mmseq2序列聚类

文章
标题：MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets
期刊：Nature Biotechnology
时间：2017

安装

source /hwfsxx1/ST_HN/P18Z10200N0423/huty/software/miniconda3_2/etc/profile.d/conda.sh
conda activate mmseq2
conda install bioconda::mmseqs2

/hwfsxx1/ST_HN/P18Z10200N0423/huty/software/miniconda3_2/envs/mmseq2/bin/mmseqs -h

使用
$符前加#脚本会报错，qsub option invalid

# merge
#mkdir 03_geneset
#touch 03_geneset/01_gene_merge.fna
#for i in `ls 02_assembly/`; do
#    cat 02_assembly/$i/gene/${i}_rename.fna >> 03_geneset/01_gene_merge.fna
#    echo -e "$i done..."
#done

# mmseqs pipline
source /hwfsxx1/ST_HN/P18Z10200N0423/huty/software/miniconda3_2/etc/profile.d/conda.sh
conda activate mmseq2

route="/hwfsxx1/ST_HN/P18Z10200N0423/huty/software/miniconda3_2/envs/mmseq2/bin"

sed -i 's/ #.*$//' 03_geneset/01_gene_merge.fna

# 2 BD
mkdir 03_geneset/02_DB
$route/mmseqs createdb 03_geneset/01_gene_merge.fna 03_geneset/02_DB/DB

# 3 cluster
mkdir 03_geneset/03_cluster
mkdir 03_geneset/03_tmp

$route/mmseqs cluster \
03_geneset/02_DB/DB \
03_geneset/03_cluster/cluster \
03_geneset/03_tmp \
--cov-mode 0 -c 0.8 --min-seq-id 0.9 --threads 24

rm -r 03_geneset/03_tmp

# 4 extract cluster info
mkdir 03_geneset/04_extract_info

$route/mmseqs createtsv \
03_geneset/02_DB/DB \
03_geneset/02_DB/DB \
03_geneset/03_cluster/cluster \
03_geneset/04_extract_info/cluter_info.tsv

# 5 extract rep fasta
mkdir 03_geneset/05_extract_rep

$route/mmseqs createsubdb \
03_geneset/03_cluster/cluster \
03_geneset/02_DB/DB \
03_geneset/05_extract_rep/cluster_rep

$route/mmseqs convert2fasta \
03_geneset/05_extract_rep/cluster_rep \
03_geneset/05_extract_rep/cluster_rep.fasta

更多：
使用 MMseq2 对序列聚类
MMseqs2软件cluster(聚类)