软件安装
# Installing GETA (https://github.com/chenlianfu/geta)
#wget https://github.com/chenlianfu/geta/archive/refs/tags/v2.6.1.tar.gz -O ~/software/geta-2.6.1.tar.gz
tar zxf ~/software/geta-2.6.1.tar.gz -C /opt/biosoft/
echo 'PATH=$PATH:/opt/biosoft/geta-2.6.1/bin/' >> ~/.bashrc
source ~/.bashrc
## 使用GETA进行基因预测
mkdir -p /home/train/10.gene_prediction/GETA
cd /home/train/10.gene_prediction/GETA
ln -s ~/00.incipient_data/data_for_genome_assembling/assemblies_of_Malassezia_sympodialis/Malassezia_sympodialis.genome_V01.fasta genome.fasta
# wget ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/328/475/GCF_000328475.2_Umaydis521_2.0/GCF_000328475.2_Umaydis521_2.0_protein.faa.gz -P ~/00.incipient_data/data_for_gene_prediction_and_RNA-seq/
gzip -dc /home/train/00.incipient_data/data_for_gene_prediction_and_RNA-seq/GCF_000328475.2_Umaydis521_2.0_protein.faa.gz > homolog.fasta
perl -p -i -e 'if (m/^>/) { s/\s+.*//; s/\./_/g; }' homolog.fasta
ln -s ~/00.incipient_data/data_for_gene_prediction_and_RNA-seq/species-families.fa species-families.fa
cat ~/00.incipient_data/data_for_gene_prediction_and_RNA-seq/*.1.fastq > reads.1.fastq
cat ~/00.incipient_data/data_for_gene_prediction_and_RNA-seq/*.2.fastq > reads.2.fastq
geta.pl --cpu 8 --RM_species fungi --RM_lib species-families.fa --pe1 reads.1.fastq --pe2 reads.2.fastq --protein homolog.fasta --augustus_species malassezia_sympodialis --HMM_db /opt/biosoft/bioinfomatics_databases/Pfam/Pfam-AB.hmm --gene_prefix MS01Gene --out_prefix Malassezia_sympodialis_V01 genome.fasta &> geta.log #--protein homolog.fasta多选几个物种,用cat命令将其合并
cd ..
网友评论