Hi,

You need to perform enrichment analysis of GO terms for DEGs over all GO terms to get p-values (can use BINGO). You can use just GO terms without p-values also but REVIGO will not give weightage based on p-values.

    #after running maker merged gff file was used and first round of filtration was carried out by AED score cutoff. 
    awk '{if($3=="mRNA")print$0}' ./base.all.gff |grep -v "trnascan"|grep  "est2genome"| grep "mRNA-1"| grep "_AED=0.00"|grep "Name"|awk '{split($9,a,";");print a[2]}'|awk '{split($1,a,"=");print a[2]}'> ./for_Augustus/MAKER_filter1_list

    grep -Fwf ./for_Augustus/MAKER_filter1_list ./base.all.gff > ./for_Augustus/MAKER_filter1.gff

    #remove mono exonic genes

     cat ./for_Augustus/MAKER_filter1.gff |awk '{split($9,a,";");print$3,a[2]}'|awk '{split($2,b,"=");print$1,b[2]}'| awk 'a ~ $0{print}; {a=$0}'|grep "^exon"| awk '{split($2,c,"-mRNA");print c[1]}'| sort -u > ./for_Augustus/non_monoExonic_MAKER_filter2.gff_list

    grep -Fwf ./for_Augustus/non_monoExonic_MAKER_filter2.gff_list ./for_Augustus/MAKER_filter2.gff > ./for_Augustus/MAKER_filter3.gff

    # get both three prime and five prime utr containing genes

    cat ./for_Augustus/MAKER_filter3.gff |awk '/three_prime_UTR/ {print$0}' |awk '{split($9,a,";");print$3,a[2]}'|awk '{split($2,b,"=");print$1,b[2]}'| awk '{split($2,c,"-mRNA");print c[1]}'| sort -u > ./for_Augustus/three_prime_utr_positive_gene_list

    cat ./for_Augustus/MAKER_filter3.gff |awk '/five_prime_UTR/ {print$0}' |awk '{split($9,a,";");print$3,a[2]}'|awk '{split($2,b,"=");print$1,b[2]}'| awk '{split($2,c,"-mRNA");print c[1]}'| sort -u > ./for_Augustus/five_prime_utr_positive_gene_list

    sort  ./for_Augustus/three_prime_utr_positive_gene_list ./for_Augustus/five_prime_utr_positive_gene_list |uniq -d > ./for_Augustus/five_three_prime_utr_positive_gene_list


    grep -Fwf ./for_Augustus/five_three_prime_utr_positive_gene_list ./for_Augustus/MAKER_filter3.gff > ./for_Augustus/MAKER_filter4.gff

# remove utrs from gff (optional, but I will suggest for running without errors)

awk '!/three_prime_UTR|five_prime_UTR/ {print$0}' ./MAKER_filter4_mod.gff > ./MAKER_filter4_mod_withoutUTR.gff


#convert to gb format (scripts are in augustus)

./scripts/gff2gbSmallDNA.pl ./MAKER_filter4_mod_withoutUTR.gff  /genome.fasta 10 ./MAKER_filter4_mod_withoutUTR.gb

# split test and training set (~1:5) (this is example, modify accordingly)

./scripts/randomSplit.pl ./MAKER_filter4_mod_withoutUTR.gb 200
grep -c LOCUS ./MAKER_filter4_mod_withoutUTR.gb*                                                               

./MAKER_filter4_mod_withoutUTR.gb:1279
./MAKER_filter4_mod_withoutUTR.gb.test:200
./MAKER_filter4_mod_withoutUTR.gb.train:1079

# create new file for your species (of interest) 

./scripts/new_species.pl --species=species

#etrain

./bin/etraining --species=species ./MAKER_filter4_mod_withoutUTR.gb.train

#test
./bin/augustus --species=species ./MAKER_filter4_mod_withoutUTR.gb.test | tee firsttest.out

#optimize
./scripts/optimize_augustus.pl --cpus=10 --species=species ./MAKER_filter4_mod_withoutUTR.gb.train --metapars=./config/species/species/species_metapars.cfg



#busco
./scripts/run_BUSCO.py -c 10 --long -sp species -o species_test -i /genome.fasta -l /BUSCO/busco/data/eukaryota_odb9 -m genome

Let me know if you face any problem with running these lines.

Best