1.提取这298个lncRNAs的symbol
cat lncRNAs#部分lncRNAs
LINC02240
AC021723
AP003352
AC087393
AC006441
AC093503
AL121985
AC093484
AC145207
AC091180
2. 由starbase API数据库进行下载
time cat x1.csv |while read id;do echo $id;\
curl http://starbase.sysu.edu.cn/api/miRNATarget/?assembly=hg19\&geneType=lncRNA\&miRNA=all\&clipExpNum=0\°raExpNum=0\&pancancerNum=0\&programNum=1\&program=PITA,RNA22\&target=${id}\&cellType=all > lncrna-mirna/$id.txt;
done
不到一分钟将全部lncRNA可能结合的miRNA下载到本地文件夹,文件大小为520B的都没有查询到可能结合的靶基因miRNA
ls -lh lncrna-mirna/
total 1.4M
-rw-rw-r-- 1 fqq1024 fqq1024 520 Aug 24 09:11 AC000120.txt
-rw-rw-r-- 1 fqq1024 fqq1024 520 Aug 24 09:11 AC002398.txt
-rw-rw-r-- 1 fqq1024 fqq1024 520 Aug 24 09:11 AC004543.txt
-rw-rw-r-- 1 fqq1024 fqq1024 520 Aug 24 09:11 AC004690.txt
-rw-rw-r-- 1 fqq1024 fqq1024 520 Aug 24 09:11 AC004784.txt
3.将所有的lncRNA靶基因进行合并整理
每个文件都有这么一个类似的表头
cat ZNF32-AS1.txt
#please cite:
#1.Zhou KR, Liu S, Cai L, Bin L, et al. ENCORI: The Encyclopedia of RNA Interactomes.
#2.Li JH, et al.starBase v2.0: decoding miRNA-ceRNA, miRNA-ncRNA and protein-RNA interaction networks from large-scale CLIP-Seq data , Nucleic Acids Res. 2014 Jan;42:D92-7.
miRNAid miRNAname geneID geneName geneType chromosome start end strand clipExpNum degraExpNum RBP merClass miRseq align targetSeq pancancerNum
The "target" parameter haven't been set correctly! Or the input of "target" parameter is not available!
合并所有的txt文件,并提取靶基因信息
cat *.txt > merge.txt
#删除注释行,删除行头,删除没有target的报错信息,
#最后获取第2例miRNA,第4例lncRNA
cat merge.txt |grep -v "#"|grep -v "chromosome"|grep -v "target"|cut -f2,4|less -SN
1 hsa-miR-588 ACTA2-AS1
2 hsa-miR-4701-5p ACTA2-AS1
3 hsa-miR-378c ACTA2-AS1
4 hsa-miR-378a-3p ACTA2-AS1
5 hsa-miR-422a ACTA2-AS1
6 hsa-miR-378h ACTA2-AS1
7 hsa-miR-378i ACTA2-AS1
8 hsa-miR-378d ACTA2-AS1
9 hsa-miR-378f ACTA2-AS1
10 hsa-miR-378b ACTA2-AS1
11 hsa-miR-378e ACTA2-AS1
12 hsa-miR-4428 ACTA2-AS1
13 hsa-miR-3167 C21orf62-AS1
14 hsa-miR-876-5p C21orf62-AS1
15 hsa-miR-627-5p C21orf62-AS1
网友评论