## step1:
mkdir sheep_db                                          ## 創建數據庫目錄

## step2: download the taxonomy information
kraken2-build --download-taxonomy --db sheep_db         ## 下載物種分類信息

## step3: download the human genome
kraken2-build --download-library human --db sheep_db      ## 下載人類基因組

## step4: download the virus genome
kraken2-build --download-library viral --db sheep_db       ## 下載病毒基因組

## step5: download the bacteria genome
kraken2-build --download-library bacteria --db sheep_db      ## 下載細菌基因組

## step6: add the sheep genome
kraken2-build --add-to-library /public/home/b20223040323/software/kraken2-2.1.3/sheep_ref/GCF_016772045.2_ARS-UI_Ramb_v3.0_genomic.fna --db sheep_db       ## 添加綿羊基因組

## step7: build database
kraken2-build --build --db sheep_db --threads 8              ## 構建數據庫

## step8:
kraken2 --db /public/home/b20223040323/software/kraken2-2.1.3/sheep_db --paired TUJ7_trim_1P.fastq.gz TUJ7_trim_2P.fastq.gz --report s_wrong.kraken.report --output s_wrong.kraken.out --use-names --threads 16    ## 運算

awk -F "\t" '$3 == "Ovis aries (taxid 9940)" {print $2}' sample_name.kraken.out > sample_name.sheep_reads   ## 提取reads 的 ID

seqtk subseq sample_name_trim_1P.fastq.gz sample_name.sheep_reads | gzip > sample_name_F_trim_1P.fastq.gz   ## 提取read1
seqtk subseq sample_name_trim_2P.fastq.gz sample_name.sheep_reads | gzip > sample_name_F_trim_2P.fastq.gz   ## 提取read2