cd /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b # step 1+2 of README-paralyze3.txt # paralyzer to bed for i in sh-clusters*txt2.csv do echo $i awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/pa2bed-gt5tc.awk $i > $i.bed.gt5tc done #remove IGG regions for i in sh-clusters-*txt2.csv.bed.gt5tc do wc $i bedtools intersect -a $i -b sh-clusters-IGG.txt2.csv.bed.gt5tc -v -s |sort -k1,1 -k2,2n > $i.noIGG wc !$ done > 193393 1160358 23474326 sh-clusters-0hrep1.txt2.csv.bed.gt5tc 173469 1040814 20985272 sh-clusters-0hrep1.txt2.csv.bed.gt5tc.noIGG 106635 639810 12775290 sh-clusters-0hrep2.txt2.csv.bed.gt5tc 96126 576756 11487443 sh-clusters-0hrep2.txt2.csv.bed.gt5tc.noIGG 290852 1745112 35703883 sh-clusters-0hrep3.txt2.csv.bed.gt5tc 273664 1641984 33503282 sh-clusters-0hrep3.txt2.csv.bed.gt5tc.noIGG 155713 934278 18881199 sh-clusters-2hrep1.txt2.csv.bed.gt5tc 132245 793470 15945601 sh-clusters-2hrep1.txt2.csv.bed.gt5tc.noIGG 167355 1004130 20493466 sh-clusters-2hrep2.txt2.csv.bed.gt5tc 152928 917568 18677367 sh-clusters-2hrep2.txt2.csv.bed.gt5tc.noIGG 178851 1073106 21604876 sh-clusters-2hrep3.txt2.csv.bed.gt5tc 164050 984300 19763391 sh-clusters-2hrep3.txt2.csv.bed.gt5tc.noIGG 271231 1627386 32518550 sh-clusters-6hrep1.txt2.csv.bed.gt5tc 249444 1496664 29793943 sh-clusters-6hrep1.txt2.csv.bed.gt5tc.noIGG 238510 1431060 29298370 sh-clusters-6hrep2.txt2.csv.bed.gt5tc 218957 1313742 26812051 sh-clusters-6hrep2.txt2.csv.bed.gt5tc.noIGG 114574 687444 13792229 sh-clusters-6hrep3.txt2.csv.bed.gt5tc 104169 625014 12507059 sh-clusters-6hrep3.txt2.csv.bed.gt5tc.noIGG 136129 816774 16381836 sh-clusters-IFN.txt2.csv.bed.gt5tc 121249 727494 14547710 sh-clusters-IFN.txt2.csv.bed.gt5tc.noIGG 96009 576054 11328986 sh-clusters-IGG.txt2.csv.bed.gt5tc 0 0 0 sh-clusters-IGG.txt2.csv.bed.gt5tc.noIGG 265482 1592892 32438462 sh-clusters-IL4.txt2.csv.bed.gt5tc 233947 1403682 28439506 sh-clusters-IL4.txt2.csv.bed.gt5tc.noIGG rm sh-clusters-IGG.txt2.csv.bed.gt5tc.noIGG # strand stats for i in sh-clusters-*txt2.csv.bed.gt5tc.noIGG do echo $i awk -f ../strandStats1.awk $i done awk -f ../strandStats1.awk sh-clusters-IGG.txt2.csv.bed.gt5tc sh-clusters-0hrep1.txt2.csv.bed.gt5tc.noIGG nclusters 173469 plus_strand 90630 52.2456 % minus_strand 82839 47.7544 % sh-clusters-0hrep2.txt2.csv.bed.gt5tc.noIGG nclusters 96126 plus_strand 51226 53.2905 % minus_strand 44900 46.7095 % sh-clusters-0hrep3.txt2.csv.bed.gt5tc.noIGG nclusters 273664 plus_strand 145758 53.2617 % minus_strand 127906 46.7383 % sh-clusters-2hrep1.txt2.csv.bed.gt5tc.noIGG nclusters 132245 plus_strand 71326 53.9347 % minus_strand 60919 46.0653 % sh-clusters-2hrep2.txt2.csv.bed.gt5tc.noIGG nclusters 152928 plus_strand 82695 54.0745 % minus_strand 70233 45.9255 % sh-clusters-2hrep3.txt2.csv.bed.gt5tc.noIGG nclusters 164050 plus_strand 84938 51.7757 % minus_strand 79112 48.2243 % sh-clusters-6hrep1.txt2.csv.bed.gt5tc.noIGG nclusters 249444 plus_strand 135573 54.3501 % minus_strand 113871 45.6499 % sh-clusters-6hrep2.txt2.csv.bed.gt5tc.noIGG nclusters 218957 plus_strand 117245 53.547 % minus_strand 101712 46.453 % sh-clusters-6hrep3.txt2.csv.bed.gt5tc.noIGG nclusters 104169 plus_strand 58142 55.8151 % minus_strand 46027 44.1849 % sh-clusters-IFN.txt2.csv.bed.gt5tc.noIGG nclusters 121249 plus_strand 64976 53.5889 % minus_strand 56273 46.4111 % sh-clusters-IL4.txt2.csv.bed.gt5tc.noIGG nclusters 233947 plus_strand 124109 53.05 % minus_strand 109838 46.95 % IGG nclusters 96009 plus_strand 50953 53.0711 % minus_strand 45056 46.9289 % # separate plus strand results for i in sh-clusters-*txt2.csv.bed.gt5tc.noIGG do wc $i awk -f ../filterPlusStrand.awk $i > $i.plus wc !