#P. citri virgin females (VF) RNAspades v3.13.0 transcriptome assembly

cd /DATA/markop/
mkdir Pcitri_rnaspades

# had to rename CLC exported files to remove brackets e.g. from "PRO1976_S1_VF_2_GGAAGAGA-CGAGAGAA_L007_R1 (paired) trimmed (orphans).R1.fastq.gz" to "PRO1976_S1_VF_2_GGAAGAGA-CGAGAGAA_L007_R1_trimmed_orphans.R1.fastq.gz"

# untrusted-contigs are transcripts predicted from P citri genome -- will be used in the assembly only for gap closure and repeat resolution. 
# --untrusted-contigs ./input/Planococcus_citri_Pcitri.v1.cds_translationid.fa \
#doesn't seem to work properly; anyways might introduce errors?

/home/administrator/SPAdes-3.13.0-Linux/bin/spades.py --rna \
-t 32 \
-o ./output \
--ss-rf \
--pe1-fr --pe2-fr --pe3-fr --pe4-fr \
--pe1-1 /FITO_ws/markop/pcitri_trimmed/PRO1976_S1*paired.R1.fastq.gz \
--pe1-2 /FITO_ws/markop/pcitri_trimmed/PRO1976_S1*paired.R2.fastq.gz \
--pe1-s /FITO_ws/markop/pcitri_trimmed/PRO1976_S1*orphans.R1.fastq.gz \
--pe2-1 /FITO_ws/markop/pcitri_trimmed/PRO1976_S2*paired.R1.fastq.gz \
--pe2-2 /FITO_ws/markop/pcitri_trimmed/PRO1976_S2*paired.R2.fastq.gz \
--pe2-s /FITO_ws/markop/pcitri_trimmed/PRO1976_S2*orphans.R1.fastq.gz \
--pe3-1 /FITO_ws/markop/pcitri_trimmed/PRO1976_S3*paired.R1.fastq.gz \
--pe3-2 /FITO_ws/markop/pcitri_trimmed/PRO1976_S3*paired.R2.fastq.gz \
--pe3-s /FITO_ws/markop/pcitri_trimmed/PRO1976_S3*orphans.R1.fastq.gz \
--pe4-1 /FITO_ws/markop/pcitri_trimmed/PRO1976_S4*paired.R1.fastq.gz \
--pe4-2 /FITO_ws/markop/pcitri_trimmed/PRO1976_S4*paired.R2.fastq.gz \
--pe4-s /FITO_ws/markop/pcitri_trimmed/PRO1976_S4*orphans.R1.fastq.gz \


#produced 128.092 hard-filtered, 199067 normal-filtered, and 317306 soft-filtered transcripts.
#should be mapped to genome scaffolds