RNA-seq数据分析完全指北-04：创建本地blast库分析物种组成

## 下载安装包
wget https://ftp.ncbi.nlm.nih.gov/blast/executables/LATEST/ncbi-blast-2.11.0+-x64-linux.tar.gz
tar zxvf ncbi-blast-2.11.0+-x64-linux.tar.gz    ## 解压
mv ncbi-blast-2.11.0+ ~/biosoft/blast/    ## 移动到自己常用的软件目录并改名

vim ~/.bashrc
## 在最后一行加上如下信息，记得改成自己的路径
export PATH=/home/csw/biosoft/blast/bin:$PATH

## 如果不会使用vim编辑器，那就运行如下命令
echo "export PATH=/home/csw/biosoft/blast/bin:\$PATH" >> ~/.bashrc

## 让配置生效
source ~/.bashrc

## 创建.ncbirc文件
vim ~/.ncbirc

## 将下列内容粘贴进去即可，记得改成自己的路径
# Start the section for BLAST configuration

[BLAST]

# Specifies the path where BLAST databases are installed
BLASTDB=/home/csw/reference/linux/blast

# Specifies the data sources to use for automatic resolution

# for sequence identifiers
DATA_LOADERS=blastdb

# Specifies the BLAST database to use resolve protein sequences
BLASTDB_PROT_DATA_LOADER=/home/csw/reference/linux/blast/nr

# Specifies the BLAST database to use resolve protein sequences
BLASTDB_NUCL_DATA_LOADER=/home/csw/reference/linux/blast/nt

BATCH_SIZE=10G

# Windowmasker settings

[WINDOW_MASKER]
WINDOW_MASKER_PATH=/home/csw/reference/linux/blast/windowmasker

# end of file

## update_blastdb --showall可以显示所有可以安装的库
nohup update_blastdb --decompress nt &    ## 后台下载，在下载中断后会自动断点续传，--decompress表示会在下载后自动解压
## 慢慢等吧，文件挺大的
## 其他参数参考update_blastdb --help

ln -s ~/projects/rna-seq/ ./
seqkit sample -n 10000 SRR11178353_1.fastq.gz | seqkit fq2fa - > SRR11178353_1.rd.fa
seqkit sample -n 10000 SRR11178353_2.fastq.gz | seqkit fq2fa - > SRR11178353_2.rd.fa

nohup blastn -query SRR11178353_1.rd.fa -out SRR11178353_1.blast -db nt -outfmt "6 std scomname" -evalue 1e-5 -num_threads 16 -qcov_hsp_perc 50.0 -num_alignments 5 &
nohup blastn -query SRR11178353_2.rd.fa -out SRR11178353_2.blast -db nt -outfmt "6 std scomname" -evalue 1e-5 -num_threads 16 -qcov_hsp_perc 50.0 -num_alignments 5 &