Platform for Drug Discovery


snpEff


概要


    ANNOVARなどに次いで、最も良く使われるSNV/SNPに対するアノテーションプログラムの一つ。

メモ


  • 入出力ともにVCF形式
  • 変異の統計を出力してくれる。

出力例


  • $ grep -v "^#" data/ERA033295.snp_indel.filtered.snpeff.vcf | head
    
    1       14907   c256AF=0.478    A       G       179.14  VQSRTrancheSNP99.90to100.00     AC=7;AF=0.875;AN=8;BaseQRankSum=-0.118;DB;DP=12;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=7;MLEAF=0.875;MQ=21.91;MQ0=1;MQRankSum=0.825;QD=14.93;ReadPosRankSum=-1.296;SB=-9.980e+01;VQSLOD=-10.1756;culprit=MQ;set=FilteredInAll;EFF=DOWNSTREAM(MODIFIER|||||DDX11L1|processed_transcript|NON_CODING|ENST00000456328|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000450305|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000515242|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000518655|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000430492|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000537342|),INTRON(MODIFIER||||449|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000488147|),INTRON(MODIFIER||||471|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000541675|),INTRON(MODIFIER||||526|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000538476|),INTRON(MODIFIER||||555|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000423562|),INTRON(MODIFIER||||593|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000438504|) GT:AD:DP:GQ:PL  0/1:2,2:4:22:37,0,22    1/1:0,1:1:3:23,3,0      1/1:0,4:4:9:97,9,0        1/1:1,2:3:6:64,6,0
    
    1       14930   c257AF=0.480    A       G       170.2   VQSRTrancheSNP99.90to100.00     AC=7;AF=0.875;AN=8;BaseQRankSum=0.000;DB;DP=11;Dels=0.00;FS=0.000;HaplotypeScore=0.2498;MLEAC=7;MLEAF=0.875;MQ=22.08;MQ0=1;MQRankSum=0.480;QD=15.47;ReadPosRankSum=0.000;SB=-1.025e+02;VQSLOD=-9.7594;culprit=MQ;set=FilteredInAll;EFF=DOWNSTREAM(MODIFIER|||||DDX11L1|processed_transcript|NON_CODING|ENST00000456328|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000450305|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000515242|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000518655|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000430492|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000537342|),INTRON(MODIFIER||||449|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000488147|),INTRON(MODIFIER||||471|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000541675|),INTRON(MODIFIER||||526|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000538476|),INTRON(MODIFIER||||555|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000423562|),INTRON(MODIFIER||||593|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000438504|)    GT:AD:DP:GQ:PL  0/1:2,2:4:19:43,0,19    1/1:0,1:1:3:23,3,0      1/1:0,3:3:9:80,9,0        1/1:0,3:3:6:66,6,0
    
    1       15211   c269AF=0.634    T       G       19.49   LowQual AC=5;AF=0.833;AN=6;BaseQRankSum=-2.017;DB;DP=17;Dels=0.00;FS=0.000;HaplotypeScore=0.3263;MLEAC=5;MLEAF=0.833;MQ=11.55;MQ0=9;MQRankSum=0.421;QD=1.22;ReadPosRankSum=0.421;SB=-1.984e+01;set=FilteredInAll;EFF=DOWNSTREAM(MODIFIER|||||DDX11L1|processed_transcript|NON_CODING|ENST00000456328|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000450305|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000515242|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000518655|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000430492|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000537342|),INTRON(MODIFIER||||449|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000488147|),INTRON(MODIFIER||||471|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000541675|),INTRON(MODIFIER||||526|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000538476|),INTRON(MODIFIER||||555|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000423562|),INTRON(MODIFIER||||593|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000438504|)    GT:AD:DP:GQ:PL  1/1:0,6:6:3:23,3,0      1/1:1,2:3:3:23,3,0        ./.     0/1:5,2:7:11:11,0,56
    
    1       55085   c641AF=0.267    T       A       13.23   LowQual AC=2;AF=1.00;AN=2;DB;DP=6;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=2;MLEAF=1.00;MQ=11.26;MQ0=4;QD=3.31;SB=-2.401e+01;set=FilteredInAll;EFF=INTERGENIC(MODIFIER|||||||||)      GT:AD:DP:GQ:PL  1/1:2,2:4:3:43,3,0        ./.     ./.     ./.
    
