-
Notifications
You must be signed in to change notification settings - Fork 2
/
pipeline_RNAseq_November2019_pchuckle.sh
549 lines (291 loc) · 30.6 KB
/
pipeline_RNAseq_November2019_pchuckle.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
########### Here is the one line that needs to be modified
metagenomics=/blah/blah/backedupdirectory
########## everything else below should be automated (if all executables are in the same directory)
Software=${metagenomics}/exec
diamond=${Software}/diamond
trimG=${Software}/trim_galore_0.3.7/trim_galore
seqtk=${Software}/seqtk-master/seqtk
samtools=${Software}/samtools-0.1.19/samtools
bedtools=/share/apps/genomics/bedtools-2.25.0/bin/
bowtie=/share/apps/genomics/bowtie2-2.4.1/bowtie2
blastn=/share/apps/genomics/blast-2.9.0/bin/blastn
############ default values
script=${output}/cluster/submission/default.sh
step1=FALSE
until [ -z "$1" ]; do
# use a case statement to test vars. we always test $1 and shift at the end of the for block.
case $1 in
--inputFiles)
shift
i=0
for fileloc in $@; do
inputFiles[ $i ]=$fileloc
((i=i+1))
done;;
--outDir )
shift
output=$1;;
--delimiter )
shift
delimiter=$1;;
--script)
shift
script=$1;;
--reference)
shift
reference=$1;;
--referencerRNA)
shift
referencerRNA=$1;;
--db )
shift
db=$1;;
--dbunivec )
shift
dbunivec=$1;;
--dbrRNA )
shift
dbrRNA=$1;;
--dbnucl)
shift
dbnucl=$1;;
--dbprot)
shift
dbprot=$1;;
--sample )
shift
sample=$1;;
--step1 )
shift
step1=$1;;
-* )
echo "Unrecognized option: $1"
exit 1;;
esac
shift
if [ "$#" = "0" ]; then break; fi
done
################ creating all the output folders
echo -e "Output folder: $output\n"
clusterDir=${output}/cluster
cluster_out=${clusterDir}/out
cluster_error=${clusterDir}/error
cluster_submission=${clusterDir}/submission
output_qc=${output}/QC
output_trim=${output}/trim
output_quickAlign_human=${output}/quickAlign_human
output_quickAlign_rRNA=${output}/quickAlign_rRNA
output_blastn=${output}/blastn
output_univec_blastn=${output}/blastn_univec
output_rRNA=${output}/blastn_rRNA
output_protein=${output}/protein
output_nucleotide=${output}/nucleotide
output_summary=${output}/summary
myFolders="$output $clusterDir $cluster_out $cluster_error $cluster_submission $output_trim $output_quickAlign_human $output_quickAlign_rRNA $output_qc $output_blastn $output_univec_blastn $output_rRNA $output_protein $output_nucleotide $output_summary "
for folder in $myFolders; do
if [ ! -e $folder ]; then
echo "Creating $folder"
mkdir $folder
fi
done
################################################################### Now writing the script
echo "Output script: $script"
echo "
#!/bin/bash
#$ -S /bin/bash
date ##to measure the duration
hostname
" > $script
# ######################################################################################### STEP1 (Trim, bowtie2, prinseq, megablastn to remove host & rRNA, Diamond for protein, megaBLAST for nucleotide) #####################################################
if [[ "$step1" == "TRUE" ]]; then
nfiles=${inputFiles[0]}
if [[ "$nfiles" != "2" ]]; then
echo "You specified $nfiles input files".
echo "Error: currently the input data MUST be paired end."
