-
Notifications
You must be signed in to change notification settings - Fork 10
/
2017-12-20.analysis.sh
executable file
·1485 lines (1346 loc) · 73.9 KB
/
2017-12-20.analysis.sh
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
step=$1
substep=$2
#=======================================
DATA=/ifs/scratch/oursu/paper_2017-12-20
resolutions=10000,50000,500000
MYCODE=/srv/gsfs0/projects/kundaje/users/oursu/code
MAPQ=30
mypython=/srv/gsfs0/projects/kundaje/users/oursu/code/anaconda2/mypython/bin/python
chrSizes=${DATA}/data/chrSizes.hg19.txt
macs2=/srv/gsfs0/projects/kundaje/users/oursu/code/anaconda2/mypython/bin/macs2
#=======================================
if [[ ${step} == "combine_score_files" ]];
then
#combine hichip files
hichip_dir=${DATA}/results/HiChIP/res50000.final/compiled_scores
all_chromo=${hichip_dir}/HiChIP.AllScores.by_chromosome.gz
all=${hichip_dir}/HiChIP.AllScores.genomewide.gz
rm ${all_chromo} ${all}
for method in GenomeDISCO HiCRep HiC-Spector;
do
zcat -f ${hichip_dir}/HiChIP.${method}.scores.by_chromosome.txt.gz | awk -v mymethod=${method} '{print mymethod"\t"$0}' >> ${all_chromo}.tmp
zcat -f ${hichip_dir}/HiChIP.${method}.scores.genomewide.txt.gz | awk -v mymethod=${method} '{print mymethod"\t"$0}' >> ${all}.tmp
done
zcat -f ${all_chromo}.tmp | gzip > ${all_chromo}
zcat -f ${all}.tmp | gzip > ${all}
rm ${all_chromo}.tmp ${all}.tmp
echo ${all_chromo}
echo ${all}
#combine hic files
hic_dir=${DATA}/results/rao/res50000.final/compiled_scores
all_chromo=${hic_dir}/HiC.AllScores.by_chromosome.gz
all=${hic_dir}/HiC.AllScores.genomewide.gz
rm ${all_chromo} ${all}
for method in GenomeDISCO HiCRep HiC-Spector;
do
zcat -f ${hic_dir}/HiC.${method}.scores.by_chromosome.txt.gz | awk -v mymethod=${method} '{print mymethod"\t"$0}' >> ${all_chromo}.tmp
zcat -f ${hic_dir}/HiC.${method}.scores.genomewide.txt.gz | awk -v mymethod=${method} '{print mymethod"\t"$0}' >> ${all}.tmp
done
zcat -f ${all_chromo}.tmp |gzip > ${all_chromo}
zcat -f ${all}.tmp | gzip > ${all}
rm ${all_chromo}.tmp ${all}.tmp
echo ${all_chromo}
echo ${all}
#combine files from simulations
sim_dir=${DATA}/simulations
all=${sim_dir}/Simulations.AllScores.gz
rm ${all}
zcat -f zcat -f ${sim_dir}/EdgeNoise/GenomeDISCO.*.results.txt | head -n1 | awk '{print "Simulation\tMethod\t"$0}' > ${all}.tmp
for sim in EdgeNoise NodeNoise BoundaryNoise DistanceDependence RepNonrep;
do
for method in GenomeDISCO HiCRep HiC-Spector;
do
zcat -f ${sim_dir}/${sim}/${method}.*.results.txt | grep -v Depth | awk -v mysim=${sim} -v mymethod=${method} '{print mysim"\t"mymethod"\t"$0}' | sort | uniq >> ${all}.tmp
done
done
zcat -f ${all}.tmp | gzip > ${all}
rm ${all}.tmp
echo ${all}
fi
if [[ ${step} == "supp_table1" ]];
then
supp_table1=${DATA}/data/Supp_Table1.txt
echo "Assay__Analysis__GEO__Resolution__CellType" | sed 's/__/\t/g' > ${supp_table1}
#hic for simulations
for cell in GM12878 K562 NHEK HUVEC HMEC IMR90 KBM7;
do
echo "Hi-C__simulations__GSE63525__50000__${cell}" | sed 's/__/\t/g' >> ${supp_table1}
done
for dataset_number in {1..83};
do
dataset="HIC"$(echo "00${dataset_number}" | sed 's/.*\(...\)/\1/')
echo "Hi-C__Real_Hi-C_analysis__GSE63525__50000__${dataset}" | sed 's/__/\t/g' >> ${supp_table1}
done
for cell in GM12878 HCASMC K562 MyLa Naive Th17 Treg;
do
echo "HiChIP__Real_HiChIP_analysis__GSE101498__50000__${cell}" | sed 's/__/\t/g' >> ${supp_table1}
done
cat ${supp_table1}
fi
if [[ ${step} == "supp_table2" ]];
then
#get it from the other table
cp ${DATA}/data/LA_metadata.forPaperTable.txt ${DATA}/data/Supp_Table2.txt #make sure to add the difference in distance dependence
fi
if [[ ${step} == "simulations" ]];
then
for res in 50000;
do
simulations=${DATA}/simulations
mkdir -p ${simulations}
mdir=/ifs/scratch/oursu/data/chr21_datasets
nodefile=${simulations}/nodes/nodes.${res}.chr21.gz
mnames="GM12878_combined,HMEC,HUVEC,IMR90,K562,KBM7,NHEK"
dddata=${mdir}/GM12878_combined.chr21.RAWobserved.gz
SIMULATION_DIR=${simulations}
mkdir -p ${SIMULATION_DIR}
EDGE_DIR=${SIMULATION_DIR}/EdgeNoise
NODE_DIR=${SIMULATION_DIR}/NodeNoise
B_DIR=${SIMULATION_DIR}/BoundaryNoise
DD_DIR=${SIMULATION_DIR}/DistanceDependence
NONREP_DIR=${SIMULATION_DIR}/RepNonrep
mkdir -p ${EDGE_DIR}
mkdir -p ${NODE_DIR}
mkdir -p ${B_DIR}
mkdir -p ${DD_DIR}
mkdir -p ${NONREP_DIR}
bashrc=${MYCODE}/3DChromatin_ReplicateQC/configuration_files/bashrc.configuration
mini_coord=320 #16Mb
maxi_coord=900 #45Mb
if [[ ${substep} == "EdgeNoise" ]];
then
for depth in 10000 100000 1000000 10000000;
do
for mname in $(echo ${mnames} | sed 's/,/ /g');
do
matpath=${mdir}/${mname}.chr21.RAWobserved.gz
nodenoise=0.0
boundarynoise=0
for edgenoise in 0.0 0.1 0.25 0.5 0.75 0.9;
do
cmd="${mypython} ${MYCODE}/3DChromatin_ReplicateQC/software/genomedisco/genomedisco/simulations_from_real_data.py --outdir ${EDGE_DIR} --resolution ${res} --nodes ${nodefile} --matrices ${matpath} --matrix_names ${mname} --distDepData ${dddata} --depth ${depth} --edgenoise ${edgenoise} --nodenoise ${nodenoise} --boundarynoise ${boundarynoise} --mini ${mini_coord} --maxi ${maxi_coord}"
s=${EDGE_DIR}/script_depth${depth}.${mname}.edgenoise$(echo ${edgenoise} | sed 's/,/_/g').sh
echo "source ${bashrc}" > ${s}
echo $cmd >> ${s}
chmod 755 ${s}
echo $s
qsub -o ${s}.o -e ${s}.e ${s}
done
done
done
fi
if [[ ${substep} == "NodeNoise" ]];
then
for depth in 10000 100000 1000000 10000000;
do
for mname in $(echo ${mnames} | sed 's/,/ /g');
do
