Newer
Older
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
#!/bin/bash
#PBS -l walltime=24:00:00
#PBS -l ncpus=1,mem=16gb
#PBS -q uv2000
#PBS -N process_trio
#PBS -j oe
# setup PATH
export PATH=$PATH:/home/u027/project/software/bcbio/anaconda/envs/python2/bin:/home/u027/project/software/bcbio/anaconda/bin
export PERL5LIB=$PERL5LIB:/home/u027/project/software/bcbio/anaconda/lib/site_perl/5.26.2
### folder structure for the downstream analysis - created by NHS_WES_trio_setup.sh ###
#BASE=/scratch/u027/project/analysis/wes_pilot
BASE=/scratch/u027/project/trio_whole_exome/analysis
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=${WORK_DIR}/CNV
SCRIPTS_DIR=/home/u027/project/scripts
# other files to be used
FAMILY_IDS=${WORK_DIR}/FAM_IDs.txt # created by NHS_WES_trio_setup.sh
CHILD_IDS=${WORK_DIR}/PRO_IDs.txt # created by NHS_WES_trio_setup.sh
TARGETS=/home/u027/project/resources/DDG2P.20190919.plus15bp.merged.bed # OK
CLINVAR=/home/u027/project/resources/DDG2P.20190919.clinvar.20190916.plus15bp.txt # OK
BLACKLIST=/home/u027/project/resources/current_blacklist.txt # OK
TRANS_MAP=/home/u027/project/resources/current_trans_map.txt # OK
### TOOLS ###
BCFTOOLS=/home/u027/project/software/bcbio/anaconda/envs/python2/bin/bcftools
BGZIP=/home/u027/project/software/bcbio/anaconda/envs/python2/bin/bgzip
TABIX=/home/u027/project/software/bcbio/anaconda/envs/python2/bin/tabix
VT=/home/u027/project/software/bcbio/anaconda/bin/vt
VASE=/home/u027/project/software/bcbio/anaconda/bin/vase
GATK4=/home/u027/project/software/bcbio/anaconda/bin/gatk
GATK3=/home/u027/project/software/GenomeAnalysisTK-3.8/GenomeAnalysisTK.jar
PYTHON2=/home/u027/project/software/bcbio/anaconda/envs/python2/bin/python2.7
VEP="/home/u027/project/software/bcbio/anaconda/bin/perl /home/u027/project/software/bcbio/anaconda/bin/vep" # points to ../share/ensembl-vep-97.3-0/vep
REFERENCE_GENOME=/home/u027/project/data/reference/hg38.fa
echo "SOURCE_DIR = ${SOURCE_DIR}" # the general path to the source BAM files (VCF and PED already copied) i.e. /scratch/u027/project/trio_whole_exome/analysis/output/
echo "BATCH_ID = ${BATCH_ID}" # the ID of the batch being processed e.g. 11870_Germain_Lorna
echo "PLATE_ID = ${PLATE_ID}" # the PCR plate ID of the batch being currently processed, e.g. 16862
echo "PROJECT_ID = ${PROJECT_ID}" # this the the folder (${BASE}/${PROJECT_ID}) where the downstream analysis will be done
# enable running singletons
if [ -z $PBS_ARRAY_INDEX ]
then
if [ -z $INDEX ]
then
export PBS_ARRAY_INDEX=1
else
export PBS_ARRAY_INDEX=$INDEX
fi
fi
# change to the LOG folder
cd ${LOG_DIR}
################################
##### for each family ####
################################
FAMILY_ID=`head -n ${PBS_ARRAY_INDEX} ${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}/NHS_WES_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, will be deleted later
##############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: ${FAMILY_ID}.ready.vcf.gz ###
###########################################################
echo "Performing G2P analysis (DD genes)for FAMILY_ID = ${FAMILY_ID}..."