$ done awk -f ../filterPlusStrand.awk sh-clusters-IGG.txt2.csv.bed.gt5tc > sh-clusters-IGG.txt2.csv.bed.gt5tc.plus 173469 1040814 20985272 sh-clusters-0hrep1.txt2.csv.bed.gt5tc.noIGG 90630 543780 10978703 sh-clusters-0hrep1.txt2.csv.bed.gt5tc.noIGG.plus 96126 576756 11487443 sh-clusters-0hrep2.txt2.csv.bed.gt5tc.noIGG 51226 307356 6142414 sh-clusters-0hrep2.txt2.csv.bed.gt5tc.noIGG.plus 273664 1641984 33503282 sh-clusters-0hrep3.txt2.csv.bed.gt5tc.noIGG 145758 874548 17899195 sh-clusters-0hrep3.txt2.csv.bed.gt5tc.noIGG.plus 132245 793470 15945601 sh-clusters-2hrep1.txt2.csv.bed.gt5tc.noIGG 71326 427956 8628279 sh-clusters-2hrep1.txt2.csv.bed.gt5tc.noIGG.plus 152928 917568 18677367 sh-clusters-2hrep2.txt2.csv.bed.gt5tc.noIGG 82695 496170 10132729 sh-clusters-2hrep2.txt2.csv.bed.gt5tc.noIGG.plus 164050 984300 19763391 sh-clusters-2hrep3.txt2.csv.bed.gt5tc.noIGG 84938 509628 10236875 sh-clusters-2hrep3.txt2.csv.bed.gt5tc.noIGG.plus 249444 1496664 29793943 sh-clusters-6hrep1.txt2.csv.bed.gt5tc.noIGG 135573 813438 16248396 sh-clusters-6hrep1.txt2.csv.bed.gt5tc.noIGG.plus 218957 1313742 26812051 sh-clusters-6hrep2.txt2.csv.bed.gt5tc.noIGG 117245 703470 14390311 sh-clusters-6hrep2.txt2.csv.bed.gt5tc.noIGG.plus 104169 625014 12507059 sh-clusters-6hrep3.txt2.csv.bed.gt5tc.noIGG 58142 348852 7006566 sh-clusters-6hrep3.txt2.csv.bed.gt5tc.noIGG.plus 121249 727494 14547710 sh-clusters-IFN.txt2.csv.bed.gt5tc.noIGG 64976 389856 7820802 sh-clusters-IFN.txt2.csv.bed.gt5tc.noIGG.plus 233947 1403682 28439506 sh-clusters-IL4.txt2.csv.bed.gt5tc.noIGG 124109 744654 15110059 sh-clusters-IL4.txt2.csv.bed.gt5tc.noIGG.plus #2 of 3 intersection bedtools multiinter -i sh-clusters-0hrep1.txt2.csv.bed.gt5tc.noIGG.plus sh-clusters-0hrep2.txt2.csv.bed.gt5tc.noIGG.plus sh-clusters-0hrep3.txt2.csv.bed.gt5tc.noIGG.plus > sh-clusters-0h.noIGG.plus.intersection-all.bed.gt5tc bedtools multiinter -i sh-clusters-2hrep1.txt2.csv.bed.gt5tc.noIGG.plus sh-clusters-2hrep2.txt2.csv.bed.gt5tc.noIGG.plus sh-clusters-2hrep3.txt2.csv.bed.gt5tc.noIGG.plus > sh-clusters-2h.noIGG.plus.intersection-all.bed.gt5tc bedtools multiinter -i sh-clusters-6hrep1.txt2.csv.bed.gt5tc.noIGG.plus sh-clusters-6hrep2.txt2.csv.bed.gt5tc.noIGG.plus sh-clusters-6hrep3.txt2.csv.bed.gt5tc.noIGG.plus > sh-clusters-6h.noIGG.plus.intersection-all.bed.gt5tc awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/filter-gt-2of3samples.awk sh-clusters-0h.noIGG.plus.intersection-all.bed.gt5tc | bedtools merge -i - > sh-clusters-0h.noIGG.plus.intersection-all.bed.gt5tc.gt2of3 wc !$ 26930 80790 764853 sh-clusters-0h.noIGG.plus.intersection-all.bed.gt5tc.gt2of3 awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/filter-gt-2of3samples.awk sh-clusters-2h.noIGG.plus.intersection-all.bed.gt5tc | bedtools merge -i - > sh-clusters-2h.noIGG.plus.intersection-all.bed.gt5tc.gt2of3 wc !$ 22960 68880 651289 sh-clusters-2h.noIGG.plus.intersection-all.bed.gt5tc.gt2of3 awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/filter-gt-2of3samples.awk sh-clusters-6h.noIGG.plus.intersection-all.bed.gt5tc | bedtools merge -i - > sh-clusters-6h.noIGG.plus.intersection-all.bed.gt5tc.gt2of3 wc !$ 38714 116142 1096177 sh-clusters-6h.noIGG.plus.intersection-all.bed.gt5tc.gt2of3 awk -v th=2 -f /data/images/proton/DKlab/mr/parclip/paralyzer/filter-gt-2of3samples.awk sh-clusters-0h.noIGG.plus.intersection-all.bed.gt5tc | bedtools merge -i - > sh-clusters-0h.noIGG.plus.intersection-all.bed.gt5tc.gt3of3 wc !