0701 D3Similarity done

总结

记录

# 172.21.85.12 /home/zjxu/zzy/hsbd/similarity/analysis
# 先统计2-32这31个靶点
for i in {2..32};do awk '$3>0.9 {print}' ../data/hsbd-1894mol-2d_results-sorted2dx3d_tgt${i}.txt|sed "s/^/target$i /" >>2-32_up0.9.txt;done
for i in {2..32};do awk '$3>0.8 {print}' ../data/hsbd-1894mol-2d_results-sorted2dx3d_tgt${i}.txt|sed "s/^/target$i /" >>2-32_up0.8.txt;done
for i in {2..32};do awk '$3>0.7 {print}' ../data/hsbd-1894mol-2d_results-sorted2dx3d_tgt${i}.txt|sed "s/^/target$i /" >>2-32_up0.7.txt;done


(base) [zjxu@R820 analysis]$ awk '{print $2}' 2-32_up0.9.txt |sort|uniq |wc -l
34


(base) [zjxu@R820 analysis]$ awk '{print $1}' 2-32_up0.9.txt |sort|uniq|wc -l
4


for a in `cat 34mol_index`;do c=`grep TCMID ../5/${a}.mol2`;sed -i "s/\b$a\b/$c/g" test.txt;done


for a in `cat result/34mol_index`;do c=`grep TCMID ../5/${a}.mol2`;sed -i "s/\b$a\b/$c/g" result.txt;done

• 5里的名字和后面交的（6-32 / 2-4）不是一样的，检查！！！！

for a in `cat 34mol_index`;do c=`grep TCMID ../../6/${a}.mol2`;sed -i "s/\b$a\b/$c/g" test2.txt;done


for a in `cat result/34mol_index`;do c=`grep TCMID ../../6/${a}.mol2`;sed -i "s/\b$a\b/$c/g" result.txt;done

# 第一个靶点阳性化合物多（400+），额外统计
# 由于切分了任务，要先把名字换回去
for i in `cat index`;do for a in {1..200};do c=`grep TCMID ../${i}/MOL_${a}.mol2`;sed -i "s/\bMOL_${a}\b/$c/g" hsbd-mol-list-${i}_results-sorted2dx3d_tgt1.txt;done;done
for a in {201..294};do c=`grep TCMID ../1894/MOL_${a}.mol2`;sed -i "s/\bMOL_${a}\b/$c/g" hsbd-mol-list-1894_results-sorted2dx3d_tgt1.txt;done


for i in `cat index`;do awk '$3>0.9 {print}' hsbd-mol-list-${i}_results-sorted2dx3d_tgt1.txt|sed "s/^/target1 /" >>1_up0.9.txt;done
for i in `cat index`;do awk '$3>0.8 {print}' hsbd-mol-list-${i}_results-sorted2dx3d_tgt1.txt|sed "s/^/target1 /" >>1_up0.8.txt;done
for i in `cat index`;do awk '$3>0.7 {print}' hsbd-mol-list-${i}_results-sorted2dx3d_tgt1.txt|sed "s/^/target1 /" >>1_up0.7.txt;done


(base) [zjxu@R820 analysis]$ awk '{print $2}' 1_up0.9.txt |sort|uniq|wc -l
16
(base) [zjxu@R820 analysis]$ awk '{print $2}' 1_up0.8.txt |sort|uniq|wc -l
51
(base) [zjxu@R820 analysis]$ awk '{print $2}' 1_up0.7.txt |sort|uniq|wc -l
117

# 统计库里的阳性化合物数量
(base) [zjxu@R820 data]$ for i in {1..32};do wc -l ~/xbzhang/2019-nCov-final/D3Similarity/D3Similarity-yqyang/VS/target-id/molall_${i}.lst>>count;done
(base) [zjxu@R820 data]$ awk '{print $1}' count |awk '{sum+=$1}END{print sum}' 
617

# 找到36个化合物的结构
/home/zjxu/zzy/hsbd/similarity/analysis/36mol
for a in `cat 1894index`;do c=`grep TCMID ../../6/MOL_${a}.mol2`;mv 1894mol/ MOL_${a}-opt.mol2 1894mol/${c}.mol2;done


# 由于有化合物和多个靶标的阳性化合物像，所以没法直接替换，用了笨办法,uniq -c -d看有哪些化合物属于上述情况，然后手动把他们的靶标修改成 targetAandB 的形式
# 之后，批量替换mol2文件中存储名字的行（第二行）
for i in `cat 36index`;do c=`grep $i pro-mol.txt`;sed "2s/.*/$c/" 36/$i.mol2 >>name-36.mol2;done