Newer
Older
#!/bin/bash
#SBATCH --cpus-per-task=1
#SBATCH --mem=16GB
#SBATCH --time=24:00:00
#SBATCH --job-name=process_trio
#SBATCH --output=process_trio.%A_%a.out
#SBATCH --error=process_trio.%A_%a.err
# setup PATH
export PATH=$PATH:/home/u035/u035/shared/software/bcbio/anaconda/envs/python2/bin:/home/u035/u035/shared/software/bcbio/anaconda/bin
export PERL5LIB=$PERL5LIB:/home/u035/u035/shared/software/bcbio/anaconda/lib/site_perl/5.26.2
### folder structure for the downstream analysis - created by trio_setup.sh ###
BASE=/home/u035/u035/shared/analysis/work
WORK_DIR=$BASE/${PROJECT_ID}
VCF_DIR=${WORK_DIR}/VCF
PED_DIR=${WORK_DIR}/PED
LOG_DIR=${WORK_DIR}/LOG
G2P_DIR=${WORK_DIR}/G2P
VASE_DIR=${WORK_DIR}/VASE
COV_DIR=${WORK_DIR}/COV
DEC_DIR=${WORK_DIR}/DECIPHER
IGV_DIR=${DEC_DIR}/IGV
CNV_DIR=${WORK_DIR}/CNV
BAMOUT_DIR=${WORK_DIR}/BAMOUT
SCRIPTS_DIR=/home/u035/u035/shared/scripts
# other files to be used
FAMILY_IDS=${WORK_DIR}/FAM_IDs.txt # created by trio_setup.sh
CHILD_IDS=${WORK_DIR}/PRO_IDs.txt # created by trio_setup.sh
TARGETS=/home/u035/u035/shared/resources/G2P/DDG2P.20220113.plus15bp.merged.bed # OK
CLINVAR=/home/u035/u035/shared/resources/G2P/DDG2P.20220113.clinvar.20220109.plus15bp.txt # OK
BLACKLIST=/home/u035/u035/shared/resources/blacklist/current_blacklist.txt # OK
TRANS_MAP=/home/u035/u035/shared/resources/trans_map/current_trans_map.txt # OK
REC_SNP=/home/u035/u035/shared/resources/reccurent/current_reccurent.bed # OK, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7116826/, Extended Data Table 1
### TOOLS ###
SAMTOOLS=/home/u035/u035/shared/software/bcbio/anaconda/bin/samtools
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
BCFTOOLS=/home/u035/u035/shared/software/bcbio/anaconda/envs/python2/bin/bcftools
BGZIP=/home/u035/u035/shared/software/bcbio/anaconda/envs/python2/bin/bgzip
TABIX=/home/u035/u035/shared/software/bcbio/anaconda/envs/python2/bin/tabix
VT=/home/u035/u035/shared/software/bcbio/anaconda/bin/vt
VASE=/home/u035/u035/shared/software/bcbio/anaconda/bin/vase
GATK4=/home/u035/u035/shared/software/bcbio/anaconda/bin/gatk # points to ../share/gatk4-4.2.1.0-0/gatk
GATK3=/home/u035/u035/shared/software/GenomeAnalysisTK-3.8/GenomeAnalysisTK.jar
PYTHON3=/home/u035/u035/shared/software/bcbio/anaconda/bin/python3 # points to python3.6
PYTHON2=/home/u035/u035/shared/software/bcbio/anaconda/envs/python2/bin/python2.7
VEP="/home/u035/u035/shared/software/bcbio/anaconda/bin/perl /home/u035/u035/shared/software/bcbio/anaconda/bin/vep" # points to ../share/ensembl-vep-100.4-0/vep
REFERENCE_GENOME=/home/u035/u035/shared/software/bcbio/genomes/Hsapiens/hg38/seq/hg38.fa
echo "SOURCE_DIR = ${SOURCE_DIR}" # the general path to the source BAM files (VCF and PED already copied) i.e. /home/u035/u035/shared/results
echo "BATCH_ID = ${BATCH_ID}" # the ID of the batch being processed e.g. 19650_Ansari_Morad
echo "BATCH_NUM = ${BATCH_NUM}" # the numerical part of the BATCH_ID e.g. 19650
echo "PLATE_ID = ${PLATE_ID}" # the PCR plate ID of the batch being currently processed, e.g. 19285
echo "PROJECT_ID = ${PROJECT_ID}" # this the the folder (${BASE}/${PROJECT_ID}) where the downstream analysis will be done
echo "VERSION_N = ${VERSION_N}" # the version of the alignment and genotyping analysis
# change to the LOG folder
cd ${LOG_DIR}
################################
##### for each family ####
################################
#~#FAMILY_ID=`head -n ${PBS_ARRAY_INDEX} ${FAMILY_IDS} | tail -n 1`
FAMILY_ID=`head -n ${SLURM_ARRAY_TASK_ID} ${FAMILY_IDS} | tail -n 1`
########################################################################
### DNU and clean the each family VCF ###
### format: ${PLATE_ID}_${FAMILY_ID}-gatk-haplotype-annotated.vcf.gz ###
########################################################################
echo "Performing DNU and cleaning of the ${PLATE_ID}_${FAMILY_ID}'s VCF file..."