$ 1745 5235 49620 sh-clusters-0h.noIGG.plus.intersection-all.bed.gt5tc.gt3of3 awk -v th=2 -f /data/images/proton/DKlab/mr/parclip/paralyzer/filter-gt-2of3samples.awk sh-clusters-2h.noIGG.plus.intersection-all.bed.gt5tc | bedtools merge -i - > sh-clusters-2h.noIGG.plus.intersection-all.bed.gt5tc.gt3of3 wc !$ 1726 5178 48807 sh-clusters-2h.noIGG.plus.intersection-all.bed.gt5tc.gt3of3 awk -v th=2 -f /data/images/proton/DKlab/mr/parclip/paralyzer/filter-gt-2of3samples.awk sh-clusters-6h.noIGG.plus.intersection-all.bed.gt5tc | bedtools merge -i - > sh-clusters-6h.noIGG.plus.intersection-all.bed.gt5tc.gt3of3 wc !$ 3056 9168 86604 sh-clusters-6h.noIGG.plus.intersection-all.bed.gt5tc.gt3of3 cd /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/ for i in /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/*gt5tc*of3 do echo $i awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/pa2annotate1.awk $i |sort -k1,1 -k4,4 -k2,2n -k5,5n > $i.anno.csv ln -s !$ done awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/pa2annotate1.awk /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/sh-clusters-IGG.txt2.csv.bed.gt5tc.plus |sort -k1,1 -k4,4 -k2,2n -k5,5n > sh-clusters-IGG.txt2.csv.bed.gt5tc.plus.anno.csv awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/pa2annotate1.awk /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/sh-clusters-IFN.txt2.csv.bed.gt5tc.noIGG.plus |sort -k1,1 -k4,4 -k2,2n -k5,5n > sh-clusters-IFN.txt2.csv.bed.gt5tc.noIGG.plus.anno.csv awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/pa2annotate1.awk /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/sh-clusters-IL4.txt2.csv.bed.gt5tc.noIGG.plus |sort -k1,1 -k4,4 -k2,2n -k5,5n > sh-clusters-IL4.txt2.csv.bed.gt5tc.noIGG.plus.anno.csv for i in /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/sh-distributions*.txt2.csv do ln -s $i done #get avg TtoC for i in sh-distributions*.txt2.csv do cat $i| awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/get-TtoC-conversionPct1.awk > $i".avg.csv" done #get avg+max TtoC (note >100% bug in /data/images/proton/DKlab/mr/parclip/paralyzer/README.PARalyzer_v1_1_src.txt, clipped to 100%) for i in sh-distributions*.txt2.csv do cat $i| awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/get-TtoC-conversionPct2.awk > $i".avg.csv" done # to bed for i in sh-distributions*.txt2.csv.avg.csv do cat $i|awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/pa-dist2bed.awk > $i".bed" done # intersect maxTtoC_gt_0.25 with clusters #/data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/ sh-distributions-0hrep1.txt2.csv.avg.csv.bed sh-distributions-0hrep2.txt2.csv.avg.csv.bed sh-distributions-0hrep3.txt2.csv.avg.csv.bed sh-distributions-2hrep1.txt2.csv.avg.csv.bed sh-distributions-2hrep2.txt2.csv.avg.csv.bed sh-distributions-2hrep3.txt2.csv.avg.csv.bed sh-distributions-6hrep1.txt2.csv.avg.csv.bed sh-distributions-6hrep2.txt2.csv.avg.csv.bed sh-distributions-6hrep3.txt2.csv.avg.csv.bed sh-distributions-IFN.txt2.csv.avg.csv.bed sh-distributions-IGG.txt2.csv.avg.csv.bed sh-distributions-IL4.txt2.csv.avg.csv.bed #with sh-clusters-0hrep1.txt2.csv.bed.gt5tc sh-clusters-0hrep2.txt2.csv.bed.gt5tc sh-clusters-0hrep3.txt2.csv.bed.gt5tc sh-clusters-2hrep1.txt2.csv.bed.gt5tc sh-clusters-2hrep2.txt2.csv.bed.gt5tc sh-clusters-2hrep3.txt2.csv.bed.gt5tc sh-clusters-6hrep1.txt2.csv.bed.gt5tc sh-clusters-6hrep2.txt2.csv.bed.gt5tc sh-clusters-6hrep3.txt2.csv.bed.gt5tc sh-clusters-IFN.txt2.csv.bed.gt5tc sh-clusters-IGG.txt2.csv.bed.gt5tc sh-clusters-IL4.txt2.csv.bed.gt5tc #is bedtools intersect -a sh-clusters-0hrep1.txt2.csv.bed.gt5tc -b /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/sh-distributions-0hrep1.txt2.csv.avg.csv.bed -wa -s > sh-clusters-0hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC bedtools intersect -a sh-clusters-0hrep2.txt2.csv.bed.gt5tc -b /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/sh-distributions-0hrep2.txt2.csv.avg.csv.bed -wa -s > sh-clusters-0hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC bedtools intersect -a sh-clusters-0hrep3.txt2.csv.bed.gt5tc -b /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/sh-distributions-0hrep3.txt2.csv.avg.csv.bed -wa -s > sh-clusters-0hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC bedtools intersect -a sh-clusters-2hrep1.txt2.csv.bed.gt5tc -b /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/sh-distributions-2hrep1.txt2.csv.avg.csv.bed -wa -s > sh-clusters-2hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC bedtools intersect -a sh-clusters-2hrep2.txt2.csv.bed.gt5tc -b /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/sh-distributions-2hrep2.txt2.csv.avg.csv.bed -wa -s > sh-clusters-2hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC bedtools intersect -a sh-clusters-2hrep3.txt2.csv.bed.gt5tc -b /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/sh-distributions-2hrep3.txt2.csv.avg.csv.bed -wa -s > sh-clusters-2hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC bedtools intersect -a sh-clusters-6hrep1.txt2.csv.bed.gt5tc -b /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/sh-distributions-6hrep1.txt2.csv.avg.csv.bed -wa -s > sh-clusters-6hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC bedtools intersect -a sh-clusters-6hrep2.txt2.csv.bed.gt5tc -b /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/sh-distributions-6hrep2.txt2.csv.avg.csv.bed -wa -s > sh-clusters-6hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC bedtools intersect -a sh-clusters-6hrep3.txt2.csv.bed.gt5tc -b /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/sh-distributions-6hrep3.txt2.csv.avg.csv.bed -wa -s > sh-clusters-6hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC bedtools intersect -a sh-clusters-IFN.txt2.csv.bed.gt5tc -b /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/sh-distributions-IFN.txt2.csv.avg.csv.bed -wa -s > sh-clusters-IFN.txt2.csv.bed.gt5tc.gt0.25TtoC bedtools intersect -a sh-clusters-IGG.txt2.csv.bed.gt5tc -b /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/sh-distributions-IGG.txt2.csv.avg.csv.bed -wa -s > sh-clusters-IGG.txt2.csv.bed.gt5tc.gt0.25TtoC bedtools intersect -a sh-clusters-IL4.txt2.csv.bed.gt5tc -b /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc/sh-distributions-IL4.txt2.csv.avg.csv.bed -wa -s > sh-clusters-IL4.txt2.csv.bed.gt5tc.gt0.25TtoC # wc *gt0.25TtoC 135421 812526 16689807 sh-clusters-0hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC 79000 474000 9595941 sh-clusters-0hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC 221471 1328826 27552243 sh-clusters-0hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC 109197 655182 13432697 sh-clusters-2hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC 131255 787530 16317463 sh-clusters-2hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC 126346 758076 15488000 sh-clusters-2hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC 193097 1158582 23460663 sh-clusters-6hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC 172278 1033668 21498121 sh-clusters-6hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC 85479 512874 10437844 sh-clusters-6hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC 102563 615378 12523811 