# HG changeset patch # User nilesh # Date 1380694804 14400 # Node ID cc5eaa9376d85d5ae9d83d44a27ca6d3d452174a # Parent b5d2f575ccb654e666a341869de76dfc95c685a1 Lance's updates diff -r b5d2f575ccb6 -r cc5eaa9376d8 RPKM_count.xml --- a/RPKM_count.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/RPKM_count.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,15 +1,14 @@ - + calculates raw count and RPKM values for transcript at exon, intron, and mRNA level - samtools + numpy rseqc - samtoolshelper.py RPKM_count.py -i $input -o output -r $refgene + + ln -s "${input}" "local_input.bam" && + ln -s "${input.metadata.bam_index}" "local_input.bam.bai" && + RPKM_count.py -i "local_input.bam" -o output -r $refgene - #if $nx - -x - #end if - #if str($strand_type.strand_specific) == "pair" -d #if str($strand_type.pair_type) == "sd" @@ -66,17 +65,19 @@ + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 - ------ +RPKM_count.py ++++++++++++++ -About RSeQC -+++++++++++ - -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. +Given a BAM file and reference gene model, this program will calculate the raw count and RPKM +values for transcript at exon, intron and mRNA level. For strand specific RNA-seq data, +program will assign read to its parental gene according to strand rule, if you don't know the +strand rule, run infer_experiment.py. Please note that chromosome ID, genome cooridinates +should be concordant between BAM and BED files. Inputs ++++++++++++++ @@ -102,46 +103,30 @@ Sample Output ++++++++++++++ -===== ===== === ========= ===== =========== ============= ============= ======== ======== -chrom start end accession score gene strand tag count (+) tag count (-) RPKM (+) RPKM (-) -===== ===== === ========= ===== =========== ============= ============= ======== ======== -chr1 29213722 29313959 NM_001166007_intron_1 0 + 431 4329 0.086 0.863 -chr1 29314417 29319841 NM_001166007_intron_2 0 + 31 1 0.114 0.004 -chr1 29320054 29323726 NM_001166007_intron_3 0 + 32 0 0.174 0 -chr1 29323831 29338376 NM_001166007_intron_4 0 + 33 2 0.045 0.003 -chr1 29338419 29342203 NM_001166007_intron_5 0 + 7 0 0.037 0 -chr1 29342279 29344735 NM_001166007_intron_6 0 + 35 4 0.285 0.033 -chr1 29344954 29356911 NM_001166007_intron_7 0 + 34 2 0.057 0.003 -chr1 29356999 29359604 NM_001166007_intron_8 0 + 19 1 0.146 0.008 -chr1 29359757 29362337 NM_001166007_intron_9 0 + 31 0 0.24 0 -chr1 29362435 29365765 NM_001166007_intron_10 0 + 11 1 0.066 0.006 -chr1 29365938 29379615 NM_001166007_intron_11 0 + 63 0 0.092 0 -chr1 29379824 29391493 NM_001166007_intron_12 0 + 383 8 0.656 0.014 -chr1 29391670 29424318 NM_001166007_intron_13 0 + 817 10 0.5 0.006 -chr1 29424447 29435847 NM_001166007_intron_14 0 + 28 0 0.049 0 -chr1 29435949 29438879 NM_001166007_intron_15 0 + 12 0 0.082 0 -chr1 29438960 29442210 NM_001166007_intron_16 0 + 22 2 0.135 0.012 -chr1 29442315 29443330 NM_001166007_intron_17 0 + 9 0 0.177 0 -chr1 29213602 29213722 NM_001166007_exon_1 0 + 164 0 27.321 0 -chr1 29313959 29314417 NM_001166007_exon_2 0 + 1699 4 74.158 0.175 -chr1 29319841 29320054 NM_001166007_exon_3 0 + 528 1 49.554 0.094 -chr1 29323726 29323831 NM_001166007_exon_4 0 + 168 0 31.985 0 -chr1 29338376 29338419 NM_001166007_exon_5 0 + 88 0 40.911 0 -chr1 29342203 29342279 NM_001166007_exon_6 0 + 114 3 29.986 0.789 -chr1 29344735 29344954 NM_001166007_exon_7 0 + 290 10 26.472 0.913 -chr1 29356911 29356999 NM_001166007_exon_8 0 + 146 1 33.166 0.227 -chr1 29359604 29359757 NM_001166007_exon_9 0 + 404 11 52.786 1.437 -chr1 29362337 29362435 NM_001166007_exon_10 0 + 85 7 17.339 1.428 -chr1 29365765 29365938 NM_001166007_exon_11 0 + 198 2 22.88 0.231 -chr1 29379615 29379824 NM_001166007_exon_12 0 + 306 5 29.269 0.478 -chr1 29391493 29391670 NM_001166007_exon_13 0 + 243 7 27.445 0.791 -chr1 29424318 29424447 NM_001166007_exon_14 0 + 298 7 46.18 1.085 -chr1 29435847 29435949 NM_001166007_exon_15 0 + 396 8 77.611 1.568 -chr1 29438879 29438960 NM_001166007_exon_16 0 + 307 0 75.767 0 -chr1 29442210 29442315 NM_001166007_exon_17 0 + 138 0 26.273 0 -chr1 29443330 29446558 NM_001166007_exon_18 0 + 2434 84 15.074 0.52 -chr1 29213602 29446558 NM_001166007_mRNA 0 + 8006 150 27.704 0.519 -===== ===== === ========= ===== =========== ============= ============= ======== ======== +===== ======== ======== ===================== ===== =========== ============= ============= ======== ========= +chrom start end accession score gene strand tag count (+) tag count (-) RPKM (+) RPKM (-) +===== ======== ======== ===================== ===== =========== ============= ============= ======== ========= +chr1 29213722 29313959 NM_001166007_intron_1 0 '+' 431 4329 0.086 0.863 +chr1 29314417 29319841 NM_001166007_intron_2 0 '+' 31 1 0.114 0.004 +chr1 29320054 29323726 NM_001166007_intron_3 0 '+' 32 0 0.174 0.000 +chr1 29213602 29213722 NM_001166007_exon_1 0 '+' 164 0 27.321 0.000 +chr1 29313959 29314417 NM_001166007_exon_2 0 '+' 1699 4 74.158 0.175 +chr1 29319841 29320054 NM_001166007_exon_3 0 '+' 528 1 49.554 0.094 +===== ======== ======== ===================== ===== =========== ============= ============= ======== ========= +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ + + diff -r b5d2f575ccb6 -r cc5eaa9376d8 RPKM_saturation.xml --- a/RPKM_saturation.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/RPKM_saturation.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,10 +1,11 @@ - + calculates raw count and RPKM values for transcript at exon, intron, and mRNA level - R + R + numpy rseqc - RPKM_saturation.py -i $input -o output -r $refgene + RPKM_saturation.py -i $input -o output -r $refgene #if str($strand_type.strand_specific) == "pair" -d @@ -56,22 +57,37 @@ - - - - + + + + + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 +RPKM_saturation.py +++++++++++++++++++ ------ +The precision of any sample statitics (RPKM) is affected by sample size (sequencing depth); +\'resampling\' or \'jackknifing\' is a method to estimate the precision of sample statistics by +using subsets of available data. This module will resample a series of subsets from total RNA +reads and then calculate RPKM value using each subset. By doing this we are able to check if +the current sequencing depth was saturated or not (or if the RPKM values were stable or not) +in terms of genes' expression estimation. If sequencing depth was saturated, the estimated +RPKM value will be stationary or reproducible. By default, this module will calculate 20 +RPKM values (using 5%, 10%, ... , 95%,100% of total reads) for each transcripts. -About RSeQC -+++++++++++ +In the output figure, Y axis is "Percent Relative Error" or "Percent Error" which is used +to measures how the RPKM estimated from subset of reads (i.e. RPKMobs) deviates from real +expression level (i.e. RPKMreal). However, in practice one cannot know the RPKMreal. As a +proxy, we use the RPKM estimated from total reads to approximate RPKMreal. -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. +.. image:: http://rseqc.sourceforge.net/_images/RelativeError.png + :height: 80 px + :width: 400 px + :scale: 100 % Inputs ++++++++++++++ @@ -102,7 +118,10 @@ 3. output.saturation.r: R script to generate plot 4. output.saturation.pdf: -.. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/saturation.png +.. image:: http://rseqc.sourceforge.net/_images/saturation.png + :height: 600 px + :width: 600 px + :scale: 80 % - All transcripts were sorted in ascending order according to expression level (RPKM). Then they are divided into 4 groups: 1. Q1 (0-25%): Transcripts with expression level ranked below 25 percentile. @@ -111,8 +130,31 @@ 4. Q4 (75-100%): Transcripts with expression level ranked above 75 percentile. - BAM/SAM file containing more than 100 million alignments will make module very slow. - Follow example below to visualize a particular transcript (using R console):: -- output example -.. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/saturation_eg.png + + pdf("xxx.pdf") #starts the graphics device driver for producing PDF graphics + x <- seq(5,100,5) #resampling percentage (5,10,15,...,100) + rpkm <- c(32.95,35.43,35.15,36.04,36.41,37.76,38.96,38.62,37.81,38.14,37.97,38.58,38.59,38.54,38.67, 38.67,38.87,38.68, 38.42, 38.23) #Paste RPKM values calculated from each subsets + scatter.smooth(x,100*abs(rpkm-rpkm[length(rpkm)])/(rpkm[length(rpkm)]),type="p",ylab="Precent Relative Error",xlab="Resampling Percentage") + dev.off() #close graphical device + +.. image:: http://rseqc.sourceforge.net/_images/saturation_eg.png + :height: 600 px + :width: 600 px + :scale: 80 % + +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ + diff -r b5d2f575ccb6 -r cc5eaa9376d8 bam2wig.xml --- a/bam2wig.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/bam2wig.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,14 +1,16 @@ - + converts all types of RNA-seq data from .bam to .wig - R - samtools + R + numpy rseqc - - samtoolshelper.py /home/nilesh/RSeQC-2.3.3/scripts/bam2wig.py -i $input -s $chromsize -o outfile + + ln -s "${input}" "local_input.bam" && + ln -s "${input.metadata.bam_index}" "local_input.bam.bai" && + bam2wig.py -i "local_input.bam" -s $chromsize -o outfile #if str($strand_type.strand_specific) == "pair" -d @@ -73,24 +75,29 @@ strand_type['strand_specific'] == 'none' - + strand_type['strand_specific'] != 'none' - + strand_type['strand_specific'] != 'none' + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 - ------ +bam2wig.py +++++++++++ -About RSeQC -+++++++++++ - -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. +Visualization is the most straightforward and effective way to QC your RNA-seq +data. For example, change of expression or new splicing can be easily checked +by visually comparing two RNA-seq tracks using genome browser such as UCSC_, +IGB_ and IGV_. `bam2wig.py` converts all types of RNA-seq data from BAM_ +format into wiggle_ format in one-stop. wiggle_ files can then be easily +converted into bigwig_. Bigwig is indexed, binary format of wiggle file, and +it's particular useful to display large, continuous dataset on genome +browser. Inputs ++++++++++++++ @@ -116,6 +123,25 @@ If RNA-seq is not strand specific, one wig file will be generated, if RNA-seq is strand specific, two wig files corresponding to Forward and Reverse will be generated. +----- + +About RSeQC ++++++++++++ + + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ +.. _UCSC: http://genome.ucsc.edu/index.html +.. _IGB: http://bioviz.org/igb/ +.. _IGV: http://www.broadinstitute.org/igv/home +.. _BAM: http://genome.ucsc.edu/goldenPath/help/bam.html +.. _wiggle: http://genome.ucsc.edu/goldenPath/help/wiggle.html +.. _bigwig: http://genome.ucsc.edu/FAQ/FAQformat.html#format6.1 - \ No newline at end of file + diff -r b5d2f575ccb6 -r cc5eaa9376d8 bam_stat.xml --- a/bam_stat.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/bam_stat.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,12 +1,13 @@ - + reads mapping statistics for a provided BAM or SAM file. + numpy rseqc s - - bam_stat.py -i $input -q $mapqual > $output + + bam_stat.py -i $input -q $mapqual 2> $output @@ -15,17 +16,19 @@ + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 - ------ - -About RSeQC +bam_stat.py +++++++++++ -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. +This program is used to calculate reads mapping statistics from provided BAM +file. This script determines "uniquely mapped reads" from `mapping quality`_, +which quality the probability that a read is misplaced (Do NOT confused with +sequence quality, sequence quality measures the probability that a base-calling +was wrong) . Inputs ++++++++++++++ @@ -44,6 +47,19 @@ - Uniquely mapped Reads = {Reads map to '+'} + {Reads map to '-'} - Uniquely mapped Reads = {Splice reads} + {Non-splice reads} +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ +.. _`mapping quality`: http://genome.sph.umich.edu/wiki/Mapping_Quality_Scores - \ No newline at end of file + diff -r b5d2f575ccb6 -r cc5eaa9376d8 clipping_profile.xml --- a/clipping_profile.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/clipping_profile.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,12 +1,13 @@ - + estimates clipping profile of RNA-seq reads from BAM or SAM file - R + R + numpy rseqc - + clipping_profile.py -i $input -o output @@ -16,17 +17,17 @@ + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 - ------ +clipping_profile.py ++++++++++++++++++++ -About RSeQC -+++++++++++ - -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. +This program is used to estimate clipping profile of RNA-seq reads from BAM or SAM file. +Note that to use this funciton, CIGAR strings within SAM/BAM file should have 'S' operation +(This means your reads aligner should support clipped mapping). Inputs ++++++++++++++ @@ -38,8 +39,23 @@ Sample Output ++++++++++++++ -.. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/clipping_good.png +.. image:: http://rseqc.sourceforge.net/_images/clipping_good.png + :height: 600 px + :width: 600 px + :scale: 80 % + +----- +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ - \ No newline at end of file + diff -r b5d2f575ccb6 -r cc5eaa9376d8 geneBody_coverage.xml --- a/geneBody_coverage.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/geneBody_coverage.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,12 +1,13 @@ - + Read coverage over gene body. - R + R + numpy rseqc - + geneBody_coverage.py -i $input -r $refgene -o output @@ -14,21 +15,25 @@ - - - - + + + + + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 +geneBody_coverage.py +++++++++++++++++++++ ------ - -About RSeQC -+++++++++++ - -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. +Read coverage over gene body. This module is used to check if reads coverage is uniform and +if there is any 5\'/3\' bias. This module scales all transcripts to 100 nt and calculates the +number of reads covering each nucleotide position. Finally, it generates a plot illustrating +the coverage profile along the gene body. NOTE: this module requires lots of memory for large +BAM files, because it load the entire BAM file into memory. We add another script +"geneBody_coverage2.py" into v2.3.1 which takes bigwig (instead of BAM) as input. +It only use 200M RAM, but users need to convert BAM into WIG, and then WIG into BigWig. Inputs ++++++++++++++ @@ -46,9 +51,26 @@ Read coverage over gene body. This module is used to check if reads coverage is uniform and if there is any 5’/3’ bias. This module scales all transcripts to 100 nt and calculates the number of reads covering each nucleotide position. Finally, it generates a plot illustrating the coverage profile along the gene body. NOTE: this module requires lots of memory for large BAM files, because it load the entire BAM file into memory. We add another script "geneBody_coverage2.py" into v2.3.1 which takes bigwig (instead of BAM) as input. It only use 200M RAM, but users need to convert BAM into WIG, and then WIG into BigWig. Example output: - .. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/geneBody_coverage.png + .. image:: http://rseqc.sourceforge.net/_images/geneBody_coverage.png + :height: 600 px + :width: 600 px + :scale: 80 % + + +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ - \ No newline at end of file + diff -r b5d2f575ccb6 -r cc5eaa9376d8 geneBody_coverage2.xml --- a/geneBody_coverage2.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/geneBody_coverage2.