#/data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl --help #-e|e_cnt - error analysis max error count allowed - optional (default 3) # - This is the maximum number of errors alloweallowed - optional (default 3) # - This is the maximum number of errors allowed per read. # If the number is greater then the read length it is equivalent to # having the error analysis turned off. For example if this is set to 5, # then if 5 such errors are found, the read is kept, but if 6 are found # then the read does not pass the analysis. #-d|e_sc - error analysis max QV score - optional (default 10) # - this is the maximum score for error analysis. This must be a number # between 0-34 since there are currently no scores above 34. # So if the score is 10 the an error is tagged if it has a QV value of 10 # or less. #-p|p_cnt - Polyclonal analysis count required - optional (default 1) # - This is the count required for the polyclonal analysis. # This number must be between [0-10]. Zero is equivalent to having the # polyclonal analysis turned off. For example if this is set to 5, # then at least 5 of the first 10 positions must exceed the passed # polyclonal QV score. #-q|p_qv - Polyclonal analysis min QV score - optional (default 25) # - This is the minimum score for the polyclonal analysis. # This must be a number between 0-34 since there are currently # no scores above 34. #-u|tr_len - desired length of read after truncation - optional # - This is the length of the sequence desired, any color calls after this # length are removed. This option must be filled in if truncation is turned on # and be an integer greater than 0. #-a|qv_analysis - turn on/off analysis of quality values - optional (default off) # - Analysis of the quality values for all of the inputted reads and # the passing reads. Analysis returns a file with a matrix of a count # of scores by position. # [on,yes,y,off,no,n] #example: SOLiD_preprocess_filter_v2_MR1.pl -i mp -f a_F3.csfasta -g a_F3_QV.qual -r b_R3.csfasta # -s b_R3_QV.qual -p 3 -q 22 -e 10 -d 9 -v off -o test_test #9 highqual start /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -p 9 -o 0hrep1filt7 -f 0hrep1/ugc_604_1_F3.csfasta -g 0hrep1/ugc_604_1_F3.QV.qual cat 0hrep1filt7_T_F3.csfasta | /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/collapseFA.pl > 0hrep1filt7_T_F3.csfasta.coll ./SeqTrimMap4Paralyzer -m 10 -l 18 -v 2 -p 10 -i -o 0hrep1F-4p10 0hrep1filt7_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl 0hrep1F-4p10.bowtie |samtools view -bS -t /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa.fai - | samtools sort -o - - > 0hrep1F-4p10.bam;samtools index 0hrep1F-4p10.bam /data/results/tools/align/rnaseqmut/rnaseqmut-master/bin/rnaseqmut.linux.x64 -r /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa -m 0 0hrep1F-4p10.bam | awk -f /data/results/tools/align/rnaseqmut/count-conversions1.awk > 0hrep1F-4p10.conversion.stats AtoC 517998 9.74356 GtoA 494720 9.3057 CtoA 393703 7.40557 TtoG 390794 7.35085 GtoC 288313 5.42318 AtoT 363640 6.84008 AtoG 408175 7.67779 GtoT 244998 4.60842 CtoT 406600 7.64816 CtoG 443212 8.33683 TtoA 669083 12.5855 TtoC 695075 13.0744 #8 highqual start /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -p 8 -o 0hrep1filt6 -f 0hrep1/ugc_604_1_F3.csfasta -g 0hrep1/ugc_604_1_F3.QV.qual cat 0hrep1filt6_T_F3.csfasta | /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/collapseFA.pl > 0hrep1filt6_T_F3.csfasta.coll ./SeqTrimMap4Paralyzer -m 10 -l 18 -v 2 -p 10 -i -o 0hrep1F-4p9 0hrep1filt6_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl 0hrep1F-4p9.bowtie |samtools view -bS -t /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa.fai - | samtools sort -o - - > 0hrep1F-4p9.bam;samtools index !