sh-clusters-IFN.txt2.csv.bed.gt5tc.gt0.25TtoC 67597 405582 8065862 sh-clusters-IGG.txt2.csv.bed.gt5tc.gt0.25TtoC 185857 1115142 23059489 sh-clusters-IL4.txt2.csv.bed.gt5tc.gt0.25TtoC # # strand stats for i in sh-clusters-*gt0.25TtoC do echo $i awk -f ../strandStats1.awk $i done sh-clusters-0hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC nclusters 135421 plus_strand 73876 54.5528 % minus_strand 61545 45.4472 % sh-clusters-0hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC nclusters 79000 plus_strand 44080 55.7975 % minus_strand 34920 44.2025 % sh-clusters-0hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC nclusters 221471 plus_strand 122914 55.4989 % minus_strand 98557 44.5011 % sh-clusters-2hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC nclusters 109197 plus_strand 61910 56.6957 % minus_strand 47287 43.3043 % sh-clusters-2hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC nclusters 131255 plus_strand 73340 55.876 % minus_strand 57915 44.124 % sh-clusters-2hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC nclusters 126346 plus_strand 68649 54.3341 % minus_strand 57697 45.6659 % sh-clusters-6hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC nclusters 193097 plus_strand 110711 57.3344 % minus_strand 82386 42.6656 % sh-clusters-6hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC nclusters 172278 plus_strand 96480 56.0025 % minus_strand 75798 43.9975 % sh-clusters-6hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC nclusters 85479 plus_strand 49788 58.2459 % minus_strand 35691 41.7541 % sh-clusters-IFN.txt2.csv.bed.gt5tc.gt0.25TtoC nclusters 102563 plus_strand 57299 55.8671 % minus_strand 45264 44.1329 % sh-clusters-IGG.txt2.csv.bed.gt5tc.gt0.25TtoC nclusters 67597 plus_strand 37734 55.822 % minus_strand 29863 44.178 % sh-clusters-IL4.txt2.csv.bed.gt5tc.gt0.25TtoC nclusters 185857 plus_strand 103278 55.5685 % minus_strand 82579 44.4315 % # separate plus strand results for i in sh-c*gt0.25TtoC do wc $i awk -f ../filterPlusStrand.awk $i > $i.plus wc !$ done 135421 812526 16689807 sh-clusters-0hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC 73876 443256 9095412 sh-clusters-0hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 79000 474000 9595941 sh-clusters-0hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC 44080 264480 5362648 sh-clusters-0hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 221471 1328826 27552243 sh-clusters-0hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC 122914 737484 15311318 sh-clusters-0hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 109197 655182 13432697 sh-clusters-2hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC 61910 371460 7625144 sh-clusters-2hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 131255 787530 16317463 sh-clusters-2hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC 73340 440040 9130130 sh-clusters-2hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 126346 758076 15488000 sh-clusters-2hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC 68649 411894 8404346 sh-clusters-2hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 193097 1158582 23460663 sh-clusters-6hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC 110711 664266 13468363 sh-clusters-6hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 172278 1033668 21498121 sh-clusters-6hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC 96480 578880 12044433 sh-clusters-6hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 85479 512874 10437844 sh-clusters-6hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC 49788 298728 6092669 sh-clusters-6hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 102563 615378 12523811 sh-clusters-IFN.txt2.csv.bed.gt5tc.gt0.25TtoC 57299 343794 7010472 sh-clusters-IFN.