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,12 +1,13 @@ - + Read coverage over gene body. - R + R + numpy rseqc - + geneBody_coverage2.py -i $input -r $refgene -o output @@ -14,21 +15,21 @@ - - - - + + + + + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 +geneBody_coverage2.py ++++++++++++++++++++++ ------ +Similar to geneBody_coverage.py. This module takes bigwig instead of BAM as input, and thus +requires much less memory. The BigWig file could be arbitrarily large. -About RSeQC -+++++++++++ - -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. Inputs ++++++++++++++ @@ -46,9 +47,25 @@ Read coverage over gene body. This module is used to check if reads coverage is uniform and if there is any 5’/3’ bias. This module scales all transcripts to 100 nt and calculates the number of reads covering each nucleotide position. Finally, it generates a plot illustrating the coverage profile along the gene body. NOTE: this module requires lots of memory for large BAM files, because it load the entire BAM file into memory. We add another script "geneBody_coverage2.py" into v2.3.1 which takes bigwig (instead of BAM) as input. It only use 200M RAM, but users need to convert BAM into WIG, and then WIG into BigWig. Example output: - .. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/geneBody_coverage.png + .. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/geneBody_coverage.png + :height: 600 px + :width: 600 px + :scale: 80 % + +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ - \ No newline at end of file + diff -r b5d2f575ccb6 -r cc5eaa9376d8 infer_experiment.xml --- a/infer_experiment.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/infer_experiment.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,9 +1,10 @@ - + speculates how RNA-seq were configured + numpy rseqc - infer_experiment.py -i $input -r $refgene + infer_experiment.py -i $input -r $refgene #if $sample_size.boolean -s $sample_size.size @@ -24,17 +25,18 @@ + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 - ------ +infer_experiment.py ++++++++++++++++++++ -About RSeQC -+++++++++++ +This program is used to speculate how RNA-seq sequencing were configured, especially how +reads were stranded for strand-specific RNA-seq data, through comparing reads' mapping +information to the underneath gene model. -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. Inputs ++++++++++++++ @@ -48,32 +50,38 @@ Number of usable sampled reads (default=200000) Number of usable reads sampled from SAM/BAM file. More reads will give more accurate estimation, but make program little slower. +Outputs ++++++++ -Output -++++++++++++++ -This program is used to speculate how RNA-seq sequencing were configured, especially how reads were stranded for strand-specific RNA-seq data, through comparing reads' mapping information to the underneath gene model. Generally, strand specific RNA-seq data should be handled differently in both visualization and RPKM calculation. +For pair-end RNA-seq, there are two different +ways to strand reads (such as Illumina ScriptSeq protocol): -For pair-end RNA-seq, there are two different ways to strand reads: +1. 1++,1--,2+-,2-+ -1) 1++,1--,2+-,2-+ - - read1 mapped to '+' strand indicates parental gene on '+' strand - - read1 mapped to '-' strand indicates parental gene on '-' strand - - read2 mapped to '+' strand indicates parental gene on '-' strand - - read2 mapped to '-' strand indicates parental gene on '+' strand -2) 1+-,1-+,2++,2-- - - read1 mapped to '+' strand indicates parental gene on '-' strand - - read1 mapped to '-' strand indicates parental gene on '+' strand - - read2 mapped to '+' strand indicates parental gene on '+' strand - - read2 mapped to '-' strand indicates parental gene on '-' strand +* read1 mapped to '+' strand indicates parental gene on '+' strand +* read1 mapped to '-' strand indicates parental gene on '-' strand +* read2 mapped to '+' strand indicates parental gene on '-' strand +* read2 mapped to '-' strand indicates parental gene on '+' strand + +2. 1+-,1-+,2++,2-- + +* read1 mapped to '+' strand indicates parental gene on '-' strand +* read1 mapped to '-' strand indicates parental gene on '+' strand +* read2 mapped to '+' strand indicates parental gene on '+' strand +* read2 mapped to '-' strand indicates parental gene on '-' strand For single-end RNA-seq, there are also two different ways to strand reads: -1) ++,-- - -read mapped to '+' strand indicates parental gene on '+' strand - - read mapped to '-' strand indicates parental gene on '-' strand -2) +-,-+ - - read mapped to '+' strand indicates parental gene on '-' strand - - read mapped to '-' strand indicates parental gene on '+' strand +1. ++,-- + +* read mapped to '+' strand indicates parental gene on '+' strand +* read mapped to '-' strand indicates parental gene on '-' strand + +2. +-,-+ + +* read mapped to '+' strand indicates parental gene on '-' strand +* read mapped to '-' strand indicates parental gene on '+' strand + Example Output ++++++++++++++ @@ -113,5 +121,21 @@ ========================================================= *Conclusion*: This is single-end, strand specific RNA-seq data. Strandness of reads are concordant with strandness of reference gene. + + +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ + + - \ No newline at end of file + diff -r b5d2f575ccb6 -r cc5eaa9376d8 inner_distance.xml --- a/inner_distance.