Commit a67739cb authored by Kosmas Hench's avatar Kosmas Hench

update RNA scripts

parent 38178bf1
#PBS -l elapstim_req=06:00:00
#PBS -l elapstim_req=10:00:00
#PBS -l memsz_job=20gb
#PBS -b 1
#PBS -l cpunum_job=1
......@@ -7,17 +7,57 @@
#PBS -o trimm_retinaRNA.stdout
#PBS -e trimm_retinaRNA.stderr
cd $WORK/assembly_ver2.0/20_retinaRNA
cd $WORK/1-output/08_annotation
for i in $( cat retina_samples ); do
mkdir RNAtrimmed
cd RNAtrimmed
# quality trimm retina samples
for i in $( cat $WORK/0_data/0_resources/retina_samples ); do
frwrd=$(echo "$i-1.fq.gz"| sed 's/-//g')
rwrse=$(echo "$i-2.fq.gz"| sed 's/-//g')
otfl=$(echo "$i.fq.gz"| sed 's/_.fq.gz//g')
echo $frwrd", "$rwrse", "$otfl;
java -jar $SFTWR/Trimmomatic/trimmomatic-0.33.jar PE \
$WORK/00_raw_LIB/02_RNAdata/02_retinas/$frwrd $WORK/00_raw_LIB/02_RNAdata/02_retinas/$rwrse \
$otfl.1p.fq.gz $otfl.1u.fq.gz $otfl.2p.fq.gz $otfl.2u.fq.gz \
ILLUMINACLIP:/sfs/fs2/work-geomar7/smomw287/software/Trimmomatic/adapters/TruSeq3-PE-2.fa:5:30:10:3 \
SLIDINGWINDOW:3:29 HEADCROP:10 MINLEN:35;
$WORK/0_data/1-0_raw/$frwrd $WORK/0_data/1-0_raw/$rwrse \
$otfl.1p.fq.gz $otfl.1u.fq.gz $otfl.2p.fq.gz $otfl.2u.fq.gz \
ILLUMINACLIP:$SFTWR/Trimmomatic/adapters/TruSeq3-PE-2.fa:5:30:10:3 \
SLIDINGWINDOW:3:29 HEADCROP:10 MINLEN:35;
done
# quality trimm other tissues
java -jar $SFTWR/Trimmomatic/trimmomatic-0.33.jar PE \
$WORK/0_data/1-0_raw/rawRNA_guill.1.fq.gz $WORK/0_data/1-0_raw/rawRNA_guill.2.fq.gz \
tmp.RNA_guill.1p.fq.gz tmp.RNA_guill.1u.fq.gz tmp.RNA_guill.2p.fq.gz tmp.RNA_guill.2u.fq.gz \
ILLUMINACLIP:$SFTWR/Trimmomatic/adapters/TruSeq3-PE-2.fa:2:30:10:3 \
SLIDINGWINDOW:5:28 HEADCROP:12 MINLEN:25;
java -jar $SFTWR/Trimmomatic/trimmomatic-0.33.jar SE -phred33 \
tmp.RNA_guill.2p.fq.gz \
RNA_guill.2.fq.gz CROP:150;
java -jar $SFTWR/Trimmomatic/trimmomatic-0.33.jar PE \
$WORK/0_data/1-0_raw/rawRNA_liver.1.fq.gz $WORK/0_data/1-0_raw/rawRNA_liver.2.fq.gz \
tmp.RNA_liver.1p.fq.gz tmp.RNA_liver.1u.fq.gz tmp.RNA_liver.2p.fq.gz tmp.RNA_liver.2u.fq.gz \
ILLUMINACLIP:$SFTWR/Trimmomatic/adapters/TruSeq3-PE-2.fa:2:30:10:3 \
SLIDINGWINDOW:5:28 HEADCROP:12 MINLEN:25;
java -jar $SFTWR/Trimmomatic/trimmomatic-0.33.jar PE \
$WORK/0_data/1-0_raw/rawRNA_muscle.1.fq.gz $WORK/0_data/1-0_raw/rawRNA_muscle.2.fq.gz \
tmp.RNA_muscle.1p.fq.gz tmp.RNA_muscle.1u.fq.gz tmp.RNA_muscle.2p.fq.gz tmp.RNA_muscle.2u.fq.gz \
ILLUMINACLIP:$SFTWR/Trimmomatic/adapters/TruSeq3-PE-2.fa:2:30:10:3 \
SLIDINGWINDOW:5:28 HEADCROP:12 MINLEN:25;
java -jar $SFTWR/Trimmomatic/trimmomatic-0.33.jar SE -phred33 \
tmp.RNA_muscle.2p.fq.gz \
RNA_muscle.2.fq.gz CROP:150;
mv tmp.RNA_guill.1p.fq.gz RNA_guill.1.fq.gz
mv tmp.RNA_liver.1p.fq.gz RNA_liver.1.fq.gz
mv tmp.RNA_liver.2p.fq.gz RNA_liver.2.fq.gz
mv tmp.RNA_muscle.1p.fq.gz RNA_muscle.1.fq.gz
# clean up
rm tmp.RNA*
......@@ -7,10 +7,14 @@
#PBS -o 1.3.4.hisat.stdout
#PBS -e 1.3.4.hisat.stderr
cd /sfs/fs2/work-geomar7/smomw287/assembly_ver2.0/20_retinaRNA
hisat2 -p 12 -x $WORK/exp_retina/00_resources/v2HM_ht/v2HM_ht \