$ /data/results/tools/align/rnaseqmut/rnaseqmut-master/bin/rnaseqmut.linux.x64 -r /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa -m 0 0hrep1F-4p9.bam | awk -f /data/results/tools/align/rnaseqmut/count-conversions1.awk > 0hrep1F-4p9.conversion.stats AtoC 1149850 7.5904 GtoA 1240966 8.19188 TtoG 1608036 10.615 CtoA 1132298 7.47454 GtoC 1120880 7.39917 AtoT 1245940 8.22471 AtoG 1291815 8.52755 GtoT 548708 3.62214 CtoT 1344343 8.87429 CtoG 1059029 6.99088 TtoA 1893276 12.4979 TtoC 1513591 9.99154 #5 highqual start, max. 1err /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -p 5 -e 1 -o 0hrep1filt4 -f 0hrep1/ugc_604_1_F3.csfasta -g 0hrep1/ugc_604_1_F3.QV.qual cat 0hrep1filt4_T_F3.csfasta | /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/collapseFA.pl > 0hrep1filt4_T_F3.csfasta.coll ./SeqTrimMap4Paralyzer -m 10 -l 18 -v 2 -p 10 -i -o 0hrep1F-4p7 0hrep1filt4_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl 0hrep1F-4p7.bowtie |samtools view -bS -t /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa.fai - | samtools sort -o - - > 0hrep1F-4p7.bam;samtools index !$ /data/results/tools/align/rnaseqmut/rnaseqmut-master/bin/rnaseqmut.linux.x64 -r /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa -m 0 0hrep1F-4p7.bam | awk -f /data/results/tools/align/rnaseqmut/count-conversions1.awk > 0hrep1F-4p7.conversion.stats AtoC 4470251 8.30193 GtoA 4059403 7.53893 TtoG 4819767 8.95104 CtoA 4181503 7.76568 GtoC 3606336 6.69751 AtoT 5108293 9.48687 AtoG 4992818 9.27242 GtoT 2463548 4.57518 CtoT 4260106 7.91166 CtoG 3603078 6.69146 TtoA 6238741 11.5863 TtoC 6042057 11.221 #10 highqual start, max. 1err /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -p 10 -e 1 -o 0hrep1filt3 -f 0hrep1/ugc_604_1_F3.csfasta -g 0hrep1/ugc_604_1_F3.QV.qual cat 0hrep1filt3_T_F3.csfasta | /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/collapseFA.pl > 0hrep1filt3_T_F3.csfasta.coll ./SeqTrimMap4Paralyzer -m 10 -l 18 -v 2 -p 10 -i -o 0hrep1F-4p5 0hrep1filt3_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl 0hrep1F-4p5.bowtie |samtools view -bS -t /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa.fai - | samtools sort -o - - > 0hrep1F-4p5.bam;samtools index !$ /data/results/tools/align/rnaseqmut/rnaseqmut-master/bin/rnaseqmut.linux.x64 -r /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa -m 0 0hrep1F-4p5.bam | awk -f /data/results/tools/align/rnaseqmut/count-conversions1.awk > 0hrep1F-4p5.conversion.stats AtoC 56196 6.07166 GtoA 50695 5.47731 TtoG 109458 11.8263 CtoA 96148 10.3882 GtoC 66328 7.16636 AtoG 81383 8.79297 AtoT 78226 8.45188 GtoT 42861 4.63089 CtoG 73822 7.97605 CtoT 35355 3.81991 TtoA 109382 11.8181 TtoC 125692 13.5803 #10 highqual start, (default max. 3err) /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -p 10 -o 0hrep1filt2 -f 0hrep1/ugc_604_1_F3.csfasta -g 0hrep1/ugc_604_1_F3.QV.qual cat 0hrep1filt2_T_F3.csfasta | /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/collapseFA.pl > 0hrep1filt2_T_F3.csfasta.coll ./SeqTrimMap4Paralyzer -m 10 -l 18 -v 2 -p 10 -i -o 0hrep1F-4p4 0hrep1filt2_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl 0hrep1F-4p4.bowtie |samtools view -bS -t /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa.fai - | samtools sort -o - - > 0hrep1F-4p4.bam samtools index 0hrep1F-4p4.bam ( bam=readSortedBam("0hrep1F-4p4.bam") countTable <- getAllSub( bam, minCov = 10 ) png("substPlot-0hrep1F-4p4.png",width=1024,height=1200,pointsize = 22) plotSubstitutions( countTable, highlight = "TC" ) # TC 3.06% (without -p10: 2.7%) dev.off() ) /data/results/tools/align/rnaseqmut/rnaseqmut-master/bin/rnaseqmut.linux.x64 -r /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa -m 0 0hrep1F-4p4.bam | awk -f /data/results/tools/align/rnaseqmut/count-conversions1.awk > 0hrep1F-4p4.conversion.stats AtoC 79338 8.37926 GtoA 51295 5.41751 TtoG 87165 9.2059 CtoA 31930 3.37228 GtoC 68090 7.1913 AtoG 79917 8.44041 AtoT 41927 4.42811 GtoT 36403 3.84469 CtoG 69022 7.28974 CtoT 103401 10.9207 TtoA 151570 16.008 TtoC 146780 15.5021 (#1mm ./SeqTrimMap4Paralyzer -m 10 -l 18 -v 1 -p 10 -i -o 0hrep1F-4p8 0hrep1filt2_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl 0hrep1F-4p8.bowtie |samtools view -bS -t /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa.fai - | samtools sort -o - - > 0hrep1F-4p8.bam samtools index 0hrep1F-4p8.bam /data/results/tools/align/rnaseqmut/rnaseqmut-master/bin/rnaseqmut.linux.x64 -r /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa -m 0 0hrep1F-4p8.bam | awk -f /data/results/tools/align/rnaseqmut/count-conversions1.awk > 0hrep1F-4p8.conversion.stats # not mm's ! ) /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -p 5 -a on -o 0hrep1filt5 -f 0hrep1/ugc_604_1_F3.csfasta -g 0hrep1/ugc_604_1_F3.QV.qual /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -p 10 -o 0hrep1filt2 -f 0hrep1/ugc_604_1_F3.csfasta -g 0hrep1/ugc_604_1_F3.QV.qual # 3mm ./SeqTrimMap4Paralyzer -m 10 -l 18 -v 3 -p 10 -i -o 0hrep1F-4p6 0hrep1filt2_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl 0hrep1F-4p6.bowtie |samtools view -bS -t /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa.fai - | samtools sort -o - - > 0hrep1F-4p6.bam samtools index !$ /data/results/tools/align/rnaseqmut/rnaseqmut-master/bin/rnaseqmut.linux.x64 -r /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa -m 0 0hrep1F-4p6.bam | awk -f /data/results/tools/align/rnaseqmut/count-conversions1.awk > 0hrep1F-4p6.conversion.stats AtoC 159044 11.4624 GtoA 79407 5.72293 CtoA 75531 5.44358 TtoG 91401 6.58735 GtoC 143173 10.3186 AtoT 135697 9.77979 AtoG 153727 11.0792 GtoT 49017 3.5327 CtoT 55773 4.01961 CtoG 87409 6.29964 TtoA 224802 16.2017 TtoC 132543 9.55248 # get TC stats for old TIA alignment: reczko@max:/data/images/proton/DKlab/mr/parclip/raw$ /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl /data/images/proton/DKlab/mr/parclip/TIA_PARCLIPraw/csfasta/ugc_604_10_Genome.bowtie |samtools view -bS -t /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa.fai - | samtools sort -o - - > TIA_ugc_604_10_Genome_old.bam samtools index !