# HG changeset patch # User timpalpant # Date 1339272239 14400 # Node ID 3e477c7e0e73d5533a56afd85d3ff8d39584a1d5 # Parent f58706d4d4212349d41d7ccec28ee921881f095f Update normalization tools to allow normalizing by chromosome (Z-scorer, scale, etc.) Add new tool to convert any interval file to Bed format. Miscellaneous bug fixes. diff -r f58706d4d421 -r 3e477c7e0e73 dist/java-genomics-toolkit.jar Binary file dist/java-genomics-toolkit.jar has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._Autocorrelation.xml Binary file galaxy-conf/._Autocorrelation.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._Correlate.xml Binary file galaxy-conf/._Correlate.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._DNAPropertyCalculator.xml Binary file galaxy-conf/._DNAPropertyCalculator.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._Divide.xml Binary file galaxy-conf/._Divide.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._DynaPro.xml Binary file galaxy-conf/._DynaPro.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._FastqIlluminaToSanger.xml Binary file galaxy-conf/._FastqIlluminaToSanger.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._FindNMers.xml Binary file galaxy-conf/._FindNMers.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._GaussianSmooth.xml Binary file galaxy-conf/._GaussianSmooth.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._InterpolateDiscontinuousData.xml Binary file galaxy-conf/._InterpolateDiscontinuousData.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._IntervalLengthDistribution.xml Binary file galaxy-conf/._IntervalLengthDistribution.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._MapDyads.xml Binary file galaxy-conf/._MapDyads.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._MovingAverageSmooth.xml Binary file galaxy-conf/._MovingAverageSmooth.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._NRLCalculator.xml Binary file galaxy-conf/._NRLCalculator.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._ReadLengthDistributionMatrix.xml Binary file galaxy-conf/._ReadLengthDistributionMatrix.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._Summary.xml Binary file galaxy-conf/._Summary.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._WaveletTransform.xml Binary file galaxy-conf/._WaveletTransform.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._WigCorrelate.xml Binary file galaxy-conf/._WigCorrelate.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._WigSummary.xml Binary file galaxy-conf/._WigSummary.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._ZScore.xml Binary file galaxy-conf/._ZScore.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/._Zinba.xml Binary file galaxy-conf/._Zinba.xml has changed diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/Add.xml --- a/galaxy-conf/Add.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/Add.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + multiple (Big)Wig files galaxyToolRunner.sh wigmath.Add -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/Average.xml --- a/galaxy-conf/Average.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/Average.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + multiple (Big)Wig files galaxyToolRunner.sh wigmath.Average -o $output $file1 $file2 diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/BaseAlignCounts.xml --- a/galaxy-conf/BaseAlignCounts.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/BaseAlignCounts.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + of sequencing reads galaxyToolRunner.sh ngs.BaseAlignCounts -i $input -a ${chromInfo} -x $X -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/Correlate.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/galaxy-conf/Correlate.xml Sat Jun 09 16:03:59 2012 -0400 @@ -0,0 +1,60 @@ + + multiple (Big)Wig files + + galaxyToolRunner.sh wigmath.Correlate -w $window -s $step -t $type -o $output $file1 $file2 + #for $input in $inputs + ${input.file} + #end for + + + + + + + + + + + + + + + + + + + + +This tool will compute a correlation matrix between the supplied Wig or BigWig files. Each row/column in the matrix is added in the order that files are added above, starting from the top left. The Wig file is downsampled into sliding windows with the specified bin size and shift by computing the mean value in each window. These