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/inner_distance.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,10 +1,11 @@ - + calculate the inner distance (or insert size) between two paired RNA reads - R + R + numpy rseqc - inner_distance.py -i $input -o output -r $refgene + inner_distance.py -i $input -o output -r $refgene #if $bounds.hasLowerBound -l $bounds.lowerBound @@ -41,22 +42,30 @@ - - - - + + + + + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 +inner_distance.py ++++++++++++++++++ ------ +This module is used to calculate the inner distance (or insert size) between two paired RNA +reads. The distance is the mRNA length between two paired fragments. We first determine the +genomic (DNA) size between two paired reads: D_size = read2_start - read1_end, then -About RSeQC -+++++++++++ +* if two paired reads map to the same exon: inner distance = D_size +* if two paired reads map to different exons:inner distance = D_size - intron_size +* if two paired reads map non-exonic region (such as intron and intergenic region): inner distance = D_size +* The inner_distance might be a negative value if two fragments were overlapped. -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. +NOTE: Not all read pairs were used to estimate the inner distance distribution. Those low +quality, PCR duplication, multiple mapped reads were skipped. Inputs ++++++++++++++ @@ -78,18 +87,36 @@ ++++++++++++++ 1. output.inner_distance.txt: -- first column is read ID --second column is inner distance. Could be negative value if PE reads were overlapped or mapping error (e.g. Read1_start < Read2_start, while Read1_end >> Read2_end due to spliced mapping of read1) -- third column indicates how paired reads were mapped: PE_within_same_exon, PE_within_diff_exon,PE_reads_overlap + - first column is read ID + -second column is inner distance. Could be negative value if PE reads were overlapped or mapping error (e.g. Read1_start < Read2_start, while Read1_end >> Read2_end due to spliced mapping of read1) + - third column indicates how paired reads were mapped: PE_within_same_exon, PE_within_diff_exon,PE_reads_overlap 2. output..inner_distance_freq.txt: -- inner distance starts -- inner distance ends -- number of read pairs -- note the first 2 columns are left side half open interval + - inner distance starts + - inner distance ends + - number of read pairs + - note the first 2 columns are left side half open interval 3. output.inner_distance_plot.r: R script to generate histogram 4. output.inner_distance_plot.pdf: histogram plot -.. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/inner_distance.png +.. image:: http://rseqc.sourceforge.net/_images/inner_distance.png + :height: 600 px + :width: 600 px + :scale: 80 % + + +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ + diff -r b5d2f575ccb6 -r cc5eaa9376d8 junction_annotation.xml --- a/junction_annotation.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/junction_annotation.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,10 +1,11 @@ - + compares detected splice junctions to reference gene model - R + R + numpy rseqc - junction_annotation.py -i $input -o output -r $refgene + junction_annotation.py -i $input -o output -r $refgene #if $intron.hasIntron -m $intron.min_Intron @@ -22,22 +23,32 @@ - - - - + + + + + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 +junction_annotation.py +++++++++++++++++++++++ ------ +For a given alignment file (-i) in BAM or SAM format and a reference gene model (-r) in BED +format, this program will compare detected splice junctions to reference gene model. splicing +annotation is performed in two levels: splice event level and splice junction level. + +* splice event: An RNA read, especially long read, can be spliced 2 or more times, each time is called a splicing event; In this sense, 100 spliced reads can produce >= 100 splicing events. +* splice junction: multiple splicing events spanning the same intron can be consolidated into one splicing junction. -About RSeQC -+++++++++++ +All detected junctions can be grouped to 3 exclusive categories: -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. +1. Annotated: The junction is part of the gene model. Both splice sites, 5' splice site + (5'SS) and 3'splice site (3'SS) can be annotated by reference gene model. +2. complete_novel: Complete new junction. Neither of the two splice sites cannot be annotated by gene model +3. partial_novel: One of the splice site (5'SS or 3'SS) is new, while the other splice site is annotated (known) Inputs ++++++++++++++ @@ -56,15 +67,32 @@ ++++++++++++++ 1. output.junc.anno.junction.xls: -- chrom ID -- start position of junction (coordinate is 0 based) -- end position of junction (coordinate is 1 based) -- number of splice events supporting this junction -- 'annotated', 'complete_novel' or 'partial_novel'. + - chrom ID + - start position of junction (coordinate is 0 based) + - end position of junction (coordinate is 1 based) + - number of splice events supporting this junction + - 'annotated', 'complete_novel' or 'partial_novel'. 2. output.anno.junction_plot.r: R script to generate pie chart 3. output.splice_junction.pdf: plot of splice junctions 4. output.splice_events.pdf: plot of splice events -.. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/junction.png + +.. image:: http://rseqc.sourceforge.net/_images/junction.png + :height: 400 px + :width: 850 px + :scale: 80 % + +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ diff -r b5d2f575ccb6 -r cc5eaa9376d8 junction_saturation.xml --- a/junction_saturation.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/junction_saturation.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,10 +1,11 @@ - + detects splice junctions from each subset and compares them to reference gene model - R + R + numpy rseqc - junction_saturation.py -i $input -o output -r $refgene -m $intronSize -v $minSplice + junction_saturation.py -i $input -o output -r $refgene -m $intronSize -v $minSplice #if $percentiles.specifyPercentiles -l $percentiles.lowBound -u $percentiles.upBound -s $percentiles.percentileStep @@ -26,20 +27,26 @@ - - + + + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 +junction_saturation.py +++++++++++++++++++++++ ------ - -About RSeQC -+++++++++++ - -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. +It's very important to check if current sequencing depth is deep enough to perform +alternative splicing analyses. For a well annotated organism, the number of expressed genes +in particular tissue is almost fixed so the number of splice junctions is also fixed. The fixed +splice junctions can be predetermined from reference gene model. All (annotated) splice +junctions should be rediscovered from a saturated RNA-seq data, otherwise, downstream +alternative splicing analysis is problematic because low abundance splice junctions are +missing. This module checks for saturation by resampling 5%, 10%, 15%, ..., 95% of total +alignments from BAM or SAM file, and then detects splice junctions from each subset and +compares them to reference gene model. Inputs ++++++++++++++ @@ -65,10 +72,28 @@ 1. output.junctionSaturation_plot.r: R script to generate plot 2. output.junctionSaturation_plot.pdf -.. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/junction_saturation.png +.. image:: http://rseqc.sourceforge.net/_images/junction_saturation.png + :height: 600 px + :width: 600 px + :scale: 80 % In this example, current sequencing depth is almost saturated for "known junction" (red line) detection because the number of "known junction" reaches a plateau. In other words, nearly all "known junctions" (expressed in this particular tissue) have already been detected, and continue sequencing will not detect additional "known junction" and will only increase junction coverage (i.e. junction covered by more reads). While current sequencing depth is not saturated for novel junctions (green). +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ + + + - \ No newline at end of file + diff -r b5d2f575ccb6 -r cc5eaa9376d8 read_GC.xml --- a/read_GC.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/read_GC.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,31 +1,28 @@ - + determines GC% and read count - R + R + numpy rseqc - read_GC.py -i $input -o output + read_GC.py -i $input -o output - - - - + + + + + + + - .. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 +read_GC.py +++++++++++ ------ - -About RSeQC -+++++++++++ - -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. Inputs ++++++++++++++ @@ -40,7 +37,24 @@ 2. output.GC_plot.r: R script to generate pdf file. 3. output.GC_plot.pdf: graphical output generated from R script. -.. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/read_gc.png +.. image:: http://rseqc.sourceforge.net/_images/read_gc.png + :height: 600 px + :width: 600 px + :scale: 80 % + +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ + diff -r b5d2f575ccb6 -r cc5eaa9376d8 read_NVC.xml --- a/read_NVC.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/read_NVC.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,10 +1,11 @@ - + to check the nucleotide composition bias - R + R + numpy rseqc - read_NVC.py -i $input -o output + read_NVC.py -i $input -o output #if $nx -x @@ -15,21 +16,26 @@ - - - + + + + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 - ------ - -About RSeQC +read_NVC.py +++++++++++ -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. +This module is used to check the nucleotide composition bias. Due to random priming, certain +patterns are over represented at the beginning (5'end) of reads. This bias could be easily +examined by NVC (Nucleotide versus cycle) plot. NVC plot is generated by overlaying all +reads together, then calculating nucleotide composition for each position of read +(or each sequencing cycle). In ideal condition (genome is random and RNA-seq reads is +randomly sampled from genome), we expect A%=C%=G%=T%=25% at each position of reads. -The RSeQC package is licensed under the GNU GPL v3 license. +NOTE: this program expect a fixed read length Inputs ++++++++++++++ @@ -51,7 +57,24 @@ 3. output.NVC_plot.pdf: NVC plot. -.. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/NVC_plot.png +.. image:: http://rseqc.sourceforge.net/_images/NVC_plot.png + :height: 600 px + :width: 600 px + :scale: 80 % + +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ + diff -r b5d2f575ccb6 -r cc5eaa9376d8 read_distribution.xml --- a/read_distribution.