time ${VT} decompose -s ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}-gatk-haplotype-annotated.vcf.gz -o ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.decomp.vcf.gz
time ${VT} normalize ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.decomp.vcf.gz -r ${REFERENCE_GENOME} -o ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.norm.vcf.gz
time ${VT} uniq ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.norm.vcf.gz -o ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.DNU.vcf.gz
# remove sites with AC=0
time ${BCFTOOLS} view --min-ac=1 --no-update ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.DNU.vcf.gz > ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.AC0.vcf
# reset GT to no-call if num_ALT < num_ALT_THERSH or VAF < VAF_THRESH and GT != 0/0
# exlude variants from the blacklist (matching on chr,pos,ref,alt)
time ${PYTHON2} ${SCRIPTS_DIR}/filter_LQ_GT.py ${BLACKLIST} ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.AC0.vcf ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.clean.vcf
# bgzip and tabix it
time cat ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.clean.vcf | ${BGZIP} > ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.ready.vcf.gz
time ${TABIX} -p vcf ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.ready.vcf.gz
# delete intermediate files
rm ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}-gatk-haplotype-annotated.vcf.gz
rm ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.decomp.vcf.gz*
rm ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.norm.vcf.gz*
rm ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.DNU.vcf.gz*
rm ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.AC0.vcf
# to avoid bgzip pipe broken annoying, but not problematic message - skip the next step, the file will be used by G2P as IN_FILE and will be deleted last
# rm ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.clean.vcf
echo ""
echo ""
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo "DNU, AC=0, num_ALT & VAF & blacklist cleaning and of the ${PLATE_ID}_${FAMILY_ID}'s VCF file: done"
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo ""
echo ""
###########################################################
### run G2P for each family VCF (DD genes) ###
### format: ${PLATE_ID}_${FAMILY_ID}.clean.vcf ###
###########################################################
echo "Performing G2P analysis (DD genes)for FAMILY_ID = ${PLATE_ID}_${FAMILY_ID}..."
echo "Using ${TARGETS}"
IN_FILE=${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.clean.vcf
G2P_LOG_DIR=${G2P_DIR}/${PLATE_ID}_${FAMILY_ID}_LOG_DIR
mkdir ${G2P_LOG_DIR}
TXT_OUT=${G2P_LOG_DIR}/${PLATE_ID}_${FAMILY_ID}.report.txt
HTML_OUT=${G2P_LOG_DIR}/${PLATE_ID}_${FAMILY_ID}.report.html
VCF_KEYS='gnomADe_r2.1.1_GRCh38|gnomADg_r3.1.1_GRCh38'
time ${VEP} \
-i ${IN_FILE} \
--output_file ${G2P_LOG_DIR}/${PLATE_ID}_${FAMILY_ID}_inter_out.txt \
--force_overwrite \
--assembly GRCh38 \
--fasta ${REFERENCE_GENOME} \
--offline \
--merged \
--use_given_ref \
--cache --cache_version 100 \
--dir_cache /home/u035/u035/shared/software/bcbio/genomes/Hsapiens/hg38/vep \
--individual all \
--transcript_filter "gene_symbol in /home/u035/u035/shared/resources/G2P/genes_in_DDG2P.20220113.txt" \
--dir_plugins /home/u035/u035/shared/software/bcbio/anaconda/share/ensembl-vep-100.4-0 \
--plugin G2P,file='/home/u035/u035/shared/resources/G2P/DDG2P.20220113.csv',af_from_vcf=1,confidence_levels='definitive&strong',af_from_vcf_keys=${VCF_KEYS},log_dir=${G2P_LOG_DIR},txt_report=${TXT_OUT},html_report=${HTML_OUT}
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
echo ""
echo ""
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo "G2P analysis of FAMILY_ID = ${PLATE_ID}_${FAMILY_ID}: done"
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo ""
echo ""
###########################################################
### run VASE for each family VCF (de novo) ###
### format: ${PLATE_ID}_${FAMILY_ID}.ready.vcf.gz ###
###########################################################
echo "Performing de novo analysis with VASE for FAMILY_ID = ${PLATE_ID}_${FAMILY_ID} ..."