exit;
fi
seq1=${inputFiles[ 1 ]}
seq2=${inputFiles[ 2 ]}
############### check that raw data files & reference exist
for file in $seq1 $seq2 $reference; do
ls -lh $file
if [ ! -e "$file" ]; then
echo "Error, file $file does not exist"
exit
fi
done
echo "1) Trim, bowtie2, QC, remove human with blast, univec for nucleotide/rRNA for protein, DIAMOND and megaBLAST to protein/nucleotide DBs"
###change the time depending on the size of dataset
echo "
#!/bin/bash -l
#$ -S /bin/bash
#$ -o $cluster_out
#$ -e $cluster_error
#$ -l h_rt=48:00:00
#$ -l tmem=34.9,h_vmem=34.9G
#$ -R y
#$ -N step1
#$ -wd ${output}
#$ -V
" >> $script
echo -e "1) Trim adapters from reads and basic quality control"
echo "
${trimG} -q 20 --length 25 --paired $seq1 $seq2 -o ${output_trim}
mv ${output_trim}/*val_1.fq.gz ${output_trim}/${sample}_1_val_1.fq.gz
mv ${output_trim}/*val_2.fq.gz ${output_trim}/${sample}_2_val_2.fq.gz
" >> $script
echo "2) Bowtie2 - human"
echo "
${bowtie} -p 6 -x ${reference}/human_GRCh38.p9_addition -1 ${output_trim}/${sample}_1_val_1.fq.gz -2 ${output_trim}/${sample}_2_val_2.fq.gz -S ${output_quickAlign_human}/${sample}.sam
" >> $script
echo -e "3) Select pairs of reads that are both non mapping"
echo "
${samtools} view -bS -o ${output_quickAlign_human}/${sample}.bam ${output_quickAlign_human}/${sample}.sam
${samtools} sort ${output_quickAlign_human}/${sample}.bam ${output_quickAlign_human}/${sample}_sorted
${samtools} index ${output_quickAlign_human}/${sample}_sorted.bam
${samtools} view -u -f 12 -F 256 ${output_quickAlign_human}/${sample}.bam > ${output_quickAlign_human}/${sample}_unmapped.bam
${bedtools}/bamToFastq -i ${output_quickAlign_human}/${sample}_unmapped.bam -fq ${output_quickAlign_human}/${sample}_1.fq -fq2 ${output_quickAlign_human}/${sample}_2.fq
" >> $script
echo "6) PrinSeq reads"
echo "
export PERL5LIB=\${PERL5LIB}:${Software}/bioperl-live
perl ${Software}/prinseq-lite-0.20.3/prinseq-lite.pl -fastq ${output_quickAlign_human}/${sample}_1.fq -fastq2 ${output_quickAlign_human}/${sample}_2.fq -min_qual_mean 20 -out_good ${output_qc}/Sample${sample} -trim_qual_right 10 -trim_qual_left 10 -lc_method dust -lc_threshold 7 -no_qual_header -qual_noscale -graph_data ${output_qc}/Sample${sample}_quality.plot -out_bad null
" >> $script
# ##megaBLAST to filter out human
echo -e "7) Submit blastn job against human reference"
echo "
${seqtk} seq -a ${output_qc}/Sample${sample}_1.fastq > ${output_qc}/Sample${sample}_1.fasta
${seqtk} seq -a ${output_qc}/Sample${sample}_2.fastq > ${output_qc}/Sample${sample}_2.fasta
cat ${output_qc}/Sample${sample}_1.fasta ${output_qc}/Sample${sample}_2.fasta > ${output_qc}/${sample}_paired.fasta
rm ${output_qc}/Sample${sample}_1.fasta ${output_qc}/Sample${sample}_2.fasta
" >> $script
echo "
awk 'BEGIN{RS=\">\"}NR>1{sub(\"\n\",\"\t\"); gsub(\"\n\",\"\"); print \$0}' ${output_qc}/${sample}_paired.fasta > ${output_qc}/NM_paired_${sample}.txt
" >> $script
echo "