-1 ../15_RNAdata/data/4_merge/RNA_5_run2_guill_1.fq,../15_RNAdata/data/4_merge/RNA_5_run2_liver.1.fq,../15_RNAdata/data/4_merge/RNA_5_run2_muscle.1.fq,R28383.1p.fq.gz,R28384.1p.fq.gz,R28385.1p.fq.gz,R28387.1p.fq.gz,R28390.1p.fq.gz,R28391.1p.fq.gz,R28394.1p.fq.gz,R28399.1p.fq.gz,RAG9RX46.1p.fq.gz,RAG9RX47.1p.fq.gz,RAG9RX48.1p.fq.gz,RAG9RX49.1p.fq.gz,RAG9RX50.1p.fq.gz,RAG9RX51.1p.fq.gz,RAG9RX52.1p.fq.gz,RAG9RX53.1p.fq.gz,RAG9RX54.1p.fq.gz,RAG9RX55.1p.fq.gz,RPL17_01.1p.fq.gz,RPL17_02.1p.fq.gz,RPL17_04.1p.fq.gz,RPL17_16.1p.fq.gz,RPL17_17.1p.fq.gz,RPL17_18.1p.fq.gz \
-2 ../15_RNAdata/data/4_merge/RNA_5_run2_guill_2.fq,../15_RNAdata/data/4_merge/RNA_5_run2_liver.2.fq,../15_RNAdata/data/4_merge/RNA_5_run2_muscle.2.fq,R28383.2p.fq.gz,R28384.2p.fq.gz,R28385.2p.fq.gz,R28387.2p.fq.gz,R28390.2p.fq.gz,R28391.2p.fq.gz,R28394.2p.fq.gz,R28399.2p.fq.gz,RAG9RX46.2p.fq.gz,RAG9RX47.2p.fq.gz,RAG9RX48.2p.fq.gz,RAG9RX49.2p.fq.gz,RAG9RX50.2p.fq.gz,RAG9RX51.2p.fq.gz,RAG9RX52.2p.fq.gz,RAG9RX53.2p.fq.gz,RAG9RX54.2p.fq.gz,RAG9RX55.2p.fq.gz,RPL17_01.2p.fq.gz,RPL17_02.2p.fq.gz,RPL17_04.2p.fq.gz,RPL17_16.2p.fq.gz,RPL17_17.2p.fq.gz,RPL17_18.2p.fq.gz \
-S hisat_allRNA_v2_HM_noN.sam
cd $WORK/1-output/08_annotation/01_RNAtrimmed
samtools view -bS hisat_allRNA_v2_HM_noN.sam | samtools sort -o hisat_allRNA_v2_HM_noN.sorted
# align RNA to hard masked genome assembly
hisat2 -p 12 -x $WORK/1-output/07_final_assembly/ht_HM/ht_HM \
-1 RNA_guill.1.fq.gz,RNA_liver.1.fq.gz,RNA_muscle.1.fq.gz,R28383.1p.fq.gz,R28384.1p.fq.gz,R28385.1p.fq.gz,R28387.1p.fq.gz,R28390.1p.fq.gz,R28391.1p.fq.gz,R28394.1p.fq.gz,R28399.1p.fq.gz,RAG9RX46.1p.fq.gz,RAG9RX47.1p.fq.gz,RAG9RX48.1p.fq.gz,RAG9RX49.1p.fq.gz,RAG9RX50.1p.fq.gz,RAG9RX51.1p.fq.gz,RAG9RX52.1p.fq.gz,RAG9RX53.1p.fq.gz,RAG9RX54.1p.fq.gz,RAG9RX55.1p.fq.gz,RPL17_01.1p.fq.gz,RPL17_02.1p.fq.gz,RPL17_04.1p.fq.gz,RPL17_16.1p.fq.gz,RPL17_17.1p.fq.gz,RPL17_18.1p.fq.gz \
-2 RNA_guill.2.fq.gz,RNA_liver.2.fq.gz,RNA_muscle.2.fq.gz,R28383.2p.fq.gz,R28384.2p.fq.gz,R28385.2p.fq.gz,R28387.2p.fq.gz,R28390.2p.fq.gz,R28391.2p.fq.gz,R28394.2p.fq.gz,R28399.2p.fq.gz,RAG9RX46.2p.fq.gz,RAG9RX47.2p.fq.gz,RAG9RX48.2p.fq.gz,RAG9RX49.2p.fq.gz,RAG9RX50.2p.fq.gz,RAG9RX51.2p.fq.gz,RAG9RX52.2p.fq.gz,RAG9RX53.2p.fq.gz,RAG9RX54.2p.fq.gz,RAG9RX55.2p.fq.gz,RPL17_01.2p.fq.gz,RPL17_02.2p.fq.gz,RPL17_04.2p.fq.gz,RPL17_16.2p.fq.gz,RPL17_17.2p.fq.gz,RPL17_18.2p.fq.gz \
-S ../hisat_allRNA_HM_noN.sam
# sort resulting SAM file
cd ..
samtools view -bS hisat_allRNA_HM_noN.sam | samtools sort -o hisat_allRNA_HM_noN.sorted
......@@ -7,7 +7,11 @@
#PBS -o 1.3.5.Trinity.stdout
#PBS -e 1.3.5.Trinity.stderr
cd $WORK/assembly_ver2.0/20_retinaRNA/trinity_run
Trinity --genome_guided_bam ../hisat_allRNA_v2_HM_noN.sorted.bam\
cd $WORK/1-output/08_annotation
mkdir 02_trinity_run
cd 02_trinity_run
Trinity --genome_guided_bam ../hisat_allRNA_HM_noN.sorted.bam\
--genome_guided_max_intron 10000 \
--max_memory 50G --CPU 20
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment