echo $PATH
mkdir sequences
cd sequences/
wget -r \
--no-directories --no-parent \
-P . \
-A GCF_006149115.2_Oner_1.1_genomic.gff https://gannet.fish.washington.edu/panopea/berdahl-sockeye-salmon/genome/ \
--no-check-certificate
wget -r \
--no-directories --no-parent \
-P . \
-A GCF_006149115.2_Oner_1.1_genomic.fna https://gannet.fish.washington.edu/panopea/berdahl-sockeye-salmon/genome/ \
--no-check-certificate
head sequences/GCF_006149115.2_Oner_1.1_genomic.fna
Calculate chromosome lengths
awk '$0 ~ ">" {print c; c=0;printf substr($0,2,14) "\t"; } $0 !~ ">" {c+=length($0);} END { print c; }' \
sequences/GCF_006149115.2_Oner_1.1_genomic.fna \
| sed 's/Cr//g' \
| awk '{print $1"\t"$3}' \
| tail -n +2 \
> sequences/GCF_006149115.2_Oner_1.1_genomic-sequence-lengths.txt
head sequences/GCF_006149115.2_Oner_1.1_genomic-sequence-lengths.txt
Generate mRNA feature track from genomic_sequence
head sequences/GCF_006149115.2_Oner_1.1_genomic.gff
grep -e "Gnomon mRNA" -e "RefSeq mRNA" -e "cmsearch mRNA" -e "tRNAscan-SE mRNA" \
sequences/GCF_006149115.2_Oner_1.1_genomic.gff \
| /home/shared/bedtools2/bin/sortBed \
-faidx sequences/GCF_006149115.2_Oner_1.1_genomic-sequence-lengths.txt \
> sequences/GCF_006149115.2_Oner_1.1_mRNA.gff
head sequences/GCF_006149115.2_Oner_1.1_mRNA.gff
Download tag-seq data - gonad
mkdir raw-data-gonad/
cd raw-data-gonad/
wget -r \
--no-directories --no-parent \
-P . \
-A .fastq.gz https://gannet.fish.washington.edu/panopea/berdahl-sockeye-salmon/20220714-tagseq-gonad/ \
--no-check-certificate
Download tag-seq data - liver
mkdir raw-data-liver/
cd raw-data-liver/
wget -r \
--no-directories --no-parent \
-P . \
-A .fastq.gz https://gannet.fish.washington.edu/panopea/berdahl-sockeye-salmon/20220917-tagseq-liver/ \
--no-check-certificate