grep

grep：一种强大的文本搜索工具，它能使用正则表达式匹配模式搜索文本，并把匹配的行打印出来
格式： grep [options] pattern file
常见参数：[options]
-w：word 精确查找某个关键词pattern
-c：count 统计匹配成功的行的数量
-v：reverse 反向选择，即输出没有没有匹配的行
-n：number 显示匹配成功的行所在的行号
-r：recursion 从目录中递归查找pattern
-e：else 指定多个匹配模式
-f：file 从指定文件中读取要匹配的pattern
-i：ignore 忽略大小写

  1. $ less Data/example.gtf |column -t| grep 'gene' -w| head -n 5
  2. chr1  HAVANA   gene         1737    4275    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENSG00000223972";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "RP11-34P13.1";      level  2;  havana_gene  "OTTHUMG00000000961";
  3. chr1  HAVANA   gene         4226    19433   .  -  .  gene_id  "ENSG00000227232";  transcript_id  "ENSG00000227232";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "WASH5P";          transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "WASH5P";            level  2;  havana_gene  "OTTHUMG00000000958";
  4. chr1  HAVANA   gene         19417   20972   .  +  .  gene_id  "ENSG00000243485";  transcript_id  "ENSG00000243485";  gene_type  "processed_transcript";  gene_status  "KNOWN";  gene_name  "AL627309.6";      transcript_type  "processed_transcript";    transcript_status  "KNOWN";  transcript_name  "AL627309.6";        level  2;  havana_gene  "OTTHUMG00000000959";
  5. chr1  ENSEMBL  gene         20229   20366   .  +  .  gene_id  "ENSG00000221311";  transcript_id  "ENSG00000221311";  gene_type  "miRNA";                 gene_status  "KNOWN";  gene_name  "hsa-mir-1302-2";  transcript_type  "miRNA";                   transcript_status  "KNOWN";  transcript_name  "hsa-mir-1302-2";    level  3;
  6. chr1  HAVANA   gene         24417   25944   .  -  .  gene_id  "ENSG00000237613";  transcript_id  "ENSG00000237613";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "FAM138A";         transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "FAM138A";           level  2;  havana_gene  "OTTHUMG00000000960";
  1. $ less Data/example.gtf |column -t| grep 'gene' -wv | head -n 5
  2. chr1  ENSEMBL  UTR          1737    2090    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENST00000456328";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "RP11-34P13.1-201";  level  3;  havana_gene  "OTTHUMG00000000961";
  3. chr1  ENSEMBL  exon         1737    2090    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENST00000456328";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "RP11-34P13.1-201";  level  3;  havana_gene  "OTTHUMG00000000961";
  4. chr1  ENSEMBL  transcript   1737    4275    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENST00000456328";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "RP11-34P13.1-201";  level  3;  havana_gene  "OTTHUMG00000000961";
  5. chr1  HAVANA   exon         1873    1920    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENST00000450305";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "unprocessed_pseudogene";  transcript_status  "KNOWN";  transcript_name  "RP11-34P13-001";    level  2;  havana_gene  "OTTHUMG00000000961";  havana_transcript  "OTTHUMT00000002844";  ont          "PGO:0000005";
  6. chr1  HAVANA   transcript   1873    3533    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENST00000450305";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "unprocessed_pseudogene";  transcript_status  "KNOWN";  transcript_name  "RP11-34P13-001";    level  2;  havana_gene  "OTTHUMG00000000961";  havana_transcript  "OTTHUMT00000002844";  ont          "PGO:0000005";
  1. $ less Data/example.gtf |column -t| grep 'gene' -wc
  2. 20
  1. $ less Data/example.gtf |column -t| grep -w -e 'gene' -e 'UTR'| head -n 5
  2. chr1  ENSEMBL  UTR          1737    2090    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENST00000456328";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "RP11-34P13.1-201";  level  3;  havana_gene  "OTTHUMG00000000961";
  3. chr1  HAVANA   gene         1737    4275    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENSG00000223972";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "RP11-34P13.1";      level  2;  havana_gene  "OTTHUMG00000000961";
  4. chr1  ENSEMBL  UTR          2476    2584    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENST00000456328";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "RP11-34P13.1-201";  level  3;  havana_gene  "OTTHUMG00000000961";
  5. chr1  ENSEMBL  UTR          3084    4021    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENST00000456328";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "RP11-34P13.1-201";  level  3;  havana_gene  "OTTHUMG00000000961";
  6. chr1  ENSEMBL  UTR          4226    4561    .  -  .  gene_id  "ENSG00000227232";  transcript_id  "ENST00000438504";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "WASH5P";          transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "WASH5P-203";        level  3;  havana_gene  "OTTHUMG00000000958";
  1. $ cat >f.txt
  2. gene
  3. UTR
  4. start_codon
  5. stop_codon
  6. ^C
  7. $ less Data/example.gtf |column -t| grep -w -f f.txt |head -n 5
  8. chr1  ENSEMBL  UTR          1737    2090    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENST00000456328";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "RP11-34P13.1-201";  level  3;  havana_gene  "OTTHUMG00000000961";
  9. chr1  HAVANA   gene         1737    4275    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENSG00000223972";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "RP11-34P13.1";      level  2;  havana_gene  "OTTHUMG00000000961";
  10. chr1  ENSEMBL  UTR          2476    2584    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENST00000456328";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "RP11-34P13.1-201";  level  3;  havana_gene  "OTTHUMG00000000961";
  11. chr1  ENSEMBL  UTR          3084    4021    .  +  .  gene_id  "ENSG00000223972";  transcript_id  "ENST00000456328";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "RP11-34P13.1-201";  level  3;  havana_gene  "OTTHUMG00000000961";
  12. chr1  ENSEMBL  start_codon  4022    4024    .  +  0  gene_id  "ENSG00000223972";  transcript_id  "ENST00000456328";  gene_type  "protein_coding";        gene_status  "KNOWN";  gene_name  "RP11-34P13.1";    transcript_type  "protein_coding";          transcript_status  "KNOWN";  transcript_name  "RP11-34P13.1-201";  level  3;  havana_gene  "OTTHUMG00000000961";