    1       69270   c922AF=0.766    A       G       306.04  VQSRTrancheSNP99.90to100.00     AC=4;AF=1.00;AN=4;DB;DP=1996;DS;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=4;MLEAF=1.00;MQ=2.17;MQ0=1960;QD=0.31;SB=-1.182e-02;VQSLOD=-17.0814;culprit=MQ;set=FilteredInAll;EFF=SYNONYMOUS_CODING(LOW|SILENT|tcA/tcG|S60|305|OR4F5|protein_coding|CODING|ENST00000335137|exon_1_69091_70008)        GT:AD:DP:GQ:PL  1/1:411,83:496:21:176,21,0      ./.     ./.     1/1:383,116:500:21:166,21,0
    
    1       69511   c926AF=0.845    A       G       5119.01 VQSRTrancheSNP99.90to100.00     AC=4;AF=0.667;AN=6;BaseQRankSum=-0.195;DB;DP=333;Dels=0.00;FS=11.639;HaplotypeScore=4.0057;MLEAC=5;MLEAF=0.833;MQ=22.58;MQ0=89;MQRankSum=-1.730;QD=15.70;ReadPosRankSum=-0.056;SB=-1.510e+03;VQSLOD=-6.6827;culprit=MQ;set=FilteredInAll;EFF=NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|Aca/Gca|T141A|305|OR4F5|protein_coding|CODING|ENST00000335137|exon_1_69091_70008)  GT:AD:DP:GQ:PL    1/1:2,133:137:99:2239,191,0     0/0:3,1:6:3:0,3,37      ./.     1/1:3,185:189:99:2880,275,0
    
    1       82609   c1131AF=0.034   C       G       15.15   LowQual AC=2;AF=1.00;AN=2;DB;DP=2;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=2;MLEAF=1.00;MQ=36.50;MQ0=0;QD=7.58;SB=-3.701e+01;set=FilteredInAll;EFF=INTERGENIC(MODIFIER|||||||||)      GT:AD:DP:GQ:PL  ./.     1/1:0,2:2:3:45,3,0        ./.     ./.
    
    1       102951  c1611AF=0.134   C       T       15.15   LowQual AC=2;AF=1.00;AN=2;DB;DP=2;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=2;MLEAF=1.00;MQ=36.50;MQ0=0;QD=7.58;SB=-3.101e+01;set=FilteredInAll;EFF=INTRON(MODIFIER||||162|RP11-34P13.7.1|antisense|NON_CODING|ENST00000477740|),INTRON(MODIFIER||||915|RP11-34P13.7.1|antisense|NON_CODING|ENST00000466430|)      GT:AD:DP:GQ:PL  ./.     1/1:0,2:2:3:45,3,0      ./.     ./.
    
    1       104186  c1657AF=0.648   T       C       20.06   LowQual AC=4;AF=1.00;AN=4;DB;DP=3;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=4;MLEAF=1.00;MQ=17.56;MQ0=1;QD=6.69;SB=-1.182e-02;set=FilteredInAll;EFF=INTRON(MODIFIER||||162|RP11-34P13.7.1|antisense|NON_CODING|ENST00000477740|),INTRON(MODIFIER||||915|RP11-34P13.7.1|antisense|NON_CODING|ENST00000466430|)      GT:AD:DP:GQ:PL  ./.     ./.     1/1:0,1:1:3:27,3,0      1/1:1,1:2:3:26,3,0
    