windows are then correlated using either Pearson_'s Product-Moment correlation coefficient or Spearman_'s rank correlation coefficient. If the window size is set to 1, the correlation is calculated between all base pairs in the genome. + +.. _Pearson: http://en.wikipedia.org/wiki/Pearson_product-moment_correlation_coefficient + +.. _Spearman: http://en.wikipedia.org/wiki/Spearman%27s_rank_correlation_coefficient + +----- + +**Syntax** + +- **Inputs** are the genomic data to correlate +- **Window size** is the size of the window to bin data into +- **Sliding step size** is the shift step size of the sliding window used during binning +- **Correlation metric** is the type of correlation to calculate + +----- + +.. class:: warningmark + +**WARN:** In order to calculate the correlation coefficient, the data is loaded into entirely into memory. For large genomes, this may require a lot of RAM unless comparably larger window sizes are used. + +----- + +**Citation** + +This tool was inspired by ACT_ from the Gerstein lab. + +.. _ACT: http://act.gersteinlab.org + +J Jee*, J Rozowsky*, KY Yip*, L Lochovsky, R Bjornson, G Zhong, Z Zhang, Y Fu, J Wang, Z Weng, M Gerstein. ACT: Aggregation and Correlation Toolbox for Analyses of Genome Tracks. (2011) Bioinformatics 27(8): 1152-4. + + + diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/DNAPropertyCalculator.xml --- a/galaxy-conf/DNAPropertyCalculator.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/DNAPropertyCalculator.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + for a genome galaxyToolRunner.sh dna.DNAPropertyCalculator -i #if $refGenomeSource.genomeSource == "history": @@ -85,12 +85,14 @@ + + diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/Divide.xml --- a/galaxy-conf/Divide.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/Divide.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + two (Big)Wig files galaxyToolRunner.sh wigmath.Divide -n $dividend -d $divisor -o $output @@ -9,30 +9,21 @@ - diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/Downsample.xml --- a/galaxy-conf/Downsample.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/Downsample.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + a (Big)Wig file galaxyToolRunner.sh wigmath.Downsample -i $input -m $metric -w $window -o $output @@ -16,6 +16,27 @@ + + + + + + + + + + + + + + + + + + + + + This tool can be used to reduce the resolution and file size of Wig files for easier upload to UCSC. Data is downsampled in non-overlapping windows starting from the beginning of each chromosome. Each window can be downsampled as the mean, minimum, maximum, total, or coverage of the original data. diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/DynaPro.xml --- a/galaxy-conf/DynaPro.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/DynaPro.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + using DynaPro galaxyToolRunner.sh nucleosomes.DynaPro -i $input -n $N #if str( $mean ) != '' diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/ExtractDataFromRegion.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/galaxy-conf/ExtractDataFromRegion.xml Sat Jun 09 16:03:59 2012 -0400 @@ -0,0 +1,27 @@ + + for a genomic interval + + galaxyToolRunner.sh ngs.ExtractDataFromRegion --chr $chr --start $start --stop $stop -o $output $file1 + #for $input in $inputs + ${input.file} + #end for + + + + + + + + + + + + + + + + +This tool will extract data from Wig or BigWig file(s) for a specific region of the genome. + + + diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/FastqIlluminaToSanger.xml --- a/galaxy-conf/FastqIlluminaToSanger.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/FastqIlluminaToSanger.xml Sat Jun 09 16:03:59 2012 -0400 @@ -15,11 +15,15 @@ -This tool will convert a FASTQ file with ASCII quality scores encoded in Illumina 1.3 format (Phred+64) to Sanger format (Phred+33). It is a simpler, faster version of the FASTQ Groomer. +This tool will convert a FASTQ file with ASCII quality scores encoded in Illumina 1.3-1.7 format (Phred+64) to Sanger format (Phred+33) for use with Bowtie and other Galaxy tools. Illumina CASAVA >= 1.8 already produces FASTQ files in Sanger format, so this tool should not be used on new Illumina sequencing data. This tool is a simpler, faster version of the FASTQ Groomer that does little error checking but performs much