$ bam=readSortedBam("TIA_ugc_604_10_Genome_old.bam" +) countTable <- getAllSub( bam, minCov = 10 ) png("substPlot-TIA_ugc_604_10_Genome_old.png",width=1024,height=1200,pointsize = 22) plotSubstitutions( countTable, highlight = "TC" ) dev.off() /data/results/tools/align/rnaseqmut/rnaseqmut-master/bin/rnaseqmut.linux.x64 -r /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa -m 0 TIA_ugc_604_10_Genome_old.bam | awk -f /data/results/tools/align/rnaseqmut/count-conversions1.awk > TIA_ugc_604_10_Genome_old.bam.conversion.stats AtoC 45591433 8.66212 GtoA 34800405 6.61188 CtoA 31338114 5.95407 TtoG 57667920 10.9566 GtoC 32066772 6.09251 AtoG 54808564 10.4133 AtoT 55939168 10.6281 GtoT 30513152 5.79733 CtoT 38702321 7.35323 CtoG 33019686 6.27356 TtoA 52301639 9.93702 TtoC 59581961 11.3202 /data/results/tools/align/rnaseqmut/rnaseqmut-master/bin/rnaseqmut.linux.x64 -r /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa -m 0 0hrep1F-4p3.sam.bam | awk -f /data/results/tools/align/rnaseqmut/count-conversions1.awk > 0hrep1F-4p3.conversion.stats AtoC 6071730 8.08974 GtoA 5410862 7.20922 TtoG 7049780 9.39285 CtoA 6334372 8.43967 GtoC 5262681 7.01179 AtoT 6778973 9.03204 AtoG 7536796 10.0417 GtoT 3268056 4.35423 CtoT 5592896 7.45176 CtoG 4956693 6.60411 TtoA 8369983 11.1518 TtoC 8421894 11.221 /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -p 10 -o IGGfilt3 -f IGG/ugc_604_12_F3.csfasta -g IGG/ugc_604_12_F3.QV.qual /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -p 10 -o 0hrep1filt2 -f 0hrep1/ugc_604_1_F3.csfasta -g 0hrep1/ugc_604_1_F3.QV.qual cd /data/images/proton/DKlab/mr/parclip/raw #errors (encoded by ".") are counted only in the first 20 colors /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -o IGGfilt7 -p 9 -f IGG/ugc_604_12_F3.csfasta -g IGG/ugc_604_12_F3.QV.qual #/data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -o 0hrep1filt7 -p 9 -f 0hrep1/ugc_604_1_F3.csfasta -g 0hrep1/ugc_604_1_F3.QV.qual /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -o 0hrep2filt7 -p 9 -f 0hrep2/ugc_604_4_F3.csfasta -g 0hrep2/ugc_604_4_F3.QV.qual /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -o 0hrep3filt7 -p 9 -f 0hrep3/ugc_604_7_F3.csfasta -g 0hrep3/ugc_604_7_F3.QV.qual /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -o 2hrep1filt7 -p 9 -f 2hrep1/ugc_604_2_F3.csfasta -g 2hrep1/ugc_604_2_F3.QV.qual /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -o 2hrep2filt7 -p 9 -f 2hrep2/ugc_604_5_F3.csfasta -g 2hrep2/ugc_604_5_F3.QV.qual /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -o 2hrep3filt7 -p 9 -f 2hrep3/ugc_604_8_F3.csfasta -g 2hrep3/ugc_604_8_F3.QV.qual /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -o 6hrep1filt7 -p 9 -f 6hrep1/ugc_604_3_F3.csfasta -g 6hrep1/ugc_604_3_F3.QV.qual /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -o 6hrep2filt7 -p 9 -f 6hrep2/ugc_604_6_F3.csfasta -g 6hrep2/ugc_604_6_F3.QV.qual /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -o 6hrep3filt7 -p 9 -f 6hrep3/ugc_604_9_F3.csfasta -g 6hrep3/ugc_604_9_F3.QV.qual /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -o IL4filt7 -p 9 -f IL4/ugc_604_11_F3.csfasta -g IL4/ugc_604_11_F3.QV.qual /data/results/tools/solid/qc-filter/SOLiD_preprocess_filter_v2_MR1.pl -a on -o IFNfilt7 -p 9 -f IFN/ugc_604_10_F3.csfasta -g IFN/ugc_604_10_F3.QV.qual for i in *filt7_T_*csfasta do echo $i cat $i | /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/collapseFA.pl > $i".coll" done #cat 0hrep1filt2_T_F3.csfasta | /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/collapseFA.pl > test.fasta ./SeqTrimMap4Paralyzer -m 10 -l 18 -v 2 -p 10 -i -o 0hrep1F-4p3 0hrep1filt7_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c ./SeqTrimMap4Paralyzer -m 10 -l 18 -v 2 -p 10 -i -o 0hrep2F-4p3 0hrep2filt7_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c ./SeqTrimMap4Paralyzer -m 10 -l 18 -v 2 -p 10 -i -o 0hrep3F-4p3 0hrep3filt7_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c ./SeqTrimMap4Paralyzer -m 10 -l 18 -v 2 -p 10 -i -o 2hrep1F-4p3 2hrep1filt7_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c ./SeqTrimMap4Paralyzer -m 10 -l 18 -v 2 -p 10 -i -o 2hrep2F-4p3 2hrep2filt7_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c ./SeqTrimMap4Paralyzer -m 10 -l 18 -v 2 -p 10 -i -o 2hrep3F-4p3 2hrep3filt7_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c ./SeqTrimMap4Paralyzer2 -m 10 -l 18 -v 2 -p 10 -i -o IGGF-4p10 IGGfilt7_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c ./SeqTrimMap4Paralyzer2 -m 10 -l 18 -v 2 -p 10 -i -o IL4F-4p10 IL4filt7_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c ./SeqTrimMap4Paralyzer2 -m 10 -l 18 -v 2 -p 10 -i -o IFNF-4p10 IFNfilt7_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c ./SeqTrimMap4Paralyzer2 -m 10 -l 18 -v 2 -p 10 -i -o 6hrep1F-4p10 6hrep1filt7_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c ./SeqTrimMap4Paralyzer2 -m 10 -l 18 -v 2 -p 10 -i -o 6hrep2F-4p10 6hrep2filt7_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c ./SeqTrimMap4Paralyzer2 -m 10 -l 18 -v 2 -p 10 -i -o 6hrep3F-4p10 6hrep3filt7_T_F3.csfasta.coll /data/results/reference/mmu/mm9/bowtie1/mm9c /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl /data/images/proton/DKlab/mr/parclip/raw/0hrep1F-4p10.bowtie > 0hrep1F-4p10.sam /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl /data/images/proton/DKlab/mr/parclip/raw/0hrep2F-4p10.bowtie > 0hrep2F-4p10.sam /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl /data/images/proton/DKlab/mr/parclip/raw/0hrep3F-4p10.bowtie > 0hrep3F-4p10.sam /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl /data/images/proton/DKlab/mr/parclip/raw/2hrep1F-4p10.bowtie > 2hrep1F-4p10.sam /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl /data/images/proton/DKlab/mr/parclip/raw/2hrep2F-4p10.bowtie > 2hrep2F-4p10.sam /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl /data/images/proton/DKlab/mr/parclip/raw/2hrep3F-4p10.bowtie > 2hrep3F-4p10.sam /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl /data/images/proton/DKlab/mr/parclip/raw/6hrep1F-4p10.bowtie > 6hrep1F-4p10.sam /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl /data/images/proton/DKlab/mr/parclip/raw/6hrep2F-4p10.bowtie > 6hrep2F-4p10.sam /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl /data/images/proton/DKlab/mr/parclip/raw/6hrep3F-4p10.bowtie > 6hrep3F-4p10.sam /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl /data/images/proton/DKlab/mr/parclip/raw/IGGF-4p10.bowtie > IGGF-4p10.sam /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl /data/images/proton/DKlab/mr/parclip/raw/IFNF-4p10.bowtie > IFNF-4p10.sam /data/results/tools/samtools/samtools-1.3/misc/bowtie2sam.pl /data/images/proton/DKlab/mr/parclip/raw/IL4F-4p10.bowtie > IL4F-4p10.sam #samtools view -bhS 0hF-4p_PARalyzer_Utilized.sam | samtools sort -o - - > test.bam #time ./PARalyzer 50G sample.ini-IGG-b #I identified a total of 4237592 reads mapping to 1072388 Unique genomic coordinates #Making up 58618 groups #Consisting of 21306 clusters #@ 1rep IGG, filtered reads, PAPpipe settings