So, all_fasta.loc could look something like this: +# +#apiMel3 apiMel3 Honeybee (Apis mellifera): apiMel3 /path/to/genome/apiMel3/apiMel3.fa +#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /path/to/genome/hg19/hg19canon.fa +#hg19full hg19 Human (Homo sapiens): hg19 Full /path/to/genome/hg19/hg19full.fa +# +#Your all_fasta.loc file should contain an entry for each individual +#fasta file. So there will be multiple fasta files for each build, +#such as with hg19 above. +#
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/tool_data_table_conf.xml.sample Mon Mar 13 13:25:01 2017 -0400 @@ -0,0 +1,7 @@ +<tables> + <!-- Locations of all fasta files under genome directory --> + <table name="all_fasta" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/all_fasta.loc" /> + </table> +</tables>