matpath=${mdir}/${mname}.chr21.RAWobserved.gz
edgenoise="0.0"
boundarynoise=0
for nodenoise in 0.0 0.1 0.25 0.5 0.75 0.9;
do
cmd="${mypython} ${MYCODE}/3DChromatin_ReplicateQC/software/genomedisco/genomedisco//simulations_from_real_data.py --outdir ${NODE_DIR} --resolution ${res} --nodes ${nodefile} --matrices ${matpath} --matrix_names ${mname} --distDepData ${dddata} --depth ${depth} --edgenoise ${edgenoise} --nodenoise ${nodenoise} --boundarynoise ${boundarynoise} --mini ${mini_coord} --maxi ${maxi_coord}"
s=${NODE_DIR}/script_depth${depth}.${mname}.nodenoise${nodenoise}.sh
echo "source ${bashrc}" > ${s}
echo $cmd >> ${s}
chmod 755 ${s}
echo $s
qsub -o ${s}.o -e ${s}.e ${s}
done
done
done
fi
if [[ ${substep} == "BoundaryNoise" ]];
then
for depth in 10000 100000 1000000 10000000;
do
for mname in $(echo ${mnames} | sed 's/,/ /g');
do
matpath=${mdir}/${mname}.chr21.RAWobserved.gz
edgenoise=0.0
nodenoise=0.0
for boundarynoise in 0 1 2 4 8 16 32;
do
cmd="${mypython} ${MYCODE}/3DChromatin_ReplicateQC/software/genomedisco/genomedisco/simulations_from_real_data.py --outdir ${B_DIR} --resolution ${res} --nodes ${nodefile} --matrices ${matpath} --matrix_names ${mname} --distDepData ${dddata} --depth ${depth} --edgenoise ${edgenoise} --nodenoise ${nodenoise} --boundarynoise ${boundarynoise} --mini ${mini_coord} --maxi ${maxi_coord}"
s=${B_DIR}/script_depth${depth}.${mname}.boundarynoise.${boundarynoise}.sh
echo "source ${bashrc}" > ${s}
echo $cmd >> ${s}
chmod 755 ${s}
echo $s
qsub -o ${s}.o -e ${s}.e ${s}
done
done
done
fi
if [[ ${substep} == "DistDep" ]];
then
#"GM12878_combined,HMEC,HUVEC,IMR90,K562,KBM7,NHEK"
d1=${mdir}/GM12878_combined.chr21.RAWobserved.gz
d2=${mdir}/HMEC.chr21.RAWobserved.gz
d3=${mdir}/HUVEC.chr21.RAWobserved.gz
d4=${mdir}/IMR90.chr21.RAWobserved.gz
d5=${mdir}/K562.chr21.RAWobserved.gz
d6=${mdir}/KBM7.chr21.RAWobserved.gz
d7=${mdir}/NHEK.chr21.RAWobserved.gz
for depth in 10000 100000 1000000 10000000;
do
for mname in $(echo ${mnames} | sed 's/,/ /g');
do
matpath=${mdir}/${mname}.chr21.RAWobserved.gz
edgenoise=0.0
nodenoise=0.0
boundarynoise=0
cmd="${mypython} ${MYCODE}/3DChromatin_ReplicateQC/software/genomedisco/genomedisco/simulations_from_real_data.py --outdir ${DD_DIR} --resolution ${res} --nodes ${nodefile} --matrices ${matpath} --matrix_names ${mname} --distDepData ${d1},${d2},${d3},${d4},${d5},${d6},${d7} --depth ${depth} --edgenoise ${edgenoise} --nodenoise ${nodenoise} --boundarynoise ${boundarynoise} --mini ${mini_coord} --maxi ${maxi_coord}"
s=${DD_DIR}/script_depth${depth}.ddHIC${HICNUM}.${mname}.sh
echo "source ${bashrc}" > ${s}
echo $cmd >> ${s}
chmod 755 ${s}
echo $s
qsub -o ${s}.o -e ${s}.e ${s}
done
done
fi
if [[ ${substep} == "nodes" ]];
then
module load bedtools/2.26.0
mkdir -p ${simulations}/nodes
nodes=${simulations}/nodes/nodes.${res}.chr21.gz
bedtools makewindows -i winnum -w ${res} -s ${res} -g ${chrSizes} | awk -v reso=${res} '{print $1"\t"$2"\t"$3"\t"$2}' | grep -w "chr21" | gzip > ${nodes}
ls -lh ${nodes}
fi
if [[ ${substep} == "metadata" ]];
then
edgenoise_metadata=${EDGE_DIR}/Metadata.samples
edgenoise_metadata_pairs=${EDGE_DIR}/Metadata.pairs
nodenoise_metadata=${NODE_DIR}/Metadata.samples
nodenoise_metadata_pairs=${NODE_DIR}/Metadata.pairs
boundarynoise_metadata=${B_DIR}/Metadata.samples
boundarynoise_metadata_pairs=${B_DIR}/Metadata.pairs
nonrep_metadata=${NONREP_DIR}/Metadata.samples
nonrep_metadata_pairs=${NONREP_DIR}/Metadata.pairs
dd_metadata=${DD_DIR}/Metadata.samples
dd_metadata_pairs=${DD_DIR}/Metadata.pairs
rm ${edgenoise_metadata}
rm ${edgenoise_metadata_pairs}
nodenoise=0.0
boundarynoise=0
for depth in 10000 100000 1000000 10000000;
do
for edgenoise in 0.0 0.1 0.25 0.5 0.75 0.9;
do
for mname in $(echo ${mnames} | sed 's/,/ /g');
do
d1=Depth_${depth}.${mname}.EN_0.0.NN_${nodenoise}.BN_${boundarynoise}.a.dd_0
d2=Depth_${depth}.${mname}.EN_${edgenoise}.NN_${nodenoise}.BN_${boundarynoise}.b.dd_0
echo "${d1}delim${d2}delimchr21" | sed 's/delim/\t/g' >> ${edgenoise_metadata_pairs}
d1=Depth_${depth}.${mname}.EN_0.0.NN_${nodenoise}.BN_${boundarynoise}.b.dd_0
d2=Depth_${depth}.${mname}.EN_${edgenoise}.NN_${nodenoise}.BN_${boundarynoise}.a.dd_0
echo "${d1}delim${d2}delimchr21" | sed 's/delim/\t/g' >> ${edgenoise_metadata_pairs}
for ab in a b;
do
chromo="simulated"
dataname_short=Depth_${depth}.${mname}.EN_${edgenoise}.NN_${nodenoise}.BN_${boundarynoise}.${ab}.dd_0
echo "${dataname_short}delim${EDGE_DIR}/${dataname_short}.gzdelimNA" | sed 's/delim/\t/g' >> ${edgenoise_metadata}
done
done
done
done
rm ${nodenoise_metadata}
rm ${nodenoise_metadata_pairs}
edgenoise=0.0
boundarynoise=0
for depth in 10000 100000 1000000 10000000;
do
for nodenoise in 0.0 0.1 0.25 0.5 0.75 0.9;
do
for mname in $(echo ${mnames} | sed 's/,/ /g');
do
d1=Depth_${depth}.${mname}.EN_${edgenoise}.NN_0.0.BN_${boundarynoise}.a.dd_0
d2=Depth_${depth}.${mname}.EN_${edgenoise}.NN_${nodenoise}.BN_${boundarynoise}.b.dd_0
echo "${d1}delim${d2}delimchr21" | sed 's/delim/\t/g' >> ${nodenoise_metadata_pairs}
d1=Depth_${depth}.${mname}.EN_${edgenoise}.NN_0.0.BN_${boundarynoise}.b.dd_0
d2=Depth_${depth}.${mname}.EN_${edgenoise}.NN_${nodenoise}.BN_${boundarynoise}.a.dd_0
echo "${d1}delim${d2}delimchr21" | sed 's/delim/\t/g' >> ${nodenoise_metadata_pairs}
for ab in a b;
do
chromo="simulated"
dataname_short=Depth_${depth}.${mname}.EN_${edgenoise}.NN_${nodenoise}.BN_${boundarynoise}.${ab}.dd_0
