# HG changeset patch # User xuebing # Date 1332270915 14400 # Node ID b11a21c704ec46e0910b9c025ef8fbabe3d6d551 # Parent a861f40db890a6ca558e8407aa54c6c874045386 Uploaded diff -r a861f40db890 -r b11a21c704ec alignr.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/alignr.xml Tue Mar 20 15:15:15 2012 -0400 @@ -0,0 +1,142 @@ + + two interval sets + alignr.py -a $inputa -w $windowsize -n $nbins -o $output_data -v $output_plot $stranded -q -l $outputlabel --ylim=$ylim --span $span + #if $inputb_source_type.inputb_select == "user": + -b "$inputb" + #else: + -b "${inputb_source_type.selectedb.fields.value}" + #end if + #if $inputa_format.inputa_select == "BAM": + -f BAM + #end if + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +**What it does** + +This tool aligns two sets of intervals, finds overlaps, calculates and plots the coverage of the first set across the second set. Applications include: + +- check read distribution around TSS/poly A site/splice site/motif site/miRNA target site +- check relative position/overlap of two lists of ChIP-seq peaks + +Two output files are generated. One is the coverage/profile for each interval in input 2. The first two columns are interval ID and the total number of overlapping intervals from input 1. Column 3 to column nbins+2 are coverage at each bin. The other file is an PDF file plotting the average coverage of each bin. To modify the visualization, please downlaod the coverage file and make your own plots. + +----- + +**Annotated features** + +Currently supports mouse genome build mm9 and human hg18. Each interval spans 1000bp upstream and 1000bp downstream of a feature such as TSS. Features with overlapping exons in the intronic/intergenic part of the 2000bp interval are removed. + +----- + +**Usage** + + -h, --help show this help message and exit + -a INPUTA (required) input file A, BED-like (first 3 columns: chr, start, end) or BAM format. The + script computes the depth of coverage of features in file + A across the features in file B + -b INPUTB (required) input file B, BED format or MACS peak file. + Requires an unique name for each line in column 4 + -m inputB is a MACS peak file. + -f AFORMAT Format of input file A. Can be BED (default) or BAM + -w WINDOW Generate new inputB by making a window of 2 x WINDOW bp + (in total) flanking the center of each input feature + -n NBINS number of bins. Features in B are binned, and the coverage + is computed for each bin. Default is 100 + -s enforce strandness: require overlapping on the same + strand. Default is off + -p load existed intersectBed outputfile + -q suppress output on screen + -o OUTPUTPROFILE (optional) output profile name. + -v PLOTFILE (optional) plot file name + + +