scripts/STAR_mapToGenomeAll_commands.txt
Version 1

_p_SUSPHIRE/_I_T31_mealybug/_S_P4_Pcitri_genome_extSamples/_A_01_mapToGenomeAll-STAR/

SEEK ID: https://fairdomhub.org/data_files/5899?version=1

Filename: scripts/STAR_mapToGenomeAll_commands.txt  Download

Format: Plain text document

Size: 7.82 KB

#mapping P. citri RNA-Seq samples from SUSPHIRE, Edinburgh, SRA to P. citri Genome v1

cd /DATB/markop/SUSPHIRE/
mkdir Pcitri_mapToGenomeAll
cd Pcitri_mapToGenomeAll
mkdir fastq

#trimming
cd fastq
trim_galore --paired --retain_unpaired --cores 8 --dont_gzip *.fastq.gz
trim_galore --cores 8 --dont_gzip --polyA *_unpaired_*.fq
trim_galore --paired --retain_unpaired --cores 8 --dont_gzip --polyA *_val_*.fq


#build P citri genome index 
# the genome is 486392826 nt long and has 17212 scaffolds, therefore genomeChrBinNbits was set to 15 [log2(486392826/17202)=14.8]

cd /DATB/markop/SUSPHIRE/Pcitri_mapToGenomeAll

mkdir star_genome_index
cp -avr /DATB/markop/SUSPHIRE/Pcitri_rnaspades_alldata/input/Planococcus_citri_Pcitri.v1.gff3 ./star_genome_index/
cp -avr /DATB/markop/SUSPHIRE/Pcitri_rnaspades_alldata/input/Planococcus_citri_Pcitri.v1.scaffolds.fa ./star_genome_index/

STAR --runThreadN 30 --runMode genomeGenerate \
--genomeDir ./star_genome_index \
--genomeFastaFiles ./star_genome_index/Planococcus_citri_Pcitri.v1.scaffolds.fa \
--sjdbGTFtagExonParentTranscript Parent \
--sjdbGTFfile ./star_genome_index/Planococcus_citri_Pcitri.v1_nomod.gtf \
--genomeChrBinNbits 15 \
--genomeSAindexNbases 13 \
--limitGenomeGenerateRAM=200000000000

##mapping short RNA-Seq reads to genome

mkdir STAR_mapToGenome

#ulimit default 1024
ulimit -n 10000

#load genome 
STAR --genomeLoad LoadAndExit --genomeDir ./star_genome_index

#SUSPHIRE dataset

#MF_08 PE
STAR \
--runMode alignReads \
--runThreadN 32 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/MF_08_1_val_1_val_1.fq ./fastq/MF_08_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_MF_08_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

# #MF_08 SE
# because not many reads map as SE, we decided to skip this part 

# cat ./fastq/MF_08_1_unpaired_1_trimmed.fq  ./fastq/MF_08_1_val_1_unpaired_1.fq  > ./fastq/MF_08_unpaired_1.fq
# cat ./fastq/MF_08_2_unpaired_2_trimmed.fq  ./fastq/MF_08_2_val_2_unpaired_2.fq  > ./fastq/MF_08_unpaired_2.fq

# STAR \
# --runMode alignReads \
# --runThreadN 32 \
# --genomeDir ./star_genome_index \
# --readFilesIn ./fastq/MF_08_unpaired_1.fq \
# --outFileNamePrefix ./STAR_mapToGenome/STAR_MF_08_SE1_ \
# --outSAMtype BAM SortedByCoordinate \
# --quantMode GeneCounts

# STAR \
# --runMode alignReads \
# --runThreadN 32 \
# --genomeDir ./star_genome_index \
# --readFilesIn ./fastq/MF_08_unpaired_2.fq \
# --outFileNamePrefix ./STAR_mapToGenome/STAR_MF_08_SE2_ \
# --outSAMtype BAM SortedByCoordinate \
# --quantMode GeneCounts


#MF_09 PE
STAR \
--runMode alignReads \
--runThreadN 32 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/MF_09_1_val_1_val_1.fq ./fastq/MF_09_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_MF_09_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#MF_10 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/MF_10_1_val_1_val_1.fq ./fastq/MF_10_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_MF_10_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#MF_11 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/MF_11_1_val_1_val_1.fq ./fastq/MF_11_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_MF_11_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#VF_02 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/VF_02_1_val_1_val_1.fq ./fastq/VF_02_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_VF_02_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#VF_03 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/VF_03_1_val_1_val_1.fq ./fastq/VF_03_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_VF_03_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#VF_05 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/VF_05_1_val_1_val_1.fq ./fastq/VF_05_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_VF_05_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#VF_06 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/VF_06_1_val_1_val_1.fq ./fastq/VF_06_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_VF_06_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts


#Edinburgh dataset

#PC_ALL_1 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/PC_ALL_1_1_val_1_val_1.fq ./fastq/PC_ALL_1_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_PC_ALL_1_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#PC_F_1 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/PC_F_1_1_val_1_val_1.fq ./fastq/PC_F_1_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_PC_F_1_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#PC_F_2 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/PC_F_2_1_val_1_val_1.fq ./fastq/PC_F_2_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_PC_F_2_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#PC_F_3 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/PC_F_3_1_val_1_val_1.fq ./fastq/PC_F_3_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_PC_F_3_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#PC_M_1 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/PC_M_1_1_val_1_val_1.fq ./fastq/PC_M_1_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_PC_M_1_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#PC_M_2 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/PC_M_2_1_val_1_val_1.fq ./fastq/PC_M_2_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_PC_M_2_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#PC_M_3 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/PC_M_3_1_val_1_val_1.fq ./fastq/PC_M_3_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_PC_M_3_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts


#SRA datasets

#SRR3239563 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/SRR3239563_1_val_1_val_1.fq ./fastq/SRR3239563_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_SRR3239563_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#SRR848068 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/SRR848068_1_val_1_val_1.fq ./fastq/SRR848068_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_SRR848068_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts

#SRR921633 PE
STAR \
--runMode alignReads \
--runThreadN 24 \
--genomeDir ./star_genome_index \
--readFilesIn ./fastq/SRR921633_1_val_1_val_1.fq ./fastq/SRR921633_2_val_2_val_2.fq \
--outFileNamePrefix ./STAR_mapToGenome/STAR_SRR921633_PE_ \
--outSAMtype BAM SortedByCoordinate \
--quantMode GeneCounts


#unload genome
STAR --genomeLoad Remove --genomeDir ./star_genome_index

#remove fq input files to release disk space
rm -rf ./fastq/*.fq
rm -rf ./fastq/*.fq.gz
help Creators and Submitter
Creator
Submitter
Activity

Views: 507   Downloads: 40

Created: 16th May 2022 at 11:28

Last updated: 6th Nov 2024 at 15:26

help Attributions

None

Version History

Version 1 (earliest) Created 16th May 2022 at 11:28 by Marko Petek

No revision comments

Powered by
(v.1.18.0)