echo "${dataname_short}delim${NODE_DIR}/${dataname_short}.gzdelimNA" | sed 's/delim/\t/g' >> ${nodenoise_metadata}
done
done
done
done
rm ${boundarynoise_metadata}
rm ${boundarynoise_metadata_pairs}
edgenoise=0.0
nodenoise=0.0
for depth in 10000 100000 1000000 10000000;
do
for boundarynoise in 0 1 2 4 8 16 32;
do
for mname in $(echo ${mnames} | sed 's/,/ /g');
do
d1=Depth_${depth}.${mname}.EN_${edgenoise}.NN_${nodenoise}.BN_0.a.dd_0
d2=Depth_${depth}.${mname}.EN_${edgenoise}.NN_${nodenoise}.BN_${boundarynoise}.b.dd_0
echo "${d1}delim${d2}delimchr21" | sed 's/delim/\t/g' >> ${boundarynoise_metadata_pairs}
d1=Depth_${depth}.${mname}.EN_${edgenoise}.NN_${nodenoise}.BN_0.b.dd_0
d2=Depth_${depth}.${mname}.EN_${edgenoise}.NN_${nodenoise}.BN_${boundarynoise}.a.dd_0
echo "${d1}delim${d2}delimchr21" | sed 's/delim/\t/g' >> ${boundarynoise_metadata_pairs}
for ab in a b;
do
chromo="simulated"
dataname_short=Depth_${depth}.${mname}.EN_${edgenoise}.NN_${nodenoise}.BN_${boundarynoise}.${ab}.dd_0
echo "${dataname_short}delim${B_DIR}/${dataname_short}.gzdelimNA" | sed 's/delim/\t/g' >> ${boundarynoise_metadata}
done
done
done
done
rm ${nonrep_metadata}
rm ${nonrep_metadata_pairs}
boundarynoise=0
nodenoise=0.0
edgenoise=0.0
for depth in 10000 100000 1000000 10000000;
do
for edgenoise in 0.0;
do
for mname1 in $(echo ${mnames} | sed 's/,/ /g');
do
for ab1 in a b;
do
dataname_short1=Depth_${depth}.${mname1}.EN_0.0.NN_${nodenoise}.BN_${boundarynoise}.${ab1}.dd_0
for mname2 in $(echo ${mnames} | sed 's/,/ /g');
do
for ab2 in a b;
do
dataname_short2=Depth_${depth}.${mname2}.EN_0.0.NN_${nodenoise}.BN_${boundarynoise}.${ab2}.dd_0
echo "${dataname_short1}delim${dataname_short2}delimsimulated" | sed 's/delim/\t/g' >> ${nonrep_metadata_pairs}.many
done
done
done
done
done
done
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/software/genomedisco/paper_analysis/orderpairs.py --file ${nonrep_metadata_pairs}.many --out ${nonrep_metadata_pairs}.many2
cat ${nonrep_metadata_pairs}.many2 | awk '{if ($1!=$2) print $0}' | sort | uniq > ${nonrep_metadata_pairs}
cp ${edgenoise_metadata} ${nonrep_metadata}
rm ${nonrep_metadata_pairs}.many*
rm ${dd_metadata}
rm ${dd_metadata_pairs}.many
rm ${dd_metadata_pairs}
boundarynoise=0
nodenoise=0.0
edgenoise=0.0
for depth in 10000 100000 1000000 10000000;
do
for mname1 in $(echo ${mnames} | sed 's/,/ /g');
do
for dd1 in 0 1 2 3 4 5 6;
do
for ab1 in a b;
do
dataname_short1=Depth_${depth}.${mname1}.EN_${edgenoise}.NN_${nodenoise}.BN_${boundarynoise}.${ab1}.dd_${dd1}
for mname2 in ${mname1};
do
for dd2 in 0 1 2 3 4 5 6;
do
for ab2 in a b;
do
dataname_short2=Depth_${depth}.${mname2}.EN_${edgenoise}.NN_${nodenoise}.BN_${boundarynoise}.${ab2}.dd_${dd2}
echo "${dataname_short1}delim${dataname_short2}delimsimulated" | sed 's/delim/\t/g' >> ${dd_metadata_pairs}.many
done
done
done
done
done
done
done
cat ${dd_metadata_pairs}.many | awk '{if ($1!=$2) print $0}' | sort | uniq > ${dd_metadata_pairs}
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/software/genomedisco/paper_analysis/orderpairs.py --file ${dd_metadata_pairs}.many --out ${dd_metadata_pairs}.many2
cat ${dd_metadata_pairs}.many2 | awk '{if ($1!=$2) print $0}' | sort | uniq > ${dd_metadata_pairs}
rm ${dd_metadata_pairs}.many*
for depth in 10000 100000 1000000 10000000;
do
for dd1 in 0 1 2 3 4 5 6;
do
for mname in $(echo ${mnames} | sed 's/,/ /g');
do
for ab1 in a b;
do
dataname_short1=Depth_${depth}.${mname}.EN_${edgenoise}.NN_${nodenoise}.BN_${boundarynoise}.${ab1}.dd_${dd1}
chromo="simulated"
echo "${dataname_short1}delim${DD_DIR}/${dataname_short1}.gzdelimNA" | sed 's/delim/\t/g' >> ${dd_metadata}
done
done
done
done
fi
if [[ ${substep} == "split" ]];
then
for spot in DistanceDependence; #RepNonrep EdgeNoise BoundaryNoise NodeNoise
do
metadata_samples=${SIMULATION_DIR}/${spot}/Metadata.samples
bins=${nodefile}
out=${SIMULATION_DIR}/${spot}
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py split --metadata_samples ${metadata_samples} --bins ${bins} --outdir ${out} --methods GenomeDISCO,HiCRep,HiC-Spector --running_mode sge
done
fi
if [[ ${substep} == "run" ]];
then
for spot in DistanceDependence; #BoundaryNoise NodeNoise; #DistanceDependence EdgeNoise RepNonrep
do
metadata_pairs=${SIMULATION_DIR}/${spot}/Metadata.pairs
out=${SIMULATION_DIR}/${spot}
echo ${metadata_pairs}
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py reproducibility --metadata_pairs ${metadata_pairs} --outdir ${out} --methods HiCRep --running_mode sge --concise_analysis
done
fi
if [[ ${substep} == "compile_scores" ]];
then
for noisedirname in ${EDGE_DIR} ${NODE_DIR} ${B_DIR} ${DD_DIR} ${NONREP_DIR};
do
for method in GenomeDISCO HiCRep HiC-Spector;
do
summary=${noisedirname}/${method}.results.txt
rm ${summary}
echo "====="
echo ${method}
echo ${summary}
cat ${noisedirname}/results/reproducibility/${method}/*txt | head
echo ${noisedirname}/results/reproducibility/${method}/
cat ${noisedirname}/results/reproducibility/${method}/*txt | cut -f1,2,4 | sort -k3 -n |sed 's/Depth_//g' | sed 's/[.]G/\tG/g' | sed 's/[.]K/\tK/g' | sed 's/[.]I/\tI/g' | sed 's/[.]H/\tH/g' | sed 's/[.]NH/\tNH/g' | sed 's/[.]EN_/\t/g' | sed 's/[.]NN_/\t/g' | sed 's/[.]eps_0[.]9//g' | sed 's/[.]BN_/\t/g' | sed 's/[.]dd_/\t/g' | sed 's/[.]a/\ta/g' | sed 's/[.]b/\tb/g' > ${summary}
if [[ ${noisedirname} == ${DD_DIR} ]];
then
cat ${noisedirname}/results/reproducibility/${method}/*.txt | cut -f1,2,4 | sort -k3 -n |sed 's/Depth_//g' | sed 's/[.]G/\tG/g' | sed 's/[.]K/\tK/g' | sed 's/[.]I/\tI/g' | sed 's/[.]H/\tH/g' | sed 's/[.]NH/\tNH/g' | sed 's/[.]EN_/\t/g' | sed 's/[.]NN_/\t/g' | sed 's/[.]eps_0[.]9//g' | sed 's/[.]BN_/\t/g' | sed 's/[.]dd_/\t/g' | sed 's/[.]a/\ta/g' | sed 's/[.]b/\tb/g' > ${summary}
fi
if [[ ${noisedirname} == ${NONREP_DIR} ]];
then
cat ${noisedirname}/results/reproducibility/${method}/*.txt | cut -f1,2,4 |sed 's/Depth_//g' | sed 's/[.]G/\tG/g' | sed 's/[.]K/\tK/g' | sed 's/[.]I/\tI/g' | sed 's/[.]H/\tH/g' | sed 's/[.]NH/\tNH/g' | sed 's/[.]EN_/\t/g' | sed 's/[.]NN_/\t/g' | sed 's/[.]BN_/\t/g' | sed 's/[.]dd_/\t/g' | sed 's/[.]a/\ta/g' | sed 's/[.]b/\tb/g' | head # > ${summary}
fi
done
done
fi
done
fi
if [[ ${step} == "encode_finalrun_downsample_189" ]];
then
metadata_samples=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_downsample/Bulk.Downsample/AllChrAnon/processed/metadata/metadata.res40000
metadata_pairs=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_downsample/Bulk.Downsample/AllChrAnon/processed/metadata/metadata.res40000.pairs
nodes=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_downsample/Bulk.Downsample/AllChrAnon/processed/nodes/Nodes.w40000.bed.gz
outanalysis=/ifs/scratch/oursu/paper_2017-12-20/encode_downsample.final
mkdir -p ${outanalysis}
params=${outanalysis}/params
cat ${MYCODE}/3DChromatin_ReplicateQC/examples/example_parameters.txt | sed 's/10G/5G/g' > ${params}
cat ${params}
if [[ ${substep} == "format_scores" ]];
then
rm ${outanalysis}/results/compiled_scores.txt
cat ${outanalysis}/results/reproducibility/GenomeDISCO*/M*txt | sort | uniq > ${outanalysis}/results/compiled_scores.txt
echo ${outanalysis}/results/compiled_scores.txt
${mypython} /srv/gsfs0/projects/kundaje/users/oursu/code/3DChromatin_ReplicateQC/software/genomedisco/paper_analysis/2017-12-20/arrange_encode_scores.py --metadata_pairs ${metadata_pairs} --scoring_file ${outanalysis}/results/compiled_scores.txt --out ${outanalysis}/results/encode_downsample.189comparisons.2018_01_30.txt
echo ${outanalysis}/results/encode_downsample.189comparisons.2018_01_30.txt
fi
if [[ ${substep} == "split" ]];
then
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py split --running_mode sge --metadata_samples ${metadata_samples} --bins ${nodes} --outdir ${outanalysis} --parameters_file ${params} --methods GenomeDISCO --subset_chromosomes chrX
fi
if [[ ${substep} == "reproducibility" ]];
then
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py reproducibility --metadata_pairs ${metadata_pairs} --outdir ${outanalysis} --methods GenomeDISCO --concise_analysis --running_mode sge --parameters_file ${params} --subset_chromosomes chrX
fi
fi
if [[ ${step} == "encode_finalrun_nonhighres_326" ]];
then
metadata_samples=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_2016-12-13/Bulk/AllChrAnon/processed/metadata/metadata.res40000
metadata_pairs=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_2016-12-13/Bulk/AllChrAnon/processed/metadata/metadata.res40000.pairs
nodes=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_2016-12-13/Bulk/AllChrAnon/processed/nodes/Nodes.w40000.bed.gz
outanalysis=/ifs/scratch/oursu/paper_2017-12-20/encode_nonhighres.final
mkdir -p ${outanalysis}
params=${outanalysis}/params
cat ${MYCODE}/3DChromatin_ReplicateQC/examples/example_parameters.txt | sed 's/10G/5G/g' > ${params}
cat ${params}
if [[ ${substep} == "split" ]];
then
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py split --running_mode sge --metadata_samples ${metadata_samples} --bins ${nodes} --outdir ${outanalysis} --parameters_file ${params} --methods GenomeDISCO --subset_chromosomes chrX
fi
if [[ ${substep} == "reproducibility" ]];
then
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py reproducibility --metadata_pairs ${metadata_pairs} --outdir ${outanalysis} --methods GenomeDISCO --concise_analysis --running_mode sge --parameters_file ${params}
fi
if [[ ${substep} == "format_scores" ]];
then
cat ${outanalysis}/results/reproducibility/GenomeDISCO/M*txt | sort | uniq > ${outanalysis}/results/compiled_scores.txt
results=${outanalysis}/results/reproducibility/GenomeDISCO
compiled=${outanalysis}/results/compiled_scores.txt
for f in $(ls ${results}/chr*);do awk -v myfile=$(basename ${f}) '{print myfile"\t"$0}' $f | sed 's/.scores.txt//g' | awk '{gsub("[.]","\t",$1)}1' | awk '{print $5"\t"$6"\t"$1"\t"$7}' >> ${compiled};done
echo ${outanalysis}/results/compiled_scores.txt
${mypython} /srv/gsfs0/projects/kundaje/users/oursu/code/3DChromatin_ReplicateQC/software/genomedisco/paper_analysis/2017-12-20/arrange_encode_scores.py --metadata_pairs ${metadata_pairs} --scoring_file ${outanalysis}/results/compiled_scores.txt --out ${outanalysis}/results/encode_nonhighres.326comparisons.2018_01_30.txt
echo ${outanalysis}/results/encode_nonhighres.326comparisons.2018_01_30.txt
fi
fi
if [[ ${step} == "encode_finalrun_highres" ]];
then
for res in 10000 40000 500000;
do
metadata_samples=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_highres/AllChrAnon/processed/metadata/metadata.res${res}
metadata_pairs=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_highres/AllChrAnon/processed/metadata/metadata.res${res}.pairs
nodes=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_highres/AllChrAnon/processed/nodes/Nodes.w${res}.bed.gz
outanalysis=/ifs/scratch/oursu/paper_2017-12-20/encode_highres.final/res${res}
mkdir -p ${outanalysis}
params=${outanalysis}/params