$blastn -db $db -query ${output_qc}/${sample}_paired.fasta -outfmt 6 -num_alignments 1 -evalue 1 -culling_limit 1 -num_threads 6 > ${output_blastn}/${sample}_paired.ncbiBLASTn
" >> $script
echo -e "8) filter out blastn hits and keep filtered dataset"
echo "
####### Make fasta files for non overlapping reads (paired end)
file1=${output_blastn}/${sample}_paired.ncbiBLASTn
file1tmp=${output_blastn}/${sample}_paired_ncbi_tmp.txt
file2=${output_qc}/NM_paired_${sample}.txt
file2tmp=${output_qc}/NM_paired_${sample}_tmp.txt
filtered=${output_blastn}/${sample}_paired_filtered.txt
awk -v x=\"${delimiter}\" 'BEGIN {FS=OFS=\"\\t\"} {split(\$1, a, x); print a[1], \$1, \$3}' \${file1} | uniq > \${file1tmp}
awk -v x=\"${delimiter}\" 'BEGIN {FS=OFS=\"\\t\"} {split(\$1, a, x); print a[1], \$1, \$2}' \${file2} | uniq > \${file2tmp}
echo \$file1tmp
echo \$file2tmp
awk 'BEGIN {FS=OFS=\"\\t\"} NR==FNR{a[\$1]=\$1;next} a[\$1]!=\$1{print \$2,\$3}' \${file1tmp} \${file2tmp} > \${filtered}
wc -l \${filtered} > ${output_blastn}/NM_paired.number
awk -F\"\\t\" '{print \">\"\$1\"\n\"\$2}' \${filtered} > ${output_blastn}/NM_paired_${sample}_filtered.fasta
" >> $script
### ###blast against univec
echo "
$blastn -db $dbunivec -query ${output_blastn}/NM_paired_${sample}_filtered.fasta -outfmt 6 -num_alignments 1 -evalue 1 -culling_limit 1 -num_threads 6 > ${output_univec_blastn}/${sample}_paired.ncbiBLASTn
" >> $script
echo -e "8) filter out blastn hits and keep filtered dataset"
echo "
####### Make fasta files for non overlapping reads (paired end)
file1=${output_univec_blastn}/${sample}_paired.ncbiBLASTn
file1tmp=${output_univec_blastn}/${sample}_paired_ncbi_tmp.txt
file2=${output_blastn}/${sample}_paired_filtered.txt
file2tmp=${output_blastn}/NM_paired_${sample}_tmp.txt
filtered=${output_univec_blastn}/${sample}_paired_filtered.txt
awk -v x=\"${delimiter}\" 'BEGIN {FS=OFS=\"\\t\"} {split(\$1, a, x); print a[1], \$1, \$3}' \${file1} | uniq > \${file1tmp}
awk -v x=\"${delimiter}\" 'BEGIN {FS=OFS=\"\\t\"} {split(\$1, a, x); print a[1], \$1, \$2}' \${file2} | uniq > \${file2tmp}
echo \$file1tmp
echo \$file2tmp
awk 'BEGIN {FS=OFS=\"\\t\"} NR==FNR{a[\$1]=\$1;next} a[\$1]!=\$1{print \$2,\$3}' \${file1tmp} \${file2tmp} > \${filtered}
wc -l \${filtered} > ${output_univec_blastn}/NM_paired.number
awk -F\"\\t\" '{print \">\"\$1\"\n\"\$2}' \${filtered} > ${output_univec_blastn}/NM_paired_${sample}_filtered.fasta
" >> $script
echo "
# ##############megaBLAST for nucleotides
#$blastn -db $dbnucl -query ${output_univec_blastn}/NM_paired_${sample}_filtered.fasta -outfmt 6 -max_target_seqs 10 -max_hsps 1 -num_threads 6 > ${output_nucleotide}/${sample}_megaBLAST.tab
" >> $script
###### And now continue processing suitable for protein search
### First create fastqs from blastn human filtered fasta to feed into bowtie2
echo "
filtered=${output_blastn}/${sample}_paired_filtered.txt
awk 'BEGIN {FS=OFS=\"\\t\"} {print \$1}' \${filtered} > ${output_blastn}/ids.txt
${seqtk} subseq ${output_qc}/Sample${sample}_1.fastq ${output_blastn}/ids.txt > ${output_blastn}/${sample}_filtered_1.fastq