IN_FILE=${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.ready.vcf.gz
OUT_FILE=${VASE_DIR}/${PLATE_ID}_${FAMILY_ID}.strict.denovo.vcf
PED_FILE=${PED_DIR}/${BATCH_ID}_${PLATE_ID}_${FAMILY_ID}.ped
time ${VASE} \
-i ${IN_FILE} \
-o ${OUT_FILE} \
--log_progress \
--prog_interval 100000 \
--freq 0.0001 \
--gq 30 --dp 10 \
--het_ab 0.3 \
--max_alt_alleles 1 \
--csq all \
--biotypes all \
--control_gq 15 --control_dp 5 \
--control_het_ab 0.01 \
--control_max_ref_ab 0.05 \
--de_novo \
--ped ${PED_FILE}
# for the cases where one of the parents is also affected, VASE de novo will crash not being able to find parents for the affected parent
# not producing any output file, which trips the pipeline downstream
# to handle: check if VASE denovo produced an output and if not (as it will be for such cases)
# create an empty VCF headered output == no denovos found)
echo ""
echo ""
if [ -f "${OUT_FILE}" ]; then
echo "VASE denovo completed successfully"
else
echo "WARNING: VASE denovo has not produced an output (e.g. affected parent), generate an empty VCF one (with headers)"
${TABIX} -H ${IN_FILE} > ${OUT_FILE}
fi
echo ""
echo ""
# do some filtering on the denovo VCFs - exclude variants not on the 24 chr, as well as variants in LCR and telomere/centromere regions
### actually, ignore the filtering of variants in LCR and telomere/centromere regions --> more variants with “Unknown” status may be classified as “denovo” if enough support
cd ${VASE_DIR}
# index the denovo VCF
time ${GATK4} IndexFeatureFile -I ${OUT_FILE}
# select only variants on the 24 chromosomes
time ${GATK4} SelectVariants -R ${REFERENCE_GENOME} -V ${OUT_FILE} -O ${PLATE_ID}_${FAMILY_ID}.strict.24chr.denovo.vcf -L /home/u035/u035/shared/resources/24_chr.list --exclude-non-variants
# sort the VCF (maybe not needed?, but just in case, and it is quick)
if [ -f "${PLATE_ID}_${FAMILY_ID}.strict.24chr.sort.denovo.vcf" ]; then
rm ${PLATE_ID}_${FAMILY_ID}.strict.24chr.sort.denovo.vcf
fi
grep '^#' ${PLATE_ID}_${FAMILY_ID}.strict.24chr.denovo.vcf > ${PLATE_ID}_${FAMILY_ID}.strict.24chr.sort.denovo.vcf \
&& grep -v '^#' ${PLATE_ID}_${FAMILY_ID}.strict.24chr.denovo.vcf | LC_ALL=C sort -t $'\t' -k1,1V -k2,2n >> ${PLATE_ID}_${FAMILY_ID}.strict.24chr.sort.denovo.vcf
# index the sorted VCF
time ${GATK4} IndexFeatureFile -I ${PLATE_ID}_${FAMILY_ID}.strict.24chr.sort.denovo.vcf
# split multi-allelic sites [by -m -any]
# left-alignment and normalization [by adding the -f]
file=${PLATE_ID}_${FAMILY_ID}.strict.24chr.sort.denovo.vcf
echo "$file"
${BCFTOOLS} norm -f ${REFERENCE_GENOME} -m -any -Ov -o ${file/.strict.24chr.sort.denovo.vcf/.ready.denovo.vcf} $file
# clean intermediate denovo files
rm ${PLATE_ID}_${FAMILY_ID}.strict.denovo.vcf*
rm ${PLATE_ID}_${FAMILY_ID}.strict.24chr.denovo.vcf*
rm ${PLATE_ID}_${FAMILY_ID}.strict.24chr.sort.denovo.vcf*
# change back to the LOG folder
cd ${LOG_DIR}
echo ""
echo ""
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo "De novo analysis of FAMILY_ID = ${PLATE_ID}_${FAMILY_ID}: done"
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo ""
echo ""