cat ${MYCODE}/3DChromatin_ReplicateQC/examples/example_parameters.txt | sed 's/10G/100G/g' > ${params}
cat ${params}
if [[ ${substep} == "format_scores" ]];
then
${mypython} /srv/gsfs0/projects/kundaje/users/oursu/code/3DChromatin_ReplicateQC/software/genomedisco/paper_analysis/2017-12-20/arrange_encode_scores.py --metadata_pairs ${metadata_pairs} --scoring_file ${outanalysis}/results/compiled_scores.txt --out ${outanalysis}/results/encode_highres.res${res}.2018_01_30.txt
echo ${outanalysis}/results/encode_highres.res${res}.2018_01_30.txt
fi
if [[ ${substep} == "split" ]];
then
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py split --running_mode sge --metadata_samples ${metadata_samples} --bins ${nodes} --outdir ${outanalysis} --parameters_file ${params} --methods GenomeDISCO
fi
if [[ ${substep} == "reproducibility" ]];
then
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py reproducibility --metadata_pairs ${metadata_pairs} --outdir ${outanalysis} --methods GenomeDISCO --concise_analysis --running_mode sge --parameters_file ${params}
fi
if [[ ${substep} == "leftovers2" ]];
then
for chromosome in 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 X;
do
old_script=/ifs/scratch/oursu/paper_2017-12-20/encode_highres.final/res40000/scripts/GenomeDISCO/Matrix55.Matrix8.sh
new_script=${old_script}.${chromosome}.sh
rm ${new_script}
echo ". /srv/gsfs0/projects/kundaje/users/oursu/code/3DChromatin_ReplicateQC/configuration_files/bashrc.configuration" >> ${new_script}
cat ${old_script} | grep -w "chr${chromosome}" | grep mypython >> ${new_script}
echo "============="
cat ${new_script}
chmod 755 ${new_script}
qsub -l h_vmem=10G -o ${new_script}.o -e ${new_script}.e ${new_script}
done
fi
if [[ ${substep} == "run_leftovers" ]];
then
for mpair in $(cat ${outanalysis}/results/reproducibility/GenomeDISCO/M*txt | cut -f1,2 | awk '{print $1".vs."$2}' | sort | uniq);
do
chromos=$(cat ${outanalysis}/results/reproducibility/GenomeDISCO/${mpair}.txt | wc -l | awk '{print $1}')
echo ${chromos}
if [[ ${chromos} != "23" ]];
then
echo ${mpair}
echo $(cat ${outanalysis}/results/reproducibility/GenomeDISCO/${mpair}.txt | cut -f3)
for chromosome in 2 3 4 5 6 7 8 9 X;
do
old_script=${outanalysis}/scripts/GenomeDISCO/$(echo ${mpair} | sed 's/[.]vs//g').sh
new_script=${old_script}.${chromosome}.sh
rm ${new_script}
echo ". /srv/gsfs0/projects/kundaje/users/oursu/code/3DChromatin_ReplicateQC/configuration_files/bashrc.configuration" >> ${new_script}
cat ${old_script} | grep -w "chr${chromosome}" | grep mypython >> ${new_script}
echo "============="
cat ${new_script}
chmod 755 ${new_script}
qsub -l h_vmem=100G -o ${new_script}.o -e ${new_script}.e ${new_script}
done
fi
done
fi
if [[ ${substep} == "compile_scores" ]];
then
results=${outanalysis}/results/reproducibility/GenomeDISCO
compiled=${outanalysis}/results/compiled_scores.txt
rm ${compiled}
for f in $(ls ${results}/chr*);do awk -v myfile=$(basename ${f}) '{print myfile"\t"$0}' $f | sed 's/.scores.txt//g' | awk '{gsub("[.]","\t",$1)}1' | awk '{print $5"\t"$6"\t"$1"\t"$7}' >> ${compiled};done
cat ${results}/M*txt >> ${compiled}
cat ${compiled} | sort | uniq > ${compiled}2
mv ${compiled}2 ${compiled}
#cat ${compiled}
echo ${compiled}
fi
done
fi
if [[ ${step} == "running_time_encode_40kb_chr21" ]];
then
metadata_samples=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_2016-12-13/Bulk/AllChrAnon/processed/metadata/metadata.res40000
metadata_pairs=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_2016-12-13/Bulk/AllChrAnon/processed/metadata/metadata.res40000.pairs
nodes=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_2016-12-13/Bulk/AllChrAnon/processed/nodes/Nodes.w40000.bed.gz
outanalysis=/ifs/scratch/oursu/encode_nonhighres/running_times_res40000_by_chromo_chr21
chromo=chr21
mkdir -p ${outanalysis}
params=${outanalysis}/params
cat ${MYCODE}/3DChromatin_ReplicateQC/examples/example_parameters.txt | sed 's/10G/20G -l hostname=scg4-h17*/g' > ${params}
cat ${params}
echo ${params}
if [[ ${substep} == "split" ]];
then
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py split --running_mode sge --metadata_samples ${metadata_samples} --bins ${nodes} --outdir ${outanalysis} --parameters_file ${params} --methods GenomeDISCO,HiCRep,HiC-Spector,QuASAR-Rep --subset_chromosomes ${chromo}
fi
if [[ ${substep} == "reproducibility" ]];
then
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py reproducibility --metadata_pairs ${metadata_pairs} --outdir ${outanalysis} --methods QuASAR-Rep --timing --subset_chromosomes ${chromo} --concise_analysis --running_mode write_scripts
fi
if [[ ${substep} == "timing_analysis" ]];
then
chromo=chr21
cd ${outanalysis}/timing
echo ${outanalysis}
for timetype in real user sys;
do
rm ${outanalysis}/timings.${timetype}
for method in GenomeDISCO HiCRep HiC-Spector ;do for f in $(ls ${method}/*${chromo}.*txt);do awk -v m=${method} '{print m"\t"FILENAME"\t"$0}' ${f} | grep ${timetype} | sed 's/\///g' | awk '{gsub(/\./,"\t",$2)}1' | grep -v site | grep -v File | awk '{print $1"\t"$3"\t"$4"\t"$5"\t"$9}' | awk '{gsub("m","\t",$5)}1' | awk '{gsub("s","",$5)}1' | awk '{t=(60*$5)+$6}{print $1"\t"$2"\t"$3"\t"$4"\t"t}' >>${outanalysis}/timings.${timetype};done;done
#do quasar
for f in $(ls QuASAR-Rep/*txt);
do
