#http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE53197 #BioProject PRJNA231088 #SRA SRP033660 # In each folder: cat > SRA.list wget -c -nv -i SRA.list sratoolkit.2.4.2-ubuntu64/bin/fastq-dump --gzip --split-files *.sra zcat SR*gz | perl -lne 's/^(\S)SRR\S+ /$1/; s/ length=\d+/\/1/; print' | gzip > 1.fq.gz rm -f SR* trinityrnaseq-2.0.2/Trinity --seqType fq --single 1.fq.gz \ --CPU 10 --max_memory 40G --trimmomatic --full_cleanup --output trinity --normalize_reads transcripts2cdsCPP.pl -n 50 Trinity.fasta