平時(shí)我們對(duì)每個(gè)基因組做了BUSCO,但是官方提供的畫(huà)圖代碼很難用,所以決定自己提取出BUSCO的結(jié)果并進(jìn)行畫(huà)圖,這一串代碼就可以批量從BUSCO的結(jié)果中提取出我們想要的結(jié)果:
# 提取數(shù)字并寫(xiě)入txt文件
echo "voucher C S D F M" > busco_summary_table.txt;
for i in $(cat list.txt); do
filename="${i}/busco/short_summary.specific.agaricales_odb10.busco.txt"
if [ -f "$filename" ]; then
# 提取數(shù)據(jù)
data=$(grep -oP 'C:([\d.]+)%\[S:([\d.]+%),D:([\d.]+)%\],F:([\d.]+)%,M:([\d.]+)%,n:\d+' "$filename" | awk -F'[:,%[]' '{print $2, $5, $8, $11, $14}')
# 將數(shù)據(jù)寫(xiě)入表格
echo "${i} $data" >> busco_summary_table; else
echo "${i} There is no BUSCO results in ${i}!" >> busco_summary_table;
fi
done