faster. If you are unsure what format your file is in, or need to do other conversions, use the FASTQ Groomer instead. + +For more information, read about FASTQ formats_ (right-click to open in new window). + +.. _formats: http://en.wikipedia.org/wiki/FASTQ_format .. class:: warningmark -This tool requires fastqillumina formatted data. If you have tabular data that was not correctly autodetected, change the metadata by clicking on the pencil icon for the dataset. +This tool requires fastqillumina formatted data. If you have fastq data that was not correctly autodetected, change the metadata by clicking on the pencil icon for the dataset. diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/FindAbsoluteMaxima.xml --- a/galaxy-conf/FindAbsoluteMaxima.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/FindAbsoluteMaxima.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + in intervals galaxyToolRunner.sh ngs.FindAbsoluteMaxima -l $window -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/FindBoundaryNucleosomes.xml --- a/galaxy-conf/FindBoundaryNucleosomes.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/FindBoundaryNucleosomes.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + in windows galaxyToolRunner.sh nucleosomes.FindBoundaryNucleosomes -i $input -l $loci -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/FindNMers.xml --- a/galaxy-conf/FindNMers.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/FindNMers.xml Sat Jun 09 16:03:59 2012 -0400 @@ -34,10 +34,19 @@ + + + + + + + + + -This tool will find all matches of a given NMer in a DNA sequence. +This tool will find all matches of a given NMer in a DNA sequence. Sequences may be provided in FASTA format or selected from available reference genomes. Mismatches are allowed, but not insertions/deletions. The output is a Bed file with the locations of matches in the reference sequence. diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/FindOutlierRegions.xml --- a/galaxy-conf/FindOutlierRegions.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/FindOutlierRegions.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + such as CNVs galaxyToolRunner.sh ngs.FindOutlierRegions -i $input -w $window -t $threshold $below -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/GaussianSmooth.xml --- a/galaxy-conf/GaussianSmooth.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/GaussianSmooth.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + a (Big)Wig file galaxyToolRunner.sh wigmath.GaussianSmooth -i $input -s $S -o $output @@ -9,48 +9,21 @@ - diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/GeneTrackToBedGraph.xml --- a/galaxy-conf/GeneTrackToBedGraph.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/GeneTrackToBedGraph.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + converter galaxyToolRunner.sh converters.GeneTrackToBedGraph -i $input -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/GeneTrackToWig.xml --- a/galaxy-conf/GeneTrackToWig.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/GeneTrackToWig.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + converter galaxyToolRunner.sh converters.GeneTrackToWig -i $input -s $shift $zero -a ${chromInfo} -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/GreedyCaller.xml --- a/galaxy-conf/GreedyCaller.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/GreedyCaller.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + in an MNase experiment galaxyToolRunner.sh nucleosomes.GreedyCaller -d $dyads -s $smoothed -n $N -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/InterpolateDiscontinuousData.xml --- a/galaxy-conf/InterpolateDiscontinuousData.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/InterpolateDiscontinuousData.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + missing values in a (Big)Wig file galaxyToolRunner.sh converters.InterpolateDiscontinousData -i $input -t $type -m $max -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/IntervalAverager.xml --- a/galaxy-conf/IntervalAverager.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/IntervalAverager.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + that have been aligned galaxyToolRunner.sh visualization.IntervalAverager -l $loci -o $output $file1 diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/IntervalLengthDistribution.xml --- a/galaxy-conf/IntervalLengthDistribution.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/IntervalLengthDistribution.xml Sat Jun 09 16:03:59 2012 -0400 @@ -8,6 +8,23 @@ + + + + + + + + + + + + + + + + + diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/IntervalToBed.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/galaxy-conf/IntervalToBed.xml Sat Jun 09 16:03:59 2012 -0400 @@ -0,0 +1,15 @@ + + converter + galaxyToolRunner.sh converters.IntervalToBed -i $input -o $output + + + + + + + + +This tool will convert any file in SAM, BAM, GFF, BedGraph, or BigBed format to Bed format. + + + diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/IntervalToWig.xml --- a/galaxy-conf/IntervalToWig.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/IntervalToWig.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + converter galaxyToolRunner.sh converters.IntervalToWig -i $input $zero -a ${chromInfo} -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/LogTransform.xml --- a/galaxy-conf/LogTransform.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/LogTransform.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + a (Big)Wig file galaxyToolRunner.sh wigmath.LogTransform -i $input -b $base -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/MapDyads.xml --- a/galaxy-conf/MapDyads.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/MapDyads.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + from sequencing reads galaxyToolRunner.sh nucleosomes.MapDyads -i $input -a ${chromInfo} -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/MovingAverageSmooth.xml --- a/galaxy-conf/MovingAverageSmooth.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/MovingAverageSmooth.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + a (Big)Wig file galaxyToolRunner.sh wigmath.MovingAverageSmooth -i $input -w $W -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/Multiply.xml --- a/galaxy-conf/Multiply.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/Multiply.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + (Big)Wig files galaxyToolRunner.sh wigmath.Multiply -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/NRLCalculator.xml --- a/galaxy-conf/NRLCalculator.xml Sat May 19 10:40:16 2012 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,35 +0,0 @@ - - from nucleosome calls - galaxyToolRunner.sh nucleosomes.NRLCalculator -i $input -l $windows -o $output - - - - - - - - - - -This tool calculates the distance between adjacent nucleosome calls (dyads) emanating from the 5' end of an interval. For each interval, the distance is calculated from the +1 to +2 nucleosome, +2 to +3 nucleosome, etc. These distances are appended as additional columns for each interval. :: - - chr start stop id alignment strand +1-to-+2 +2-to-+3 ... - -Each interval will have a different number of columns based on the number of nucleosome calls that were in that interval. - ------ - -.. class:: warningmark - -Because the distances are calculated from the 5' end of each gene, as you move into the gene body it becomes more likely that a nucleosome call will be skipped, resulting in an outlier distance (~320bp rather than ~165bp). In addition, nucleosome calls in fuzzy regions tend to be inaccurate, so the NRL distances will not be robust. - -.. class:: warningmark - -This tool requires a set of nucleosome calls as input in the format created by the Nucleosomes -> Call Nucleosomes tool. - -.. class:: warningmark - -Intervals must be provided in Bed, BedGraph, or GFF format. BedGraph intervals are always considered to be on the + strand. - - - diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/PercusDecomposition.xml --- a/galaxy-conf/PercusDecomposition.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/PercusDecomposition.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + from occupancy data galaxyToolRunner.sh nucleosomes.PercusDecomposition -d $dyads -n $N -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/PredictFAIRESignal.xml --- a/galaxy-conf/PredictFAIRESignal.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/PredictFAIRESignal.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,11 +1,11 @@ - + from nucleosome occupancy galaxyToolRunner.sh nucleosomes.PredictFAIRESignal -i $input -s $sonication -c $crosslinking -x $extend -o $output - + diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/RollingReadLength.xml --- a/galaxy-conf/RollingReadLength.