cd /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_5 ./PARalyzer 5G /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_5/sample.ini-IGGF-4p3-HAFNER_APPROACH.ini ./PARalyzer 5G /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_5/sample.ini-IFNF-4p3-HAFNER_APPROACH.ini ./PARalyzer 5G /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_5/sample.ini-IL4F-4p3-HAFNER_APPROACH.ini ./PARalyzer 9G /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_5/sample.ini-0hF-4p3-HAFNER_APPROACH.ini ./PARalyzer 9G /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_5/sample.ini-2hF-4p3-HAFNER_APPROACH.ini ./PARalyzer 9G /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_5/sample.ini-6hF-4p3-HAFNER_APPROACH.ini #mod HERE ./prepParPipe1.sh 0hF-4p3-HAFNER_APPROACH ./prepParPipe1.sh IGGF-4p3-HAFNER_APPROACH # cp IGGF-4p2_PARalyzer_Utilized.sam test.sam # samtools view -bS -t /data/results/reference/mmu/Mus_musculus/UCSC/mm9/Sequence/WholeGenomeFasta/genome.fa.fai test.sam | samtools sort -o - - > test.bam # samtools index test.bam # Stage readAttributes #/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/readAttributesTC_MR1.pl test.sam > test.attr # Stage annotateReads #mod HERE #cp clusters-IGGF-4p2.txt test.clusters #cp groups-IGGF-4p2.txt test.groups #cp test.attr test.clusters test.groups /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/test3 #cd /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/test3 #./anno-mm9.sh #cp test.clusterbed test.readcsv test.groupbed /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_5/ # Stage read_bed /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/reads2bed.py test.readcsv > test.readbed # Stage annotateClusters # Stage addInfo intersectBed -a test.readbed -b test.clusterbed -wao -s | awk -F " " 'BEGIN{OFS=",";} { print $5,$7,$8,$9,$11,$12}' | sed '/,\-1/d' | /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/editClustersTC.pl .6 > test.clusters.csv # Stage visbed cat test.clusters.csv | /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/visclusterbed.py > test.clusters.bed # Stage geneLvl perl /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/geneLevel.pl test.clusters.csv /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/files/gencode.v11.annotation.gtf > test.gene_cl.csv # Stage annotateGroups #/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/annotate.pl -g /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/files/gencode.v11.annotation.gtf -p /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/annotationRank.txt -r /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/files/mm9_rmsk.bed.gz -s /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/files/mm9_rmsk_info -strict -oi test.groups | /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/PARclusters2bed.py > test.groupbed # Stage addInfoGroups intersectBed -a test.readbed -b test.groupbed -wao -s | awk -F " " 'BEGIN{OFS=",";} { print $5,$7,$8,$9,$11,$12}' | sed '/,\-1/d' | /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/editClustersTC.pl > test.groups.csv # Stage geneLvlGroups perl /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/geneLevel.pl test.groups.csv /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/files/gencode.v11.annotation.gtf > test.gene_gr.csv # Stage statsTable /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/extractDataTC_MR1.pl