    1       104281  c1667AF=0.123   T       C       20.06   LowQual AC=4;AF=1.00;AN=4;DB;DP=3;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=4;MLEAF=1.00;MQ=17.56;MQ0=1;QD=10.03;SB=-1.182e-02;set=FilteredInAll;EFF=INTRON(MODIFIER||||162|RP11-34P13.7.1|antisense|NON_CODING|ENST00000477740|),INTRON(MODIFIER||||915|RP11-34P13.7.1|antisense|NON_CODING|ENST00000466430|)     GT:AD:DP:GQ:PL  ./.     ./.     1/1:0,1:1:3:27,3,0      1/1:0,1:1:3:26,3,0
    • header行は除外して先頭10行。
  • 出力されるVCF上記の内8列目の"EFF="以降がsnpEffによってつかされる情報。
    • $ grep -v "^#" data/ERA033295.snp_indel.filtered.snpeff.vcf | head | cut -f 8 | sed -n 's/^.\+\(EFF=.*\)$/\1/p'
      
      EFF=DOWNSTREAM(MODIFIER|||||DDX11L1|processed_transcript|NON_CODING|ENST00000456328|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000450305|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000515242|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000518655|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000430492|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000537342|),INTRON(MODIFIER||||449|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000488147|),INTRON(MODIFIER||||471|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000541675|),INTRON(MODIFIER||||526|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000538476|),INTRON(MODIFIER||||555|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000423562|),INTRON(MODIFIER||||593|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000438504|)
      
      EFF=DOWNSTREAM(MODIFIER|||||DDX11L1|processed_transcript|NON_CODING|ENST00000456328|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000450305|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000515242|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000518655|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000430492|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000537342|),INTRON(MODIFIER||||449|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000488147|),INTRON(MODIFIER||||471|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000541675|),INTRON(MODIFIER||||526|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000538476|),INTRON(MODIFIER||||555|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000423562|),INTRON(MODIFIER||||593|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000438504|)
      
      EFF=DOWNSTREAM(MODIFIER|||||DDX11L1|processed_transcript|NON_CODING|ENST00000456328|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000450305|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000515242|),DOWNSTREAM(MODIFIER|||||DDX11L1|transcribed_unprocessed_pseudogene|NON_CODING|ENST00000518655|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000430492|),DOWNSTREAM(MODIFIER|||||WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000537342|),INTRON(MODIFIER||||449|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000488147|),INTRON(MODIFIER||||471|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000541675|),INTRON(MODIFIER||||526|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000538476|),INTRON(MODIFIER||||555|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000423562|),INTRON(MODIFIER||||593|WASH7P|unprocessed_pseudogene|NON_CODING|ENST00000438504|)
      
      EFF=INTERGENIC(MODIFIER|||||||||)
      
      EFF=SYNONYMOUS_CODING(LOW|SILENT|tcA/tcG|S60|305|OR4F5|protein_coding|CODING|ENST00000335137|exon_1_69091_70008)
      
      EFF=NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|Aca/Gca|T141A|305|OR4F5|protein_coding|CODING|ENST00000335137|exon_1_69091_70008)
      
      EFF=INTERGENIC(MODIFIER|||||||||)
      
      EFF=INTRON(MODIFIER||||162|RP11-34P13.7.1|antisense|NON_CODING|ENST00000477740|),INTRON(MODIFIER||||915|RP11-34P13.7.1|antisense|NON_CODING|ENST00000466430|)
      
      EFF=INTRON(MODIFIER||||162|RP11-34P13.7.1|antisense|NON_CODING|ENST00000477740|),INTRON(MODIFIER||||915|RP11-34P13.7.1|antisense|NON_CODING|ENST00000466430|)
      
      EFF=INTRON(MODIFIER||||162|RP11-34P13.7.1|antisense|NON_CODING|ENST00000477740|),INTRON(MODIFIER||||915|RP11-34P13.7.1|antisense|NON_CODING|ENST00000466430|)

論文


参考情報


Contact us
Copyright © 2009-2017 National Institute of Genetics  [Site Policy] [Privacy Policy]