diff --git a/08-submission/gff-01-compose_gff.sh b/08-submission/gff-01-compose_gff.sh index c6e0f95551fed06ebcf6ce5dd1988d5619415ecc..38131a36c3de83fadc67ab7d987055d0e514184b 100644 --- a/08-submission/gff-01-compose_gff.sh +++ b/08-submission/gff-01-compose_gff.sh @@ -2,6 +2,9 @@ # compose the GFF3 file to prepare for ENA submission +module load conda +conda activate agat-1.4.1 + # set base and result directory BASE=/lisc/scratch/zoology/pycnogonum/genome/draft/annot_merge RESULT=/lisc/scratch/zoology/pycnogonum/genome/submission @@ -12,12 +15,18 @@ BRAKER_R1=$BASE/braker.gff BRAKER_R2=$BASE/braker2_unique_renamed_nocodon_intron.gff3 DENOVO=$BASE/denovo_txomes/overlap_translated.gff3 TRNASCAN=$BASE/../trnascan/trnascan.gff3 - +# Also add the g8324 gene as predicted by BRAKER3; manual inspection has determined that it should +# replace gene models PB.7650, at_DN0411, and at_DN0412 +g8324=$BASE/g8324.gff3 # navigate to output directory cd $RESULT || exit # merge the GFF3 files -cat $ISOSEQ $BRAKER_R1 $BRAKER_R2 $DENOVO $TRNASCAN > merged.gff3 +cat $ISOSEQ $BRAKER_R1 $BRAKER_R2 $DENOVO $TRNASCAN $g8324 > merged_mix.gff3 + +# remove the gene models for the 3 genes that are replaced by g8324 +{ echo "PB.7650"; echo "at_DN0411"; echo "at_DN0412"; } > kill_list +agat_sp_filter_feature_from_kill_list.pl --gff merged_mix.gff3 --kill_list kill_list -p gene -o merged.gff3 # rename pseudochromosomes 54-59 to 52-57 to reflect decontamination sed -i 's/pseudochrom_54/pseudochrom_52/g' merged.gff3