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/RollingReadLength.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + over each locus galaxyToolRunner.sh ngs.RollingReadLength -i $input -a ${chromInfo} -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/Scale.xml --- a/galaxy-conf/Scale.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/Scale.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,9 +1,10 @@ - + a (Big)Wig file - galaxyToolRunner.sh wigmath.Scale -i $input -m $M -o $output + galaxyToolRunner.sh wigmath.Scale -i $input -m $M $chr -o $output + @@ -49,7 +50,7 @@ -This tool will multiply all values in a Wig file by a scalar. For example, this can be used to normalize to read depth by multiplying by 1/(# reads). By default, the tool will scale to 1/(mean value), which is equivalent to dividing by coverage and multiplying by the size of the genome. The resulting output file should have mean 1. +This tool will multiply all values in a Wig file by a scale factor. For example, this can be used to normalize to read depth by multiplying by 1/(# reads). By default, the tool will scale to 1/(mean value), which is equivalent to dividing by coverage and multiplying by the size of the genome. The resulting output file should have mean 1. .. class:: infomark diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/Shift.xml --- a/galaxy-conf/Shift.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/Shift.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,9 +1,10 @@ - + a (Big)Wig file - galaxyToolRunner.sh wigmath.Shift -i $input -m $M -o $output + galaxyToolRunner.sh wigmath.Shift -i $input -m $M $chr -o $output + diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/StripMatrix.xml --- a/galaxy-conf/StripMatrix.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/StripMatrix.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + from an aligned matrix galaxyToolRunner.sh visualization.StripMatrix -i $input -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/Subtract.xml --- a/galaxy-conf/Subtract.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/Subtract.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + two (Big)Wig files galaxyToolRunner.sh wigmath.Subtract -m $minuend -s $subtrahend -o $output diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/Summary.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/galaxy-conf/Summary.xml Sat Jun 09 16:03:59 2012 -0400 @@ -0,0 +1,83 @@ + + of a (Big)Wig file + galaxyToolRunner.sh wigmath.Summary -i $input -o $output + + + + + + + + + + + + + + + + + + + + + + + +This tool will output a summary of a Wig or BigWig file, including information about the chromosomes and types of contigs in the Wig file, as well as basic descriptive statistics. + +----- + +**Example:** + +The following is an example of the output of this tool :: + + ASCII Text Wiggle file: track type=wiggle_0 + Chromosomes: + 2micron start=1 stop=6318 + chrVI start=1 stop=270148 + chrI start=1 stop=230208 + chrIII start=1 stop=316617 + chrXII start=1 stop=1078175 + chrXV start=1 stop=1091289 + chrXVI start=1 stop=948062 + chrII start=1 stop=813178 + chrVIII start=1 stop=562643 + chrX start=1 stop=745742 + chrXIII start=1 stop=924429 + chrV start=1 stop=576869 + chrXIV start=1 stop=784333 + chrIV start=1 stop=1531919 + chrXI start=1 stop=666454 + chrIX start=1 stop=439885 + chrM start=1 stop=85779 + chrVII start=1 stop=1090947 + Contigs: + fixedStep chrom=2micron start=1 span=1 step=1 + fixedStep chrom=chrVI start=1 span=1 step=1 + fixedStep chrom=chrI start=1 span=1 step=1 + fixedStep chrom=chrIII start=1 span=1 step=1 + fixedStep chrom=chrXII start=1 span=1 step=1 + fixedStep chrom=chrXVI start=1 span=1 step=1 + fixedStep chrom=chrXV start=1 span=1 step=1 + fixedStep chrom=chrII start=1 span=1 step=1 + fixedStep chrom=chrVIII start=1 span=1 step=1 + fixedStep chrom=chrXIII start=1 span=1 step=1 + fixedStep chrom=chrX start=1 span=1 step=1 + fixedStep chrom=chrV start=1 span=1 step=1 + fixedStep chrom=chrXIV start=1 span=1 step=1 + fixedStep chrom=chrIV start=1 span=1 step=1 + fixedStep chrom=chrXI start=1 span=1 step=1 + fixedStep chrom=chrIX start=1 span=1 step=1 + fixedStep chrom=chrM start=1 span=1 step=1 + fixedStep chrom=chrVII start=1 span=1 step=1 + Basic Statistics: + Mean: 1.000000164913575 + Standard Deviation: 1.8843731523620193 + Total: 1.2162997005843896E7 + Bases Covered: 12162995 + Min value: 0.0 + Max value: 277.98996 + + + diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/ValueDistribution.xml --- a/galaxy-conf/ValueDistribution.