awk '{print "QuASAR-Rep\t"FILENAME"\t"$0}' ${f} |grep ${timetype} | sed 's/\///g' | awk '{gsub(/\./,"\t",$2)}1' | grep -v site | grep -v File | awk '{print $1"\tchr21\t"$3"\t"$4"\t"$8}' | awk '{gsub("m","\t",$5)}1' | awk '{gsub("s","",$5)}1' | awk '{t=(60*$5)+$6}{print $1"\t"$2"\t"$3"\t"$4"\t"t}' >>${outanalysis}/timings.${timetype}
done
cat ${outanalysis}/timings.${timetype} | sort | uniq > ${outanalysis}/timings.${timetype}.uniq
mv ${outanalysis}/timings.${timetype}.uniq ${outanalysis}/timings.${timetype}
echo ${outanalysis}/timings.${timetype}
module load R/3.4.1
Rscript /srv/gsfs0/projects/kundaje/users/oursu/code/plot_running_time.R ${outanalysis}/timings.${timetype} ${outanalysis}/timings.${timetype}.pdf
done
fi
fi
if [[ ${step} == "running_time_encode_40kb" ]];
then
metadata_samples=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_2016-12-13/Bulk/AllChrAnon/processed/metadata/metadata.res40000
metadata_pairs=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_2016-12-13/Bulk/AllChrAnon/processed/metadata/metadata.res40000.pairs
nodes=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_2016-12-13/Bulk/AllChrAnon/processed/nodes/Nodes.w40000.bed.gz
outanalysis=/ifs/scratch/oursu/encode_nonhighres/running_times_res40000_by_chromo
chromo=chr1
params=${outanalysis}/params
cat ${MYCODE}/3DChromatin_ReplicateQC/examples/example_parameters.txt | sed 's/10G/50G/g' > ${params}
cat ${params}
echo ${params}
if [[ ${substep} == "split" ]];
then
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py split --running_mode sge --metadata_samples ${metadata_samples} --bins ${nodes} --outdir ${outanalysis} --parameters_file ${params}
fi
if [[ ${substep} == "reproducibility" ]];
then
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py reproducibility --running_mode sge --metadata_pairs ${metadata_pairs} --outdir ${outanalysis} --methods GenomeDISCO --timing --concise_analysis
fi
if [[ ${substep} == "timing_analysis" ]];
then
chromo=chr21
cd ${outanalysis}/timing
for timetype in real user sys;
do
rm ${outanalysis}/timings.${chromo}
for method in GenomeDISCO HiCRep HiC-Spector ;do for f in $(ls ${method}/*${chromo}.*txt);do awk -v m=${method} '{print m"\t"FILENAME"\t"$0}' ${f} | grep ${timetype} | sed 's/\///g' | awk '{gsub(/\./,"\t",$2)}1' | grep -v site | grep -v File | awk '{print $1"\t"$3"\t"$4"\t"$5"\t"$9}' | awk '{gsub("m","\t",$5)}1' | awk '{gsub("s","",$5)}1' | awk '{t=(60*$5)+$6}{print $1"\t"$2"\t"$3"\t"$4"\t"t}' >>${outanalysis}/timings.${timetype};done;done
#do quasar
#for f in $(ls ${method}/*${chromo}.*txt)
cat ${outanalysis}/timings.${timetype}
echo ${outanalysis}/timings.${timetype}
module load R/3.4.1
Rscript /srv/gsfs0/projects/kundaje/users/oursu/code/plot_running_time.R ${outanalysis}/timings.${timetype} ${outanalysis}/timings.${timetype}.pdf
done
fi
fi
if [[ ${step} == "running_time_encode" ]];
then
for res in 10000 40000 500000;
do
metadata_samples=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_highres/AllChrAnon/processed/metadata/metadata.res${res}
metadata_pairs=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_highres/AllChrAnon/processed/metadata/metadata.res${res}.pairs
nodes=/srv/gsfs0/projects/kundaje/users/oursu/3d/encode_highres/AllChrAnon/processed/nodes/Nodes.w${res}.bed.gz
outanalysis=/ifs/scratch/oursu/encode_highres/running_times_res${res}
chromo=chr21
if [[ ${substep} == "split" ]];
then
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py split --running_mode sge --metadata_samples ${metadata_samples} --bins ${nodes} --outdir ${outanalysis} --subset_chromosomes ${chromo}
fi
if [[ ${substep} == "reproducibility" ]];
then
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py reproducibility --running_mode sge --metadata_pairs ${metadata_pairs} --outdir ${outanalysis} --subset_chromosomes chr21 --timing
fi
#rm test;for method in $(ls);do for f in $(ls ${method}/*txt);do awk -v m=${method} '{print m"\t"FILENAME"\t"$0}' ${f} | grep user | grep -v site | grep -v File | sed 's/0m//g' | sed 's/s$//g'>>test;done;done
done
fi
if [[ ${step} == "setup_folder" ]];
then
mkdir -p ${DATA}
mkdir -p ${DATA}/data
cp /srv/gsfs0/projects/kundaje/commonRepository/annotations/human/hg19.GRCh37/genomeSize/hg19.genome ${chrSizes}
cp /srv/gsfs0/projects/snyder/oursu/software/git/public_genomedisco/genomedisco/paper_analysis/2017-06-08/real/LA_metadata.txt ${DATA}/data/
fi
if [[ ${step} == "install_code" ]];
then
#3DChromatin_ReplicateQC
cd ${MYCODE}
git clone http://github.com/kundajelab/3DChromatin_ReplicateQC
cd 3DChromatin_ReplicateQC
install_scripts/install_3DChromatin_ReplicateQC.sh --pathtopython /srv/gsfs0/projects/kundaje/users/oursu/code/anaconda2/mypython/bin/python --pathtor R --rlib /srv/gsfs0/projects/kundaje/users/oursu/code/Rlibs --pathtobedtools bedtools --modules R/3.4.1,bedtools/2.26.0
#for hic file extraction
mkdir -p ${MYCODE}/juicer_tools
cd ${MYCODE}/juicer_tools
wget http://hicfiles.tc4ga.com.s3.amazonaws.com/public/juicer/juicer_tools.1.7.5_linux_x64_jcuda.0.8.jar
#genome_utils
git clone https://github.com/oursu/genome_utils
#macs2
/srv/gsfs0/projects/kundaje/users/oursu/code/anaconda2/mypython/bin/pip install MACS2
fi
if [[ ${step} == "get_Rao_data" ]];
then
if [[ ${substep} == "hic_files" ]];
then
mkdir -p ${DATA}/Rao_data/hic
mv /ifs/scratch/oursu/data/hic/* ${DATA}/Rao_data/hic/
for f in $(ls ${DATA}/Rao_data/hic/*gz);
do
gunzip $f
done
fi
if [[ ${substep} == "individual_reads" ]];
then
mkdir -p ${DATA}/Rao_data/counts
mv /srv/gsfs0/projects/kundaje/users/oursu/3d/LA/merged_nodups/data/* ${DATA}/Rao_data/counts/
fi
fi
if [[ ${step} == "Rao" ]];
then
if [[ ${substep} == "resolutions_hic_files" ]];
then
for f in $(ls ${DATA}/Rao_data/hic/*hic);
do
s=${DATA}/Rao_data/hic/split_$(basename ${f}).sh
echo "module load java/latest" > ${s}
for res in $(echo ${resolutions} | sed 's/,/ /g');
do
mkdir -p ${DATA}/Rao_data/hic/res${res}
for chromo in $(echo "1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,X" | sed 's/,/ /g');
do
out=${DATA}/Rao_data/hic/res${res}/$(basename ${f}).res${res}.chr${chromo}.gz
echo "/usr/java/latest/bin/java -jar ${MYCODE}/juicer_tools/juicer_tools.1.7.5_linux_x64_jcuda.0.8.jar dump observed NONE ${f} ${chromo} ${chromo} BP ${res} ${out}.f" >> ${s}
echo "zcat -f ${out}.f | awk -v chromosome=${chromo} '{print chromosome\"\t\""'$'"1\"\t\"chromosome\"\t\""'$'"2\"\t\""'$'"3}' | gzip > ${out}" >> ${s}
echo "rm ${out}.f" >> ${s}
done
done
chmod 755 ${s}
$s
done
#do the gm separately
for chromo in $(echo "1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,X" | sed 's/,/ /g');
do
echo ${chromo}
zcat -f ${DATA}/Rao_data/hic/GM12878_combined/10kb_resolution_intrachromosomal/chr${chromo}/MAPQGE30/chr${chromo}_10kb.RAWobserved | awk -v chromosome=${chromo} '{print chromosome"\t"$1"\t"chromosome"\t"$2"\t"$3}' | gzip > ${DATA}/Rao_data/hic/res10000/GM12878_combined.res10000.chr${chromo}.gz
done
for chromo in $(echo "1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,X" | sed 's/,/ /g');
do
echo ${chromo}
zcat -f ${DATA}/Rao_data/hic/GM12878_combined/50kb_resolution_intrachromosomal/chr${chromo}/MAPQGE30/chr${chromo}_50kb.RAWobserved | awk -v chromosome=${chromo} '{print chromosome"\t"$1"\t"chromosome"\t"$2"\t"$3}' | gzip > ${DATA}/Rao_data/hic/res50000/GM12878_combined.res50000.chr${chromo}.gz
done
for chromo in $(echo "1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,X" | sed 's/,/ /g');
do
echo ${chromo}
zcat -f ${DATA}/Rao_data/hic/GM12878_combined/500kb_resolution_intrachromosomal/chr${chromo}/MAPQGE30/chr${chromo}_500kb.RAWobserved | awk -v chromosome=${chromo} '{print chromosome"\t"$1"\t"chromosome"\t"$2"\t"$3}' | gzip > ${DATA}/Rao_data/hic/res500000/GM12878_combined.res500000.chr${chromo}.gz
done
for cellline in GM12878_combined HMEC HUVEC IMR90 K562 KBM7 NHEK;
do
echo ${cellline}
for res in $(echo ${resolutions} | sed 's/,/ /g');
do
zcat -f ${DATA}/Rao_data/hic/res${res}/*${cellline}*chr*gz | gzip > ${DATA}/Rao_data/hic/res${res}/${cellline}.res${res}.gz
done
done
fi
if [[ ${substep} == "resolutions_reads_files" ]];
then
for f in $(ls ${DATA}/Rao_data/counts/*gz);
do
for res in $(echo ${resolutions} | sed 's/,/ /g');
do
mkdir -p ${DATA}/Rao_data/counts/res${res}
#once for the whole genome
out=${DATA}/Rao_data/counts/res${res}/$(basename ${f} | sed 's/_merged_nodups[.]txt[.]gz[.]//g' | sed 's/_/\t/g' | cut -f2).res${res}.gz
s=${out}.sh
echo ${out}
echo "${MYCODE}/genome_utils/3Dutils/LA_reads_to_n1n2value_bins.sh ${f} ${out} ${MAPQ} intra ${res}" > ${s}
echo "rm ${s}" >> ${s}
chmod 755 ${s}
qsub -o ${s}.o -e ${s}.e ${s}
done
done
fi
fi
if [[ ${step} == "Rao_metadata" ]];
then
for res in $(echo ${resolutions} | sed 's/,/ /g');
do
#metadata samples
mkdir -p ${DATA}/results/metadata
metadata_samples=${DATA}/results/metadata/metadata.samples.res${res}
rm ${metadata_samples}
for dataset_number in {1..83};
do
dataset="HIC"$(echo "00${dataset_number}" | sed 's/.*\(...\)/\1/')
echo "${dataset}delim${DATA}/Rao_data/counts/res${res}/${dataset}.res${res}.gz" | sed 's/delim/\t/g' >> ${metadata_samples}
done
#metadata pairs
metadata_pairs=${DATA}/results/metadata/metadata.pairs.res${res}
rm ${metadata_pairs}*
#odds
for data1 in $(zcat -f ${metadata_samples} | cut -f1 | sed -n 'p;n');
do
for data2 in $(zcat -f ${metadata_samples} | cut -f1 | sed -n 'p;n');
do
echo "${data1}delim${data2}" | sed 's/delim/\t/g' >> ${metadata_pairs}.tmp
done
done
#evens
for data1 in $(zcat -f ${metadata_samples} | cut -f1 | sed -n 'n;p');
do
for data2 in $(zcat -f ${metadata_samples} | cut -f1 | sed -n 'n;p');
do
echo "${data1}delim${data2}" | sed 's/delim/\t/g' >> ${metadata_pairs}.tmp
done
done
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/software/genomedisco/genomedisco/scripts/orderpairs.py --file ${metadata_pairs}.tmp --out ${metadata_pairs}.tmp2
cat ${metadata_pairs}.tmp2 | sort | uniq | awk '{if ($1!=$2) print $0}' > ${metadata_pairs}
rm ${metadata_pairs}.tmp*
echo ${metadata_pairs}
done
fi
if [[ ${step} == "bins" ]];
then
source ${MYCODE}/3DChromatin_ReplicateQC/configuration_files/bashrc.configuration
for res in $(echo ${resolutions} | sed 's/,/ /g');
do
mkdir -p ${DATA}/results/bins
bedtools makewindows -w ${res} -g ${chrSizes} | awk '{print $1"\t"$2"\t"$3"\t"$2}' | gzip > ${DATA}/results/bins/bins.res${res}.gz
done
fi
if [[ ${step} == "Rao_runs" ]];
then
for res in 50000; #$(echo ${resolutions} | sed 's/,/ /g');
do
out=${DATA}/results/rao/res${res}
bins=${DATA}/results/bins/bins.res${res}.gz
metadata_samples=${DATA}/results/metadata/metadata.samples.res${res}
metadata_pairs=${DATA}/results/metadata/metadata.pairs.res${res}
if [[ ${substep} == "split_final" ]];
then
out=${out}.final
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py split --metadata_samples ${metadata_samples} --bins ${bins} --outdir ${out} --methods GenomeDISCO,HiCRep,HiC-Spector --running_mode sge
fi
if [[ ${substep} == "split" ]];
then