############################################################################################################################################################################################
### run coverage for each proband (DD genes) ###
### format: ${SOURCE_DIR}/${BATCH_NUM}_${VERSION_N}/families/????-??-??_${BATCH_NUM}_${VERSION_N}_${PLATE_ID}_${FAMILY_ID}/${INDI_ID}_${FAMILY_ID}/${INDI_ID}_${FAMILY_ID}-ready.bam ###
############################################################################################################################################################################################
#################################
##### for each proband ####
#################################
#~#PROBAND_ID=`head -n ${PBS_ARRAY_INDEX} ${CHILD_IDS} | tail -n 1` # contains only the proband IDs (e.g. 107060)
PROBAND_ID=`head -n ${SLURM_ARRAY_TASK_ID} ${CHILD_IDS} | tail -n 1` # contains only the proband IDs (e.g. 107060)
echo "Performing coverage analysis for PROBAND_ID = ${PROBAND_ID}_${FAMILY_ID} ..."
# make sure we are reading the data from the exact batch & plate ID
#~#BAM_FILE=${SOURCE_DIR}/????-??-??_${VERSION_N}_${BATCH_ID}_${PLATE_ID}_${FAMILY_ID}/${PROBAND_ID}_${FAMILY_ID}/${PROBAND_ID}_${FAMILY_ID}-ready.bam
BAM_FILE=${SOURCE_DIR}/${BATCH_NUM}_${VERSION_N}/families/????-??-??_${BATCH_NUM}_${VERSION_N}_${PLATE_ID}_${FAMILY_ID}/${PROBAND_ID}_${FAMILY_ID}/${PROBAND_ID}_${FAMILY_ID}-ready.bam
OUT_FILE=${COV_DIR}/${PROBAND_ID}_${FAMILY_ID}.DD15
time java -Xmx8g -jar ${GATK3} -T DepthOfCoverage -R ${REFERENCE_GENOME} -o ${OUT_FILE} -I ${BAM_FILE} -L ${TARGETS} \
--omitDepthOutputAtEachBase \
--minBaseQuality 20 \
--minMappingQuality 20 \
-ct 20 \
-jdk_deflater \
-jdk_inflater \
--allow_potentially_misencoded_quality_scores
echo ""
echo ""
echo "----------------------------------------------------------------------------------------------------"
echo "percentage of DD exons (+/-15bp) covered at least 20x in PROBAND_ID = ${PROBAND_ID}_${FAMILY_ID} ..."
cat ${COV_DIR}/${PROBAND_ID}_${FAMILY_ID}.DD15.sample_summary | awk '{print $7}'
echo "----------------------------------------------------------------------------------------------------"
# now compute the coverage per DD exon (+/-15bp) interval, adding the number of P/LP ClinVar variants (assertion criteria provided) in each interval
time ${PYTHON2} ${SCRIPTS_DIR}/get_cov_output.py ${COV_DIR}/${PROBAND_ID}_${FAMILY_ID}.DD15.sample_interval_summary ${CLINVAR} ${COV_DIR}/${PROBAND_ID}_${FAMILY_ID}.DD15.COV.txt
echo ""
echo ""
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo "Coverage analysis of PROBAND_ID = ${PROBAND_ID}_${FAMILY_ID}: done "
echo " Coverage file = ${COV_DIR}/${PROBAND_ID}_${FAMILY_ID}.DD15.COV.txt"
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo ""
echo ""
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
################################################################################################
# check the coverage per each of the reccurent de novo SNPs (padded with 15bp both directions) #
################################################################################################
echo "Performing recurrent coverage analysis for PROBAND_ID = ${PROBAND_ID}_${FAMILY_ID} ..."
