原理

http://www.imeta.science/iMeta/Papers/10Slide/imt2.55cn.pdf

结果

文件上传

scp -P 20328 -r /Users/mszeng/Desktop/work/other/泛基因组/pp_genome [email protected]:~/pangenome/data

scp -P 20328 -r /Users/mszeng/Desktop/work/other/泛基因组/all_genome [email protected]:~/pangenome/data

prokka

参考链接：https://indexofire.github.io/pathongs/book/C03_Genome-Annotation/01_prokka/

https://github.com/tseemann/prokka

准备

conda create -n pangenome #创建环境
conda activate pangenome
conda install -c conda-forge -c bioconda -c defaults  prokka #安装

cd pangenome
mkdir prokka

测试

cd /pangenome/data/pp_genome/ncbi_dataset/data/GCF_000597985.1
prokka GCF_000597985.1_ASM59798v1_genomic.fna
#测试结果
(pangenome) zms@shpc-49506-instance-6QslimRj:~/pangenome/data/pp_genome/ncbi_dataset/data/GCF_000597985.1/PROKKA_06132024$ cat *.txt
organism: Genus species strain
contigs: 1
bases: 5828436
CDS: 5024
rRNA: 39
repeat_region: 2
tRNA: 110
tmRNA: 1

运行脚本

prokka_Paenibacillus_polymyxa.sh

#!/bin/bash

threads_num=10

source ~/anaconda3/etc/profile.d/conda.sh
conda activate pangenome

# 建立结果文件夹
cd ~/pangenome
mkdir -p 01prokka_o_Paenibacillus_polymyxa

echo "#### Step 1: prokka注释 ####"
echo "##### run prokka #####"
cd ~/pangenome/data/pp_genome/ncbi_dataset/data/
for i in *
do
        if [ -d ${i} ];then
                if [ ! -d ~/pangenome/01prokka_o_Paenibacillus_polymyxa/${i} ];then
                {
                        echo "### Sample" ${i} "run prokka... ###"
                        cd ${i}
                        prokka --outdir ~/pangenome/01prokka_o_Paenibacillus_polymyxa/${i} --species Paenibacillus_polymyxa --prefix ${i} *.fna --cpus ${threads_num}
                        cd ..
                }
                else
                        echo "### ${i} has run prokka ###"
                fi
        fi
done
echo "##### Step 1: prokka done #####"

#添加可执行权限
chmod a+x prokka_Paenibacillus_polymyxa.sh
#运行
nohup ./prokka_Paenibacillus_polymyxa.sh &
#运行情况
ps aux | grep prokka

prokka_Paenibacillus.sh

#!/bin/bash

threads_num=15

source ~/anaconda3/etc/profile.d/conda.sh
conda activate pangenome

# 建立结果文件夹
cd ~/pangenome
mkdir -p 01prokka_o_Paenibacillus

echo "#### Step 1: prokka注释 ####"
echo "##### run prokka #####"
cd ~/pangenome/data/all_genome/ncbi_dataset/data/
for i in *
do
        if [ -d ${i} ];then
                if [ ! -d ~/pangenome/01prokka_o_Paenibacillus/${i} ];then
                {
                        echo "### Sample" ${i} "run prokka... ###"
                        cd ${i}
                        prokka --outdir ~/pangenome/01prokka_o_Paenibacillus/${i} --species Paenibacillus_polymyxa --prefix ${i} *.fna --cpus ${threads_num}
                        cd ..
                }
                else
                        echo "### ${i} has run prokka ###"
                fi
        fi
done
echo "##### Step 1: prokka done #####"

#添加可执行权限
chmod a+x prokka_Paenibacillus.sh
#运行
nohup ./prokka_Paenibacillus.sh > prokka_Paenibacillus.out &
#运行情况
ps aux | grep prokka