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py split --metadata_samples ${metadata_samples} --bins ${bins} --outdir ${out} --methods GenomeDISCO,HiCRep,HiC-Spector --running_mode sge
fi
if [[ ${substep} == "split_transition" ]];
then
out=${DATA}/results/rao/res${res}.keepDiag.transition
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py split --metadata_samples ${metadata_samples} --bins ${bins} --outdir ${out} --methods GenomeDISCO,HiCRep,HiC-Spector --running_mode sge
fi
if [[ ${substep} == "run_final" ]];
then
out=${DATA}/results/rao/res${res}.final
params=${out}/params
cat ${MYCODE}/3DChromatin_ReplicateQC/examples/example_parameters.txt | sed 's/GenomeDISCO|scoresByStep\tno/GenomeDISCO|scoresByStep\tyes/g' | sed 's/tmin\t3/tmin\t1/g' | sed 's/tmax\t3/tmax\t5/g' | sed 's/10G/50G/g' > ${params}
cat ${params}
echo ${params}
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py reproducibility --metadata_pairs ${metadata_pairs} --outdir ${out} --methods GenomeDISCO --concise_analysis --running_mode sge --parameters_file ${params} --timing
fi
if [[ ${substep} == "split_genomedisco_paper" ]];
then
out=${DATA}/results/rao/res${res}.final.fortiming
mkdir -p ${out}
echo ${out}
echo "cp -r ${DATA}/results/rao/res${res}.final/data ${out}/"
fi
if [[ ${substep} == "timing_genomedisco_paper" ]];
then
chromo=chr21
out=${DATA}/results/rao/res${res}.final.fortiming
params=${out}/params
cat ${MYCODE}/3DChromatin_ReplicateQC/examples/example_parameters.txt | sed 's/GenomeDISCO|scoresByStep\tno/GenomeDISCO|scoresByStep\tyes/g' | sed 's/tmin\t3/tmin\t1/g' | sed 's/tmax\t3/tmax\t5/g' | sed 's/10G/50G/g' > ${params}
cat ${params}
echo ${params}
echo "${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py reproducibility --metadata_pairs ${metadata_pairs} --outdir ${out} --methods GenomeDISCO --concise_analysis --parameters_file ${params} --timing "
fi
if [[ ${substep} == "timing_genomedisco_paper_timing" ]];
then
outanalysis=${DATA}/results/rao/res${res}.final.fortiming
cd ${outanalysis}/timing
for timetype in real user sys;
do
echo $timetype
rm ${outanalysis}/timings.${timetype}
for method in GenomeDISCO HiCRep HiC-Spector ;do for f in $(ls ${method}/*${chromo}.*txt);do awk -v m=${method} '{print m"\t"FILENAME"\t"$0}' ${f} | grep ${timetype} | sed 's/\///g' | awk '{gsub(/\./,"\t",$2)}1' | grep -v site | grep -v File | awk '{print $1"\t"$3"\t"$4"\t"$5"\t"$9}' | awk '{gsub("m","\t",$5)}1' | awk '{gsub("s","",$5)}1' | awk '{t=(60*$5)+$6}{print $1"\t"$2"\t"$3"\t"$4"\t"t}' >>${outanalysis}/timings.${timetype};done;done
cat ${outanalysis}/timings.${timetype} | sort | uniq | grep -v chrY > ${outanalysis}/timings.${timetype}.uniq
mv ${outanalysis}/timings.${timetype}.uniq ${outanalysis}/timings.${timetype}
cat ${outanalysis}/timings.${timetype}
echo ${outanalysis}/timings.${timetype}
module load R/3.4.1
echo "Rscript /srv/gsfs0/projects/kundaje/users/oursu/code/plot_running_time_genomewide.R ${outanalysis}/timings.${timetype} ${outanalysis}/timings.${timetype}.pdf"
done
fi
if [[ ${substep} == "run" ]];
then
echo "here"
echo ${metadata_pairs}
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py reproducibility --metadata_pairs ${metadata_pairs} --outdir ${out} --methods GenomeDISCO --parameters_file ${MYCODE}/3DChromatin_ReplicateQC/examples/example_parameters.bystep.txt --subset_chromosomes chr2 --concise_analysis --running_mode sge #--parameters_file ${MYCODE}/3DChromatin_ReplicateQC/examples/example_parameters.bystep.10steps.transition.txt
fi
if [[ ${substep} == "run_transition" ]];
then
out=${DATA}/results/rao/res${res}.keepDiag.transition
echo ${metadata_pairs}
${mypython} ${MYCODE}/3DChromatin_ReplicateQC/3DChromatin_ReplicateQC.py reproducibility --metadata_pairs ${metadata_pairs} --outdir ${out} --methods GenomeDISCO --subset_chromosomes chr21 --concise_analysis --running_mode sge --parameters_file ${MYCODE}/3DChromatin_ReplicateQC/examples/example_parameters.bystep.10steps.transition.txt
fi
if [[ ${substep} == "compile_scores_final" ]];
then
echo "here"
d=${DATA}/results/rao/res${res}.final
mkdir -p ${d}/compiled_scores
scores_genomedisco_multiple_t=""
scores_genomedisco=""
scores_hicrep=""
scores_hicspector=""
for chromo in 22 21 20 19 18 17 16 15 14 13 12 11 10 9 8 7 6 5 4 3 2 1 X;
do
echo ${chromo}
zcat -f ${d}/results/reproducibility/GenomeDISCO/chr${chromo}.*.scoresByStep.txt | awk -v chromosome=${chromo} '{print "chr"chromosome"\t"$0}' | grep -v m1 > ${d}/compiled_scores/chr${chromo}.GenomeDISCO.scores.multiple_t.txt
zcat -f ${d}/results/reproducibility/GenomeDISCO/chr${chromo}.*.scoresByStep.txt | awk -v chromosome=${chromo} '{print "chr"chromosome"\t"$1"\t"$2"\t"$5}' | grep -v m1 > ${d}/compiled_scores/chr${chromo}.GenomeDISCO.scores.txt
zcat -f ${d}/results/reproducibility/HiCRep/*.txt | grep -w "chr${chromo}" | cut -f1,2,4 | awk -v chromosome=${chromo} '{print "chr"chromosome"\t"$1"\t"$2"\t"$3}' > ${d}/compiled_scores/chr${chromo}.HiCRep.scores.txt
zcat -f ${d}/results/reproducibility/HiC-Spector/*.txt | grep -w "chr${chromo}" | cut -f1,2,4| awk -v chromosome=${chromo} '{print "chr"chromosome"\t"$1"\t"$2"\t"$3}' > ${d}/compiled_scores/chr${chromo}.HiC-Spector.scores.txt
scores_genomedisco_multiple_t=${scores_genomedisco_multiple_t}" "${d}/compiled_scores/chr${chromo}.GenomeDISCO.scores.multiple_t.txt
scores_genomedisco=${scores_genomedisco}" "${d}/compiled_scores/chr${chromo}.GenomeDISCO.scores.txt
scores_hicrep=${scores_hicrep}" "${d}/compiled_scores/chr${chromo}.HiCRep.scores.txt