${seqtk} subseq ${output_qc}/Sample${sample}_2.fastq ${output_blastn}/ids.txt > ${output_blastn}/${sample}_filtered_2.fastq
" >> $script
echo "5) Bowtie2 - rRNA"
echo "
${bowtie} -p 6 -x ${referencerRNA}/SILVA_128_SSU_LSU_UniVec -1 ${output_blastn}/${sample}_filtered_1.fastq -2 ${output_blastn}/${sample}_filtered_2.fastq -S ${output_quickAlign_rRNA}/${sample}.sam
" >> $script
echo -e "4) Select pairs of reads that are both non mapping"
echo "
${samtools} view -bS -o ${output_quickAlign_rRNA}/${sample}.bam ${output_quickAlign_rRNA}/${sample}.sam
${samtools} sort ${output_quickAlign_rRNA}/${sample}.bam ${output_quickAlign_rRNA}/${sample}_sorted
${samtools} index ${output_quickAlign_rRNA}/${sample}_sorted.bam
${samtools} view -u -f 12 -F 256 ${output_quickAlign_rRNA}/${sample}.bam > ${output_quickAlign_rRNA}/${sample}_unmapped.bam
${bedtools}/bamToFastq -i ${output_quickAlign_rRNA}/${sample}_unmapped.bam -fq ${output_quickAlign_rRNA}/${sample}_1.fq -fq2 ${output_quickAlign_rRNA}/${sample}_2.fq
${seqtk} seq -a ${output_quickAlign_rRNA}/${sample}_1.fq > ${output_quickAlign_rRNA}/${sample}_1.fasta
${seqtk} seq -a ${output_quickAlign_rRNA}/${sample}_2.fq > ${output_quickAlign_rRNA}/${sample}_2.fasta
cat ${output_quickAlign_rRNA}/${sample}_1.fasta ${output_quickAlign_rRNA}/${sample}_2.fasta > ${output_quickAlign_rRNA}/${sample}_paired.fasta
awk 'BEGIN{RS=\">\"}NR>1{sub(\"\n\",\"\t\"); gsub(\"\n\",\"\"); print \$0}' ${output_quickAlign_rRNA}/${sample}_paired.fasta > ${output_quickAlign_rRNA}/${sample}_paired_filtered.txt
" >> $script
# # ##megaBLAST to filter out rRNA
# ### #blastn against ribosomal RNA (silva)
echo -e "9) Submit blastn job against rRNA reference"
echo "
$blastn -db $dbrRNA -query ${output_quickAlign_rRNA}/${sample}_paired.fasta -outfmt 6 -num_alignments 1 -evalue 0.1 -culling_limit 1 -num_threads 6 > ${output_rRNA}/${sample}_paired.ncbiBLASTn
" >> $script
echo -e "10) filter out blastn hits and keep filtered dataset"
echo "
####### Make fasta files for non overlapping reads (paired end)
file1=${output_rRNA}/${sample}_paired.ncbiBLASTn
file1tmp=${output_rRNA}/${sample}_paired_ncbi_tmp.txt
file2=${output_quickAlign_rRNA}/${sample}_paired_filtered.txt
file2tmp=${output_quickAlign_rRNA}/${sample}_paired_filtered_tmp.txt
filtered=${output_rRNA}/${sample}_paired_filtered_rRNA.txt
awk -v x=\"${delimiter}\" 'BEGIN {FS=OFS=\"\\t\"} {split(\$1, a, x); print a[1], \$1, \$3}' \${file1} | uniq > \${file1tmp}
awk -v x=\"${delimiter}\" 'BEGIN {FS=OFS=\"\\t\"} {split(\$1, a, x); print a[1], \$1, \$2}' \${file2} | uniq > \${file2tmp}
echo \$file1tmp
echo \$file2tmp
awk 'BEGIN {FS=OFS=\"\\t\"} NR==FNR{a[\$1]=\$1;next} a[\$1]!=\$1{print \$2,\$3}' \${file1tmp} \${file2tmp} > \${filtered}
wc -l \${filtered} > ${output_rRNA}/NM_paired.number
awk -F\"\\t\" '{print \">\"\$1\"\n\"\$2}' \${filtered} > ${output_rRNA}/NM_paired_${sample}_filtered_rRNA.fasta
" >> $script
echo -e "nucleotide similarity"
echo "