######################################################################################IN_FILE=${VCF_DIR}/${FAMILY_ID}.ready.vcf.gz
IN_FILE=${VCF_DIR}/${FAMILY_ID}.clean.vcf #################################################################################
G2P_LOG_DIR=${G2P_DIR}/${FAMILY_ID}_LOG_DIR
mkdir ${G2P_LOG_DIR}
TXT_OUT=${G2P_LOG_DIR}/${FAMILY_ID}.report.txt
HTML_OUT=${G2P_LOG_DIR}/${FAMILY_ID}.report.html
VCF_KEYS='gnomADe|gnomADg'
time ${VEP} \
-i ${IN_FILE} \
--output_file ${G2P_LOG_DIR}/${FAMILY_ID}_inter_out.txt \
--force_overwrite \
--assembly GRCh38 \
--fasta ${REFERENCE_GENOME} \
--offline \
--merged \
--use_given_ref \
--cache --cache_version 97 \
--dir_cache /home/u027/project/software/bcbio/genomes/Hsapiens/hg38/vep \
--individual all \
--transcript_filter "gene_symbol in /home/u027/project/resources/genes_in_DDG2P.19092019.txt" \
--dir_plugins /home/u027/project/software/bcbio/anaconda/share/ensembl-vep-97.3-0 \
--plugin G2P,file='/home/u027/project/resources/DDG2P.19092019.csv',af_from_vcf=1,confidence_levels='confirmed&probable&both RD and IF',
af_from_vcf_keys=${VCF_KEYS},log_dir=${G2P_LOG_DIR},txt_report=${TXT_OUT},html_report=${HTML_OUT}
echo ""
echo ""
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo "G2P analysis of FAMILY_ID = ${FAMILY_ID}: done"
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo ""
echo ""
###########################################################
### run VASE for each family VCF (de novo) ###
### format: ${FAMILY_ID}.ready.vcf.gz ###
###########################################################
echo "Performing de novo analysis with VASE for FAMILY_ID = ${FAMILY_ID} ..."
IN_FILE=${VCF_DIR}/${FAMILY_ID}.ready.vcf.gz
OUT_FILE=${VASE_DIR}/${FAMILY_ID}.strict.denovo.vcf
# PED_FILE=${PED_DIR}/${BATCH}_${FAMILY_ID}.ped
PED_FILE=${PED_DIR}/*_${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}
# 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 -F ${OUT_FILE}
# select only variants on the 24 chromosomes
time ${GATK4} SelectVariants -R ${REFERENCE_GENOME} -V ${OUT_FILE} -O ${FAMILY_ID}.strict.24chr.denovo.vcf -L /home/u027/project/resources/24_chr.list --exclude-non-variants
# sort the VCF (maybe not needed?, but just in case, and it is quick)
rm ${FAMILY_ID}.strict.24chr.sort.denovo.vcf
grep '^#' ${FAMILY_ID}.strict.24chr.denovo.vcf > ${FAMILY_ID}.strict.24chr.sort.denovo.vcf \
&& grep -v '^#' ${FAMILY_ID}.strict.24chr.denovo.vcf | LC_ALL=C sort -t $'\t' -k1,1V -k2,2n >> ${FAMILY_ID}.strict.24chr.sort.denovo.vcf
# index the sorted VCF
time ${GATK4} IndexFeatureFile -F ${FAMILY_ID}.strict.24chr.sort.denovo.vcf
# split multi-allelic sites [by -m -any]
# left-alignment and normalization [by adding the -f]
file=${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 ${FAMILY_ID}.strict.denovo.vcf*
rm ${FAMILY_ID}.strict.24chr.denovo.vcf*
rm ${FAMILY_ID}.strict.24chr.sort.denovo.vcf*
###rm ${FAMILY_ID}.clean.denovo.vcf*
# change back to the LOG folder
cd ${LOG_DIR}
echo ""
echo ""
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo "De novo analysis of FAMILY_ID = ${FAMILY_ID}: done"
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo ""
echo ""
#################################################################################################################################################
### run coverage for each proband (DD genes) ###
### format: ${SOURCE_DIR}/????-??-??_${BATCH_ID}_${PLATE_ID}_${FAMILY_ID}/${PROBAND_ID}_${FAMILY_ID}/${PROBAND_ID}_${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)
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=${SOURCE_DIR}/????-??-??_${BATCH_ID}_${PLATE_ID}_${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}/generate_coverage_result_file.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 ""
.........................
###################################################################################
### 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
# get the ped file
PED_FILE=${PED_DIR}/${BATCH_ID}_${PLATE_ID}_${FAMILY_ID}.ped
# call the python scrpit
time ${PYTHON2} ${SCRIPTS_DIR}/NHS_WES_generate_DEC_IGV.py ${PED_FILE} ${G2P_DIR}/${PLATE_ID}_${FAMILY_ID}_LOG_DIR/${PLATE_ID}_${FAMILY_ID}.report.txt \
${VASE_DIR}/${PLATE_ID}_${FAMILY_ID}.ready.denovo.vcf \
${VCF_DIR}/${FAMILY_ID} ${DEC_DIR} ${IGV_DIR} ${IGV_DIR}/${FAMILY_ID} ${SOURCE_DIR} ${FAMILY_ID} \
${WORK_DIR} ${TRANS_MAP}
echo ""
echo ""
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo "DECIPHER analysis of PROBAND_ID = ${PROBAND_ID}: done"
echo "^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^"
echo ""
echo ""
rm ${VCF_DIR}/${FAMILY_ID}.clean.vcf ##################################################