# we have identified the name of the proband's BAM file above (BAM_FILE), reuse it
# set the name of the file containing info about the coverage of the recurrent SNPs
REC_OUT_FILE=${COV_DIR}/${PROBAND_ID}_${FAMILY_ID}.REC_SNP_COV.txt
while IFS=$'\t' read -ra var; do
gene="${var[0]}"
chr="${var[1]}"
pos="${var[2]}"
lo=$(expr $pos - 15)
hi=$(expr $pos + 15)
reg="$lo-$hi"
echo "============================================="
echo "$gene : recurrent variant at $chr:$pos"
echo "exploring coverage at $chr:$reg"
echo "---------------------------------------------"
echo "precisely at the position"
${SAMTOOLS} depth -aa -Q 20 -r $chr:$reg ${BAM_FILE} | grep "$pos"
echo "---------------------------------------------"
echo "average in the +/- 15bp region"
${SAMTOOLS} depth -aa -Q 20 -r $chr:$reg ${BAM_FILE} | awk '{sum+=$3} END { print "Average = ",sum/NR}'
echo "---------------------------------------------"
echo "detailed in the +/- 15bp region"
${SAMTOOLS} depth -aa -Q 20 -r $chr:$reg ${BAM_FILE}
done < ${REC_SNP} > ${REC_OUT_FILE}
echo ""
echo ""
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo "Coverage analysis of recurring SNPs for PROBAND_ID = ${PROBAND_ID}_${FAMILY_ID}: done "
echo " Coverage file = ${REC_OUT_FILE}"
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo ""
echo ""
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
###################################################################################
### for each proband generate the DECIPHER file ###
### ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.ready.vcf.gz - the cleaned family VCF ###
### ${VASE_DIR}/${PLATE_ID}_${FAMILY_ID}.ready.denovo.vcf - the VASE file ###
### ${TRANS_MAP} - the current transcript mapping file ###
###################################################################################
echo "Generating the DECIPHER file for PROBAND_ID = ${PROBAND_ID}_${FAMILY_ID} ..."
# first, split the family VCF to individual VCFs
# -c1: minimum allele count (INFO/AC) of sites to be printed
# split multi-allelic sites (by -m -any)
# left-alignment and normalization (by adding the -f)
file=${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.ready.vcf.gz
echo "splitting $file"
for indi in `${BCFTOOLS} query -l $file`; do
${BCFTOOLS} view -c1 -Oz -s $indi -o ${file/.vcf*/.$indi.rough.vcf.gz} $file
${BCFTOOLS} norm -f ${REFERENCE_GENOME} -m -any -Oz -o ${file/.vcf*/.$indi.vcf.gz} ${file/.vcf*/.$indi.rough.vcf.gz}
rm ${file/.vcf*/.$indi.rough.vcf.gz}
done
# VASE file - already split, left-aligned and normalized
# create the names of the needed files
PED_FILE=${PED_DIR}/${BATCH_ID}_${PLATE_ID}_${FAMILY_ID}.ped
DEC_MAP=${WORK_DIR}/DECIPHER_INTERNAL_IDs.txt
IN_G2P_FILE=${G2P_DIR}/${PLATE_ID}_${FAMILY_ID}_LOG_DIR/${PLATE_ID}_${FAMILY_ID}.report.txt
IN_VASE_FILE=${VASE_DIR}/${PLATE_ID}_${FAMILY_ID}.ready.denovo.vcf
FAM_IGV_DIR=${IGV_DIR}/${PLATE_ID}_${FAMILY_ID}
#~#FAM_BAM_DIR=${SOURCE_DIR}/????-??-??_${VERSION_N}_${BATCH_ID}_${PLATE_ID}_${FAMILY_ID}
FAM_BAM_DIR=${SOURCE_DIR}/${BATCH_NUM}_${VERSION_N}/families/????-??-??_${BATCH_NUM}_${VERSION_N}_${PLATE_ID}_${FAMILY_ID}
## call the python scrpit
##time ${PYTHON2} /home/u035/u035/shared/temp/generate_DEC_IGV_scripts.py \
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
time ${PYTHON2} ${SCRIPTS_DIR}/generate_DEC_IGV_scripts.py \
${DEC_MAP} \
${TRANS_MAP} \
${PED_FILE} \
${IN_G2P_FILE} \
${IN_VASE_FILE} \
${FAM_IGV_DIR} \
${VCF_DIR} \
${PLATE_ID} \
${FAMILY_ID} \
${DEC_DIR} \
${FAM_BAM_DIR}
## using the DECIPHER bulk upload file v9 --> generate the DECIPHER bulk upload file v10
echo "...Generating v10 Decipher bulk upload file for proband = ${PROBAND_ID}, family_id = ${FAMILY_ID} ..."