test > test.clusters.txt # Stage spatialPerl perl /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/Spatial.pl -g /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/files/gencode.v11.annotation.gtf -a test -strict -t /data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/files/isoforms.fpkm_tracking # Stage spatialR unset TMP; unset TEMP; TEMPDIR="/tmp/47609700210084528-0" setsid Rscript - <<'!' yn<-'n' fn<-'test' resolution<-3 install.packages('/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/colorRamps_2.3.tar.gz', lib='/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/') install.packages('/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/schoolmath_0.4.tar.gz', lib='/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/') install.packages('/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/gtools_3.4.1.tar.gz', lib='/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/') install.packages('/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/ellipse_0.3-8.tar.gz', lib='/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/') install.packages('/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/RColorBrewer_1.1-2.tar.gz', lib='/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/') install.packages('/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/LSD_2.5.tar.gz', lib='/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/') library(colorRamps, lib.loc='/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/') library(schoolmath, lib.loc='/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/') library(gtools, lib.loc='/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/') library(ellipse, lib.loc='/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/') library(RColorBrewer, lib.loc='/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/') library(LSD, lib.loc='/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/') library(parallel) source('/data/images/proton/DKlab/mr/parclip/parpipe/PARpipe-master/scripts/Spatial.R') ! awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_5/clusters2bed.awk clusters-6hF-4p10-HAFNER_APPROACH.txt > clusters-6hF-4p10-HAFNER_APPROACH.bed awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_5/clusters2bed.awk clusters-IGGF-4p10-HAFNER_APPROACH.txt > clusters-IGGF-4p10-HAFNER_APPROACH.bed reczko@max:/data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_5$ for i in groups-*-4p3-HAFNER_APPROACH.txt do awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_5/clusters2bed.awk $i > $i.bed done for i in groups-*-4p3-HAFNER_APPROACH.txt.bed do bedtools intersect -a $i -b groups-IGGF-4p3-HAFNER_APPROACH.txt.bed -v > $i.noIGG.bed wc !$ done #mapkap1 chr2:34,287,523-34,480,470 groups-6hF-4p10-HAFNER_APPROACH.bed *chr2 34303627 34303649 G21172 0 + chr2 34365162 34365184 G21173 0 + !chr2 34402254 34402272 G21174 0 + *chr2 34403898 34403919 G21175 0 + groups-2hF-4p10-HAFNER_APPROACH.txt *chr2,+,34303625,34303647,G23737,CACTGCCACTGAGCCTTGGCCAC,39,0,0 chr2,+,34350666,34350687,G23738,CCAGGCACACTACTAGGCATGG,6,0,0 chr2,+,34365162,34365183,G23739,TTGGATGGCTACGTGTACTTGG,7,0,0 !chr2,+,34402252,34402272,G23740,GCTGCAATATGACAGCAGAGC,16,0,0 *chr2,+,34403898,34403917,G23741,GCTATTCACATTATACAGCA,31,0,0 groups-0hF-4p10-HAFNER_APPROACH.txt *chr2,+,34303625,34303649,G20221,CACTGCCACTGAGCCTTGGCCACTG,58,0,0 !chr2,+,34402253,34402272,G20222,CTGCAATATGACAGCAGAGC,5,0,0 *chr2,+,34403898,34403918,G20223,GCTATTCACATTATACAGCAT,16,0,0 chr2,+,34464385,34464407,G20224,TCAGAACCAATGCCAGCCAAAAG,8,0,0 chr2,+,34562653,34562671,G20225,GGGCATGACAGCAGGGCAA,11,0,0 chr2,+,34681311,34681329,G20226,AGCCTTGGGGCATCAATGT,27,0,0 groups-0hF-4p3-HAFNER_APPROACH.txt.bed.noIGG.bed chr2 34292499 34292521 G185927 nr 15 nc 0 + chr2 34299023 34299046 G185928 nr 8 nc 0 + chr2 34313489 34313508 G185930 nr 5 nc 0 + chr2 34337027 34337049 G185931 nr 18 nc 0 + chr2 34350666 34350687 G185932 nr 6 nc 0 + chr2 34354381 34354401 G185933 nr 5 nc 0 + chr2 34364372 34364390 G185934 nr 5 nc 0 + chr2 34373531 34373551 G185936 nr 8 nc 0 + chr2 34397462 34397481 G185937 nr 7 nc 0 + chr2 34401621 34401642 G185938 nr 16 nc 0 + !chr2 34402253 34402275 G185939 nr 6 nc 0 + chr2 34415520 34415541 G185941 nr 5 nc 0 + chr2 34431608 34431627 G185942 nr 7 nc 0 + chr2 34438845 34438863 G185943 nr 5 nc 0 + chr2 34440070 34440090 G185944 nr 8 nc 0 + chr2 34451154 34451178 G185945 nr 5 nc 0 + chr2 34452604 34452624 G185946 nr 6 nc 0 + chr2 34456041 34456064 G185947 nr 5 nc 0 + chr2 34460214 34460239 G185948 nr 6 nc 0 + chr2 34464385 34464407 G185949 nr 40 nc 0 + groups-IFNF-4p10-HAFNER_APPROACH.txt *chr2,+,34303627,34303646,G6995,CTGCCACTGAGCCTTGGCCA,12,0,0 !chr2,+,34402252,34402272,G6996,GCTGCAATATGACAGCAGAGC,237,0,0 *chr2,+,34403898,34403918,G6997,GCTATTCACATTATACAGCAT,14,0,0 groups-IL4F-4p10-HAFNER_APPROACH.txt *chr2,+,34303625,34303649,G10439,CACTGCCACTGAGCCTTGGCCACTG,23,0,0 *chr2,+,34403898,34403918,G10440,GCTATTCACATTATACAGCAT,19,0,0 groups-IL4F-4p3-HAFNER_APPROACH.txt chr2,+,34292499,34292518,G95634,CTGCCTTGGCATGGCAGGTG,5,0,0 *chr2,+,34303625,34303651,G95635,CACTGCCACTGAGCCTTGGCCACTGTT,39,0,0 chr2,+,34308820,34308841,G95636,TTTGCAAAATATGCTACTATGC,19,0,0 chr2,+,34308916,34308936,G95637,AGTATTAGTGTCAGATAAAGA,7,0,0 chr2,+,34365162,34365183,G95638,TTGGATGGCTACGTGTACTTGG,18,0,0 chr2,+,34389208,34389231,G95639,TCTCCAAAATATTCACCGGCATTT,6,0,0 *chr2,+,34403898,34403919,G95640,GCTATTCACATTATACAGCATT,406,0,0 chr2,+,34414736,34414754,G95641,GTAGCTTGGAATTTCCTTA,5,0,0 chr2,+,34431606,34431627,G95642,GGTAAGTTTCCTAAAGGTTAAT,5,0,0 chr2,+,34457603,34457622,G95643,TGATCTTGAGCGGCCTTAAT,6,0,0 chr2,+,34479832,34479853,G95644,CTCCTCATAGCAAGTATGATAT,5,0,0 groups-IGGF-4p10-HAFNER_APPROACH.txt *chr2,+,34303625,34303646,G4981,CACTGCCACTGAGCCTTGGCCA,30,0,0 *chr2,+,34403898,34403916,G4982,GCTATTCACATTATACAGC,9,0,0 for i in groups-*-4p3-HAFNER_APPROACH.txt do awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_5/clusters2bed.awk $i > $i.bed done for i in groups-*-4p3-HAFNER_APPROACH.txt.bed do bedtools intersect -a $i -b groups-IGGF-4p3-HAFNER_APPROACH.txt.bed -v > $i.noIGG.bed wc !$ done 321321 1927926 11425398 groups-0hF-4p3-HAFNER_APPROACH.txt.bed.noIGG.bed 271739 1630434 9651623 groups-2hF-4p3-HAFNER_APPROACH.txt.bed.noIGG.bed 329958 1979748 11738606 groups-6hF-4p3-HAFNER_APPROACH.txt.bed.noIGG.bed 54661 327966 1897915 groups-IFNF-4p3-HAFNER_APPROACH.txt.bed.noIGG.bed 0 0 0 groups-IGGF-4p3-HAFNER_APPROACH.txt.bed.noIGG.bed 151519 909114 5344514 groups-IL4F-4p3-HAFNER_APPROACH.txt.bed.noIGG.bed bedtools intersect -a clusters-6hF-4p10-HAFNER_APPROACH.bed -b clusters-IGGF-4p10-HAFNER_APPROACH.bed -wo > foo #not in IGG bedtools intersect -a clusters-6hF-4p10-HAFNER_APPROACH.bed -b clusters-IGGF-4p10-HAFNER_APPROACH.bed -v |wc