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/read_distribution.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,9 +1,10 @@ - + calculates how mapped reads were distributed over genome feature + numpy rseqc - read_distribution.py -i $input -r $refgene > $output + read_distribution.py -i $input -r $refgene > $output @@ -12,17 +13,33 @@ + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 - ------ +read_distribution.py +++++++++++++++++++++ -About RSeQC -+++++++++++ +Provided a BAM/SAM file and reference gene model, this module will calculate how mapped +reads were distributed over genome feature (like CDS exon, 5'UTR exon, 3' UTR exon, Intron, +Intergenic regions). When genome features are overlapped (e.g. a region could be annotated +as both exon and intron by two different transcripts) , they are prioritize as: +CDS exons > UTR exons > Introns > Intergenic regions, for example, if a read was mapped to +both CDS exon and intron, it will be assigned to CDS exons. -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. +* "Total Reads": This does NOT include those QC fail,duplicate and non-primary hit reads +* "Total Tags": reads spliced once will be counted as 2 tags, reads spliced twice will be counted as 3 tags, etc. And because of this, "Total Tags" >= "Total Reads" +* "Total Assigned Tags": number of tags that can be unambiguously assigned the 10 groups (see below table). +* Tags assigned to "TSS_up_1kb" were also assigned to "TSS_up_5kb" and "TSS_up_10kb", tags assigned to "TSS_up_5kb" were also assigned to "TSS_up_10kb". Therefore, "Total Assigned Tags" = CDS_Exons + 5'UTR_Exons + 3'UTR_Exons + Introns + TSS_up_10kb + TES_down_10kb. +* When assign tags to genome features, each tag is represented by its middle point. -The RSeQC package is licensed under the GNU GPL v3 license. +RSeQC cannot assign those reads that: + +* hit to intergenic regions that beyond region starting from TSS upstream 10Kb to TES downstream 10Kb. +* hit to regions covered by both 5'UTR and 3' UTR. This is possible when two head-to-tail transcripts are overlapped in UTR regions. +* hit to regions covered by both TSS upstream 10Kb and TES downstream 10Kb. + Inputs ++++++++++++++ @@ -36,33 +53,36 @@ Sample Output ++++++++++++++ -:: - - Total Read: 44,826,454 :: - - Total Tags: 50,023,249 :: - - Total Assigned Tags: 36,057,402 :: +Output: - Group Total_bases Tag_count Tags/Kb - CDS_Exons 33302033 20022538 601.24 - 5'UTR_Exons 21717577 4414913 203.29 - 3'UTR_Exons 15347845 3641689 237.28 - Introns 1132597354 6312099 5.57 - TSS_up_1kb 17957047 215220 11.99 - TSS_up_5kb 81621382 392192 4.81 - TSS_up_10kb 149730983 769210 5.14 - TES_down_1kb 18298543 266157 14.55 - TES_down_5kb 78900674 730072 9.25 - TES_down_10kb 140361190 896953 6.39 +=============== ============ =========== =========== +Group Total_bases Tag_count Tags/Kb +=============== ============ =========== =========== +CDS_Exons 33302033 20002271 600.63 +5'UTR_Exons 21717577 4408991 203.01 +3'UTR_Exons 15347845 3643326 237.38 +Introns 1132597354 6325392 5.58 +TSS_up_1kb 17957047 215331 11.99 +TSS_up_5kb 81621382 392296 4.81 +TSS_up_10kb 149730983 769231 5.14 +TES_down_1kb 18298543 266161 14.55 +TES_down_5kb 78900674 729997 9.25 +TES_down_10kb 140361190 896882 6.39 +=============== ============ =========== =========== -Note: -- "Total Reads": This does NOT include those QC fail,duplicate and non-primary hit reads -- "Total Tags": reads spliced once will be counted as 2 tags, reads spliced twice will be counted as 3 tags, etc. And because of this, "Total Fragments" >= "Total Reads" -- "Total Assigned Tags": number of tags that can be unambiguously assigned the 10 groups (above table). -- Tags assigned to "TSS_up_1kb" were also assigned to "TSS_up_5kb" and "TSS_up_10kb", tags assigned to "TSS_up_5kb" were also assigned to "TSS_up_10kb". Therefore, "Total Assigned Tags" = CDS_Exons + 5'UTR_Exons + 3'UTR_Exons + Introns + TSS_up_10kb + TES_down_10kb. -- When assigning tags to genome features, each tag is represented by its middle point. -- RSeQC cannot assign those reads that: 1) hit to intergenic regions that beyond region starting from TSS upstream 10Kb to TES downstream 10Kb. 2) hit to regions covered by both 5'UTR and 3' UTR. This is possible when two head-to-tail transcripts are overlapped in UTR regions. 3) hit to regions covered by both TSS upstream 10Kb and TES downstream 10Kb. +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ + diff -r b5d2f575ccb6 -r cc5eaa9376d8 read_duplication.xml --- a/read_duplication.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/read_duplication.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,32 +1,34 @@ - + determines reads duplication rate with sequence-based and mapping-based strategies - R + R + numpy rseqc - read_duplication.py -i $input -o output -u $upLimit + read_duplication.py -i $input -o output -u $upLimit - - - - + + + + + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 +read_duplication.py ++++++++++++++++++++ ------ +Two strategies were used to determine reads duplication rate: -About RSeQC -+++++++++++ - -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. +* Sequence based: reads with exactly the same sequence content are regarded as duplicated reads. +* Mapping based: reads mapped to the same genomic location are regarded as duplicated reads. For splice reads, reads mapped to the same starting position and splice the same way are regarded as duplicated reads. Inputs ++++++++++++++ @@ -45,7 +47,24 @@ 3. output.DupRate_plot.r: R script to generate pdf file 4. output.DupRate_plot.pdf: graphical output generated from R script -.. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/duplicate.png +.. image:: http://rseqc.sourceforge.net/_images/duplicate.png + :height: 600 px + :width: 600 px + :scale: 80 % + +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ + diff -r b5d2f575ccb6 -r cc5eaa9376d8 read_quality.xml --- a/read_quality.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/read_quality.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,31 +1,37 @@ - + determines Phred quality score - R + R + numpy rseqc - read_quality.py -i $input -o output -r $reduce + read_quality.py -i $input -o output -r $reduce - - - + + + + + + + -.. image:: https://code.google.com/p/rseqc/logo?cct=1336721062 +read_quality.py ++++++++++++++++ ------ - -About RSeQC -+++++++++++ - -The RSeQC package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. “Basic modules” quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while “RNA-seq specific modules” investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. - -The RSeQC package is licensed under the GNU GPL v3 license. +According to SAM specification, if Q is the character to represent "base calling quality" +in SAM file, then Phred Quality Score = ord(Q) - 33. Here ord() is python function that +returns an integer representing the Unicode code point of the character when the argument +is a unicode object, for example, ord('a') returns 97. Phred quality score is widely used +to measure "reliability" of base-calling, for example, phred quality score of 20 means +there is 1/100 chance that the base-calling is wrong, phred quality score of 30 means there +is 1/1000 chance that the base-calling is wrong. In general: Phred quality score = -10xlog(10)P, +here P is probability that base-calling is wrong. Inputs ++++++++++++++ @@ -41,10 +47,31 @@ 1. output.qual.r 2. output.qual.boxplot.pdf -.. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/36mer.qual.plot.png + .. image:: http://rseqc.sourceforge.net/_images/36mer.qual.plot.png + :height: 600 px + :width: 600 px + :scale: 80 % 3. output.qual.heatmap.pdf -.. image:: http://dldcc-web.brc.bcm.edu/lilab/liguow/RSeQC/figure/36mer.qual.heatmap.png -use different color to represent nucleotide density ("blue"=low density,"orange"=median density,"red"=high density") + .. image:: http://rseqc.sourceforge.net/_images/36mer.qual.heatmap.png + :height: 600 px + :width: 600 px + :scale: 80 % + +Heatmap: use different color to represent nucleotide density ("blue"=low density,"orange"=median density,"red"=high density") + +----- + +About RSeQC ++++++++++++ + +The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation. + +The RSeQC package is licensed under the GNU GPL v3 license. + +.. image:: http://rseqc.sourceforge.net/_static/logo.png + +.. _RSeQC: http://rseqc.sourceforge.net/ + diff -r b5d2f575ccb6 -r cc5eaa9376d8 tool_dependencies.xml --- a/tool_dependencies.xml Thu Jul 11 12:33:27 2013 -0400 +++ b/tool_dependencies.xml Wed Oct 02 02:20:04 2013 -0400 @@ -1,14 +1,40 @@ - + - http://CRAN.R-project.org/src/base/R-2/R-2.15.1.tar.gz - ./configure --prefix=$INSTALL_DIR/lib - make - - bin/R - $INSTALL_DIR/lib/bin + http://cran.rstudio.com/src/base/R-2/R-2.11.0.tar.gz + + ./configure --enable-R-shlib \ + --with-readline=no \ + --with-x=no \ + --prefix=$INSTALL_DIR \ + --libdir=$INSTALL_DIR/lib \ + --disable-R-framework + + make && make install + + $INSTALL_DIR/lib/R + $INSTALL_DIR/lib/R/library + $INSTALL_DIR/lib/R/bin + + + + + R is a free software environment for statistical computing and graphics. + NOTE: See custom compilation options above + + + + + + + + + http://sourceforge.net/projects/rseqc/files/RSeQC-2.3.7.tar.gz + python setup.py install --root $INSTALL_DIR --prefix . --install-lib lib + + $INSTALL_DIR/lib $INSTALL_DIR/bin @@ -16,45 +42,9 @@ - You need a FORTRAN compiler or perhaps f2c in addition to a C compiler to build R. + RSeQC version 2.3.7, documentation available at http://dldcc-web.brc.bcm.edu/lilab/liguow/CGI/rseqc/_build/html/index.html#. + Requires gcc, python, numpy, and R - - - - http://sourceforge.net/projects/samtools/files/samtools/0.1.19/samtools-0.1.19.tar.bz2 - make - - samtools - $INSTALL_DIR/bin - - - bcftools/bcftools - $INSTALL_DIR/bin - - - $INSTALL_DIR/bin - - - - Both BCFTools and Samtools installed in this dependency.Compiling SAMtools requires the ncurses and zlib development libraries. - - - - - http://sourceforge.net/projects/rseqc/files/RSeQC-2.3.7.tar.gz - python setup.py install --root $INSTALL_DIR/lib/rseqc - - $INSTALL_DIR/lib/rseqc/usr/local/lib/python2.7/site-packages - - - $INSTALL_DIR/lib/rseqc/usr/local/bin - - - - - RSeQC version 2.3.7, documentation available at http://dldcc-web.brc.bcm.edu/lilab/liguow/CGI/rseqc/_build/html/index.html#. - - - +