time ${PYTHON3} ${SCRIPTS_DIR}/convert_DEC_to_v10.py ${DEC_DIR} ${PROBAND_ID}_${FAMILY_ID}
echo ""
echo ""
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo "DECIPHER analysis of PROBAND_ID = ${PROBAND_ID}_${FAMILY_ID}: done"
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo ""
echo ""
rm ${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.clean.vcf
##############################################################################################
### for each variant in the DECIPHER upload file ###
### generate a IGV snapshot based on the realigned BAM used by GATK for calling variants ###
### first, generate BAMOUTs for each variant (to be stored in the BAMOUT folder) ###
### then, generate a batch script for IGV to produce the snapshots based on the BAMOUTs ###
##############################################################################################
# we have so far
# FAMILY_ID=`head -n ${SLURM_ARRAY_TASK_ID} ${FAMILY_IDS} | tail -n 1`
# PROBAND_ID=`head -n ${SLURM_ARRAY_TASK_ID} ${CHILD_IDS} | tail -n 1`
echo "...Generating BAMOUT files for the ${FAMILY_ID} family, proband = ${PROBAND_ID} ..."
# identify parent IDs from the trio VCF file
kid_id=''
par_1_id=''
par_2_id=''
file=${VCF_DIR}/${PLATE_ID}_${FAMILY_ID}.ready.vcf.gz
for indi in `${BCFTOOLS} query -l $file`; do
echo "indi = $indi"
if [ "${indi}" = "${PROBAND_ID}_${FAMILY_ID}" ]
then
kid_id=${indi}
elif [ "${par_1_id}" = "" ]
then
par_1_id=${indi}
else
par_2_id=${indi}
fi
done
echo "...kid_id = ${kid_id}, par_1_id = ${par_1_id}, par_2_id = ${par_2_id} "
# gather the trio BAM files
#~#kid_bam=${SOURCE_DIR}/????-??-??_${VERSION_N}_${BATCH_ID}_${PLATE_ID}_${FAMILY_ID}/${kid_id}/${kid_id}-ready.bam
#~#par_1_bam=${SOURCE_DIR}/????-??-??_${VERSION_N}_${BATCH_ID}_${PLATE_ID}_${FAMILY_ID}/${par_1_id}/${par_1_id}-ready.bam
#~#par_2_bam=${SOURCE_DIR}/????-??-??_${VERSION_N}_${BATCH_ID}_${PLATE_ID}_${FAMILY_ID}/${par_2_id}/${par_2_id}-ready.bam
kid_bam=${SOURCE_DIR}/${BATCH_NUM}_${VERSION_N}/families/????-??-??_${BATCH_NUM}_${VERSION_N}_${PLATE_ID}_${FAMILY_ID}/${kid_id}/${kid_id}-ready.bam
par_1_bam=${SOURCE_DIR}/${BATCH_NUM}_${VERSION_N}/families/????-??-??_${BATCH_NUM}_${VERSION_N}_${PLATE_ID}_${FAMILY_ID}/${par_1_id}/${par_1_id}-ready.bam
par_2_bam=${SOURCE_DIR}/${BATCH_NUM}_${VERSION_N}/families/????-??-??_${BATCH_NUM}_${VERSION_N}_${PLATE_ID}_${FAMILY_ID}/${par_2_id}/${par_2_id}-ready.bam
echo "...kid_bam = ${kid_bam}..."
echo "...par_1_bam = ${par_1_bam}..."
echo "...par_2_bam = ${par_2_bam}..."