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 67597 405582 8065862 sh-clusters-IGG.txt2.csv.bed.gt5tc.gt0.25TtoC 37734 226404 4507031 sh-clusters-IGG.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 185857 1115142 23059489 sh-clusters-IL4.txt2.csv.bed.gt5tc.gt0.25TtoC 103278 619668 12803866 sh-clusters-IL4.txt2.csv.bed.gt5tc.gt0.25TtoC.plus #remove IGG regions for i in sh-clusters-*gt0.25TtoC.plus do wc $i bedtools intersect -a $i -b sh-clusters-IGG.txt2.csv.bed.gt5tc.gt0.25TtoC.plus -v -s |sort -k1,1 -k2,2n > $i.noIGG wc !$ done 73876 443256 9095412 sh-clusters-0hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 68230 409380 8377155 sh-clusters-0hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG 44080 264480 5362648 sh-clusters-0hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 40863 245178 4962377 sh-clusters-0hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG 122914 737484 15311318 sh-clusters-0hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 117165 702990 14561671 sh-clusters-0hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG 61910 371460 7625144 sh-clusters-2hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 55531 333186 6812745 sh-clusters-2hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG 73340 440040 9130130 sh-clusters-2hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 68652 411912 8529155 sh-clusters-2hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG 68649 411894 8404346 sh-clusters-2hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 64209 385254 7843126 sh-clusters-2hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG 110711 664266 13468363 sh-clusters-6hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 103984 623904 12612750 sh-clusters-6hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG 96480 578880 12044433 sh-clusters-6hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 90418 542508 11258588 sh-clusters-6hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG 49788 298728 6092669 sh-clusters-6hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 46381 278286 5667245 sh-clusters-6hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG 57299 343794 7010472 sh-clusters-IFN.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 52611 315666 6420070 sh-clusters-IFN.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG 37734 226404 4507031 sh-clusters-IGG.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 0 0 0 sh-clusters-IGG.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG 103278 619668 12803866 sh-clusters-IL4.txt2.csv.bed.gt5tc.gt0.25TtoC.plus 94689 568134 11694649 sh-clusters-IL4.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG #2 of 3 intersection bedtools multiinter -i sh-clusters-0hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG sh-clusters-0hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG sh-clusters-0hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG > sh-clusters-0h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc bedtools multiinter -i sh-clusters-2hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG sh-clusters-2hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG sh-clusters-2hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG > sh-clusters-2h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc bedtools multiinter -i sh-clusters-6hrep1.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG sh-clusters-6hrep2.