text 集成到wi-nf / SnpEff注释中

Posted 2021-05-03

# OUT PUT FILES::::

# elegans_transcript_WS258.bed ( COMES FROM /elegans_genes_WS258.bb )
# elegans_gene_WS258.bed (remember; comes from GFF3)
# FASTA! c_elegans.PRJNA13758.WS245.genomic.fa (ftp://ftp.wormbase.org/pub/wormbase/releases/WS258/species/c_elegans/PRJNA13758/)

# Download gene file
wget ftp://ftp.wormbase.org/pub/wormbase/releases/WS258/MULTI_SPECIES/hub/elegans/elegans_genes_WS258.bb
# Bit of a misnomer --> These are transcripts
BigBedToBed elegans_genes_WS258.bb elegans_transcripts_WS258.bed

# brew install igvtools
igvtools index elegans_transcripts_WS258.bed

# get GFF
wget ftp://ftp.wormbase.org/pub/wormbase/releases/WS258/species/c_elegans/PRJNA13758/c_elegans.PRJNA13758.WS258.annotations.gff3.gz

# Generate gene track ~ Required bedops + bedtools
sortBed -i c_elegans.PRJNA13758.WS258.annotations.gff3.gz | gff2bed gff - | grep 'locus'  |\
gawk '{ match($0, "locus=([^;\t]+)", f); print $1 "\t" $2 "\t" $3 "\t" f[1] "\t" 100 "\t" $6 "\t" $2 "\t" $3  "\t0\t1\t" $3 - $2 - 1 "\t0"  }' > elegans_gene.WS258.bed