# gather the variants in the DECIPHER file for which to generate bamouts
# chr is the second column - need to add the 'chr' prefix
# pos is the third column
# the first line is a header line, starting with 'Internal reference number or ID'
# file called: ${DEC_DIR}/<proband_id>_<fam_id>_DEC_FLT.csv
# and for each run GATK to generate the bamout files
# to be stored in ${BAMOUT_DIR}/${FAMILY_ID}
mkdir ${BAMOUT_DIR}/${FAMILY_ID}
var_file=${DEC_DIR}/${kid_id}_DEC_FLT.csv
echo "... reading ${var_file} to generate the bamouts..."
grep -v '^Internal' ${var_file} |
while IFS= read -r line
do
echo "$line"
IFS=, read -ra ary <<<"$line"
# for key in "${!ary[@]}"; do echo "$key ${ary[$key]}"; done
chr=${ary[1]}
pos=${ary[2]}
ref=${ary[4]}
alt=${ary[5]}
echo " --> chr = $chr, pos = $pos, ref = ${ref}, alt = ${alt}"
# generate the bamout file
echo "...doing the bamout"
echo " time ${GATK4} HaplotypeCaller --reference ${REFERENCE_GENOME} --input ${kid_bam} --input ${par_1_bam} --input ${par_2_bam} -L chr${chr}:${pos} --interval-padding 500 \"
echo " --active-probability-threshold 0.000 -ploidy 2 \"
echo " --output ${BAMOUT_DIR}/${FAMILY_ID}/${FAMILY_ID}_chr${chr}_${pos}.bamout.vcf -bamout ${BAMOUT_DIR}/${FAMILY_ID}/${FAMILY_ID}_chr${chr}_${pos}.bamout.bam"
time ${GATK4} HaplotypeCaller --reference ${REFERENCE_GENOME} --input ${kid_bam} --input ${par_1_bam} --input ${par_2_bam} -L chr${chr}:${pos} \
--interval-padding 500 --active-probability-threshold 0.000 -ploidy 2 \
--output ${BAMOUT_DIR}/${FAMILY_ID}/${FAMILY_ID}_chr${chr}_${pos}.bamout.vcf -bamout ${BAMOUT_DIR}/${FAMILY_ID}/${FAMILY_ID}_chr${chr}_${pos}.bamout.bam
done
#################################################################
# write the IGV batch file for this family based on the bamouts #
# to be stored as /home/u035/u035/shared/analysis/work/${PROJECT_ID}/DECIPHER/IGV/bamout_${PROBAND_ID}_${FAMILY_ID}.snapshot.txt #
#################################################################
snap_file=/home/u035/u035/shared/analysis/work/${PROJECT_ID}/DECIPHER/IGV/bamout_${PROBAND_ID}_${FAMILY_ID}.snapshot.txt
# check if previous version exist, if so - delete it
if [ -f "${snap_file}" ]; then
echo "previous version of ${snap_file} exist --> deleted"
rm ${snap_file}
fi
# write the header for the IGV batch file
echo "new" >> ${snap_file}
echo "genome hg38" >> ${snap_file}
echo "snapshotDirectory \"/home/u035/u035/shared/analysis/work/${PROJECT_ID}/DECIPHER/IGV/${PLATE_ID}_${FAMILY_ID}\"" >> ${snap_file}
echo "" >> ${snap_file}
# now, go again over the variants in the DECIPHER file and generate one snapshot file for all the variants
var_file=${DEC_DIR}/${kid_id}_DEC_FLT.csv
echo "... reading ${var_file} to generate the IGV batch file using the bamouts..."
grep -v '^Internal' ${var_file} |
while IFS= read -r line
do
IFS=, read -ra ary <<<"$line"
chr=${ary[1]}
pos=${ary[2]}
ref=${ary[4]}
alt=${ary[5]}
left=$((${pos}-25))
right=$((${pos}+25))
echo "new" >> ${snap_file}
echo "load ${BAMOUT_DIR}/${FAMILY_ID}/${FAMILY_ID}_chr${chr}_${pos}.bamout.bam" >> ${snap_file}
echo "preference SAM.SHADE_BASE_QUALITY true" >> ${snap_file}
echo "goto chr${chr}:${left}-${right}" >> ${snap_file}
echo "group SAMPLE" >> ${snap_file}
echo "sort base" >> ${snap_file}
echo "squish" >> ${snap_file}
echo "snapshot bamout_${PROBAND_ID}_${FAMILY_ID}_chr${chr}_${pos}_${ref}_${alt}.png" >> ${snap_file}
echo "" >> ${snap_file}
echo "" >> ${snap_file}
done
echo "Generating of the IGV batch files based on bamouts - done!"
echo "snap_file = ${snap_file}"
echo "+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
echo "+++ Variant prioritization of family ${FAMILY_ID} completed +++"
echo "+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"