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG sh-clusters-6hrep3.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG > sh-clusters-6h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/filter-gt-2of3samples.awk sh-clusters-0h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc | bedtools merge -i - > sh-clusters-0h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc.gt2of3 wc !$ 17734 53202 504139 sh-clusters-0h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc.gt2of3 awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/filter-gt-2of3samples.awk sh-clusters-2h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc | bedtools merge -i - > sh-clusters-2h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc.gt2of3 wc !$ 15155 45465 430087 sh-clusters-2h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc.gt2of3 awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/filter-gt-2of3samples.awk sh-clusters-6h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc | bedtools merge -i - > sh-clusters-6h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc.gt2of3 wc !$ 24342 73026 690248 sh-clusters-6h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc.gt2of3 awk -v th=2 -f /data/images/proton/DKlab/mr/parclip/paralyzer/filter-gt-2of3samples.awk sh-clusters-0h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc | bedtools merge -i - > sh-clusters-0h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc.gt3of3 wc !$ 918 2754 26121 sh-clusters-0h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc.gt3of3 awk -v th=2 -f /data/images/proton/DKlab/mr/parclip/paralyzer/filter-gt-2of3samples.awk sh-clusters-2h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc | bedtools merge -i - > sh-clusters-2h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc.gt3of3 wc !$ 910 2730 25779 sh-clusters-2h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc.gt3of3 awk -v th=2 -f /data/images/proton/DKlab/mr/parclip/paralyzer/filter-gt-2of3samples.awk sh-clusters-6h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc | bedtools merge -i - > sh-clusters-6h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc.gt3of3 wc !$ 1518 4554 43124 sh-clusters-6h.gt0.25TtoC.plus.noIGG.intersection-all.bed.gt5tc.gt3of3 mkdir /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc_gt0.25TtoC cd /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/res/recommended_settings_gt5tc_gt0.25TtoC for i in /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/*gt0.25TtoC*of3 do echo $i awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/pa2annotate1.awk $i |sort -k1,1 -k4,4 -k2,2n -k5,5n > $i.anno.csv ln -s !$ done awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/pa2annotate1.awk /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/sh-clusters-IGG.txt2.csv.bed.gt5tc.gt0.25TtoC.plus |sort -k1,1 -k4,4 -k2,2n -k5,5n > sh-clusters-IGG.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.anno.csv awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/pa2annotate1.awk /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/sh-clusters-IFN.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG |sort -k1,1 -k4,4 -k2,2n -k5,5n > sh-clusters-IFN.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG.anno.csv awk -f /data/images/proton/DKlab/mr/parclip/paralyzer/pa2annotate1.awk /data/images/proton/DKlab/mr/parclip/paralyzer/PARalyzer_v1_1b/sh-clusters-IL4.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG |sort -k1,1 -k4,4 -k2,2n -k5,5n > sh-clusters-IL4.txt2.csv.bed.gt5tc.gt0.25TtoC.plus.noIGG.anno.csv