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/ValueDistribution.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,4 +1,4 @@ - + of a (Big)Wig file galaxyToolRunner.sh wigmath.ValueDistribution -i $input #if str( $min ) != '' diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/WaveletTransform.xml --- a/galaxy-conf/WaveletTransform.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/WaveletTransform.xml Sat Jun 09 16:03:59 2012 -0400 @@ -9,7 +9,7 @@ - + @@ -17,5 +17,24 @@ +This tool will perform a Wavelet_ scaling_ analysis on an interval of genomic data. For each base pair in the interval, the similarity (correlation) is calculated between the data and the wavelet over a range of scales. This can be used to identify high-frequency and low-frequency features in the data. The output is a matrix in matrix2png format that can be used to generate a heatmap: along the x-axis (columns) are the base pairs in the interval, along the y-axis (rows) are the correlation coefficients for each Wavelet size, with the largest Wavelet scale at the top and the smallest scale at the bottom. + +.. _Wavelet: http://en.wikipedia.org/wiki/Wavelet + +.. _scaling: http://en.wikipedia.org/wiki/Scaleogram + +----- + +**Syntax** + +- **Input data** is the genomic data on which to compute the Wavelet scaling analysis. +- **Wavelet** a single column of values representing a discrete Wavelet. +- **Chromosome** a locus in the genome +- **Start base pair** a locus in the genome +- **Stop base pair** a locus in the genome +- **Minimum wavelet size** the smallest Wavelet to analyze +- **Minimum wavelet size** the largest Wavelet to analyze +- **Scaling step size** the step size for the range of wavelet scales. The provided wavelet will be scaled to each size in the set min:step:max by interpolating the provided wavelet. + diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/WigCorrelate.xml --- a/galaxy-conf/WigCorrelate.xml Sat May 19 10:40:16 2012 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,58 +0,0 @@ - - multiple (Big)Wig files - - galaxyToolRunner.sh wigmath.WigCorrelate -w $window -s $step -t $type -o $output - #for $input in $inputs - ${input.file} - #end for - - - - - - - - - - - - - - - - - - -This tool will compute a correlation matrix between the supplied Wig or BigWig files. Each row/column in the matrix is added in the order that files are added above, starting from the top left. The Wig file is downsampled into sliding windows with the specified bin size and shift by computing the mean value in each window. These windows are then correlated using either Pearson_'s Product-Moment correlation coefficient or Spearman_'s rank correlation coefficient. If the window size is set to 1, the correlation is calculated between all base pairs in the genome. - -.. _Pearson: http://en.wikipedia.org/wiki/Pearson_product-moment_correlation_coefficient - -.. _Spearman: http://en.wikipedia.org/wiki/Spearman%27s_rank_correlation_coefficient - ------ - -**Syntax** - -- **Inputs** are the genomic data to correlate -- **Window size** is the size of the window to bin data into -- **Sliding step size** is the shift step size of the sliding window used during binning -- **Correlation metric** is the type of correlation to calculate - ------ - -.. class:: warningmark - -**WARN:** In order to calculate the correlation coefficient, the data is loaded into entirely into memory. For large genomes, this may require a lot of RAM unless comparably larger window sizes are used. - ------ - -**Citation** - -This tool was inspired by ACT_ from the Gerstein lab. - -.. _ACT: http://act.gersteinlab.org - -J Jee*, J Rozowsky*, KY Yip*, L Lochovsky, R Bjornson, G Zhong, Z Zhang, Y Fu, J Wang, Z Weng, M Gerstein. ACT: Aggregation and Correlation Toolbox for Analyses of Genome Tracks. (2011) Bioinformatics 27(8): 1152-4. - - - diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/WigSummary.xml --- a/galaxy-conf/WigSummary.xml Sat May 19 10:40:16 2012 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,83 +0,0 @@ - - of a (Big)Wig file - galaxyToolRunner.sh wigmath.WigSummary -i $input -o $output - - - - - - - - - - - - - - - - - - - - - - - -This tool will output a summary of a Wig or BigWig file, including information about the chromosomes and types of contigs in the Wig file, as well as basic descriptive statistics. - ------ - -**Example:** - -The following is an example of the output of this tool :: - - ASCII Text Wiggle file: track type=wiggle_0 - Chromosomes: - 2micron start=1 stop=6318 - chrVI start=1 stop=270148 - chrI start=1 stop=230208 - chrIII start=1 stop=316617 - chrXII start=1 stop=1078175 - chrXV start=1 stop=1091289 - chrXVI start=1 stop=948062 - chrII start=1 stop=813178 - chrVIII start=1 stop=562643 - chrX start=1 stop=745742 - chrXIII start=1 stop=924429 - chrV start=1 stop=576869 - chrXIV start=1 stop=784333 - chrIV start=1 stop=1531919 - chrXI start=1 stop=666454 - chrIX start=1 stop=439885 - chrM start=1 stop=85779 - chrVII start=1 stop=1090947 - Contigs: - fixedStep chrom=2micron start=1 span=1 step=1 - fixedStep chrom=chrVI start=1 span=1 step=1 - fixedStep chrom=chrI start=1 span=1 step=1 - fixedStep chrom=chrIII start=1 span=1 step=1 - fixedStep chrom=chrXII start=1 span=1 step=1 - fixedStep chrom=chrXVI start=1 span=1 step=1 - fixedStep chrom=chrXV start=1 span=1 step=1 - fixedStep chrom=chrII start=1 span=1 step=1 - fixedStep chrom=chrVIII start=1 span=1 step=1 - fixedStep chrom=chrXIII start=1 span=1 step=1 - fixedStep chrom=chrX start=1 span=1 step=1 - fixedStep chrom=chrV start=1 span=1 step=1 - fixedStep chrom=chrXIV start=1 span=1 step=1 - fixedStep chrom=chrIV start=1 span=1 step=1 - fixedStep chrom=chrXI start=1 span=1 step=1 - fixedStep chrom=chrIX start=1 span=1 step=1 - fixedStep chrom=chrM start=1 span=1 step=1 - fixedStep chrom=chrVII start=1 span=1 step=1 - Basic Statistics: - Mean: 1.000000164913575 - Standard Deviation: 1.8843731523620193 - Total: 1.2162997005843896E7 - Bases Covered: 12162995 - Min value: 0.0 - Max value: 277.98996 - - - diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/ZScore.xml --- a/galaxy-conf/ZScore.xml Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/ZScore.xml Sat Jun 09 16:03:59 2012 -0400 @@ -1,8 +1,9 @@ - + a (Big)Wig file - galaxyToolRunner.sh wigmath.ZScore -i $input -o $output + galaxyToolRunner.sh wigmath.ZScore -i $input $chr -o $output + diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/Zinba.xml --- a/galaxy-conf/Zinba.xml Sat May 19 10:40:16 2012 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,16 +0,0 @@ - - with ZINBA - runZINBA.sh -i $input -o $output - - - - - - - - - - - - - diff -r f58706d4d421 -r 3e477c7e0e73 galaxy-conf/log4j.properties --- a/galaxy-conf/log4j.properties Sat May 19 10:40:16 2012 -0400 +++ b/galaxy-conf/log4j.properties Sat Jun 09 16:03:59 2012 -0400 @@ -7,4 +7,6 @@ log4j.appender.stdout.layout.ConversionPattern=%m%n # Only output errors from the BigWig library -log4j.logger.org.broad.igv.bbfile=ERROR \ No newline at end of file +log4j.logger.org.broad.igv.bbfile=ERROR +# Only output errors from java-genomics-io +log4j.logger.edu.unc.genomics.io=ERROR \ No newline at end of file diff -r f58706d4d421 -r 3e477c7e0e73 lib/java-genomics-io.jar Binary file lib/java-genomics-io.jar has changed diff -r f58706d4d421 -r 3e477c7e0e73 lib/jcommander-1.20.jar Binary file lib/jcommander-1.20.jar has changed diff -r f58706d4d421 -r 3e477c7e0e73 lib/jcommander-1.27.jar Binary file lib/jcommander-1.27.jar has changed diff -r f58706d4d421 -r 3e477c7e0e73 tool_data_table_conf.xml.sample --- a/tool_data_table_conf.xml.sample Sat May 19 10:40:16 2012 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,118 +0,0 @@ - - - - - value, dbkey, name, path - -
- - - value, dbkey, formats, name, path - -
- - - value, name, path - -
- - - value, name, path - -
- - - value, dbkey, name, path - -
- - - value, dbkey, name, path - -
- - - value, dbkey, name, path - -
- - - value, dbkey, name, path - -
- - - value, dbkey, name, path - -
- - - name, value, dbkey, species - -
- - - value, dbkey, name, path - -
- - - value, name, path - -
- - - value, name, path - -
- - - value, name, path - -
- - - line_type, value, path - -
- - - value, dbkey, name, path - -
- - - value, dbkey, name, path - -
- - - value, name, gatk_value, tools_valid_for - -
- - - value, dbkey, name, path - -
- - - value, dbkey, name, path - -
- - - value, dbkey, name, path - -
- - - value, name, path - -
- - - value, dbkey, name, path - -
-