# ##############megaBLAST for nucleotides
$blastn -db $dbnucl -query ${output_rRNA}/NM_paired_${sample}_filtered_rRNA.fasta -outfmt 6 -max_target_seqs 10 -max_hsps 1 -num_threads 6 > ${output_nucleotide}/${sample}_megaBLAST_norRNA.tab
" >> $script
echo -e "11) Submit DIAMOND for protein"
echo "
$diamond blastx -d $dbprot -q ${output_rRNA}/NM_paired_${sample}_filtered_rRNA.fasta -f 6 -k 10 -p 6 -sensitive -e 1 > ${output_protein}/${sample}_diamond.tab
" >> $script
# echo -e "12) Remove large files that won't be reused i.e sam "
echo "
# ### remove files that take up too much storage space and won't be used downstream
# ### from bowtie folders
rm ${output_quickAlign_human}/${sample}.sam
rm ${output_quickAlign_rRNA}/${sample}.sam
# ##from QC folder
# rm ${output_qc}/NM_paired_${sample}.txt
# rm ${output_qc}/NM_paired_${sample}_tmp.txt
# ## from blastn folders
# rm ${output_blastn}/${sample}_paired_ncbi_tmp.txt
" >> $script
# ###############make reads stats summary
echo -e "13) Create reads stats summary"
echo "
grep 'Processed reads:' ${output_trim}/${sample}_1.fastq.gz_trimming_report.txt | awk -F\":\" 'BEGIN {OFS=\"\t\"}{print \"Raw reads\", \$2*2}' > ${output_summary}/${sample}_raw.count
grep 'Trimmed reads:' ${output_trim}/${sample}_1.fastq.gz_trimming_report.txt | awk -F\":\" 'BEGIN {OFS=\"\t\"}{print \"Trimmed reads\", \$2*2}' > ${output_summary}/${sample}_trimmed.count
wc -l ${output_quickAlign_human}/${sample}_1.fq | awk 'BEGIN {OFS=\"\t\"}{ print \"Non human (bowtie2)\", (\$1/4)*2}' > ${output_summary}/${sample}_nonhuman.count
wc -l ${output_quickAlign_rRNA}/${sample}_1.fq | awk 'BEGIN {OFS=\"\t\"}{ print \"Non rRNA (bowtie2)\", (\$1/4)*2}' > ${output_summary}/${sample}_nonrRNA.count
wc -l ${output_QC}/${sample}_paired.fasta | awk 'BEGIN {OFS=\"\t\"}{ print \"after QC\", $1/2}' > ${output_summary}/${sample}_QC.count
awk '{s+=\$1} END {print s}' ${output_blastn}/NM_paired.number | awk -F\":\" 'BEGIN {OFS=\"\t\"}{ print \"non human (blastn)\", \$1}' > ${output_summary}/${sample}_nonhuman_blastn.count
awk '{s+=\$1} END {print s}' ${output_rRNA}/NM_paired.number | awk -F\":\" 'BEGIN {OFS=\"\t\"}{ print \"non rRNA (blastn)\", \$1}' > ${output_summary}/${sample}_nonrRNA_blastn.count
awk -F\"\t\" '{print \$1}' ${output_protein}/${sample}_diamond.tab | sort | uniq | wc -l | awk -F\" \" '{print \"Reads mapping to prot DB\", \$1}' > ${output_summary}/${sample}_maptoprot.count
awk -F\"\t\" '{print \$1}' ${output_nucleotide}/${sample}_megaBLAST.tab | sort | uniq | wc -l | awk -F\" \" '{print \"Reads mapping to nucl DB\", \$1}' > ${output_summary}/${sample}_maptonucl.count
cat ${output_summary}/${sample}_raw.count ${output_summary}/${sample}_trimmed.count ${output_summary}/${sample}_nonhuman.count ${output_summary}/${sample}_nonrRNA.count ${output_summary}/${sample}_QC.count ${output_summary}/${sample}_nonhuman_blastn.count ${output_summary}/${sample}_nonrRNA_blastn.count ${output_summary}/${sample}_maptoprot.count ${output_summary}/${sample}_maptonucl.count > ${output_summary}/${sample}_summary.count.new
" >> $script
qsub $script
fi
# ################end of STEP1