Difference between revisions of "VAT Commands in Exercise"

From Statistical Genetics Courses

Jump to: navigation, search
Line 2: Line 2:
  
 
==VAT Commands in Exercise==
 
==VAT Commands in Exercise==
<pre> vtools -h
+
<pre>  
 +
vtools -h
 
  vtools init VATDemo
 
  vtools init VATDemo
 
  vtools import *.vcf.gz --var_info DP filter --geno_info DP_geno --build hg18 -j1
 
  vtools import *.vcf.gz --var_info DP filter --geno_info DP_geno --build hg18 -j1
Line 15: Line 16:
 
  vtools show fields
 
  vtools show fields
 
  vtools select variant --count
 
  vtools select variant --count
  vtools show genotypes &gt; GenotypeSummary.txt
+
  vtools show genotypes > GenotypeSummary.txt
 
  head GenotypeSummary.txt
 
  head GenotypeSummary.txt
 
  vtools output variant "max(DP)" "min(DP)" "avg(DP)" "stdev(DP)" "lower_quartile(DP)" "upper_quartile(DP)" --header
 
  vtools output variant "max(DP)" "min(DP)" "avg(DP)" "stdev(DP)" "lower_quartile(DP)" "upper_quartile(DP)" --header
Line 23: Line 24:
 
  vtools show fields
 
  vtools show fields
 
  vtools show table variant
 
  vtools show table variant
  vtools update variant --from_stat 'totalGD10=#(GT)' 'numGD10=#(alt)' 'hetGD10=#(het)' 'homGD10=#(hom)' 'otherGD10=#(other)' 'mafGD10=maf()' --genotypes "DP_geno &gt; 10"
+
  vtools update variant --from_stat 'totalGD10=#(GT)' 'numGD10=#(alt)' 'hetGD10=#(het)' 'homGD10=#(hom)' 'otherGD10=#(other)' 'mafGD10=maf()' --genotypes "DP_geno > 10"
 
  vtools show fields
 
  vtools show fields
 
  vtools show table variant
 
  vtools show table variant
Line 30: Line 31:
 
  vtools phenotype --set "RACE=1" --samples "filename like 'CEU%'"
 
  vtools phenotype --set "RACE=1" --samples "filename like 'CEU%'"
 
  vtools show samples --limit 10
 
  vtools show samples --limit 10
  vtools update variant --from_stat 'CEU_mafGD10=maf()' --genotypes 'DP_geno&gt;10' --samples "RACE=1"
+
  vtools update variant --from_stat 'CEU_mafGD10=maf()' --genotypes 'DP_geno>10' --samples "RACE=1"
  vtools update variant --from_stat 'YRI_mafGD10=maf()' --genotypes 'DP_geno&gt;10' --samples "RACE=0"
+
  vtools update variant --from_stat 'YRI_mafGD10=maf()' --genotypes 'DP_geno>10' --samples "RACE=0"
 
  vtools output variant chr pos mafGD10 CEU_mafGD10 YRI_mafGD10 --header --limit 10
 
  vtools output variant chr pos mafGD10 CEU_mafGD10 YRI_mafGD10 --header --limit 10
  vtools phenotype --from_stat 'CEU_totalGD10=#(GT)' 'CEU_numGD10=#(alt)' --genotypes 'DP_geno&gt;10' --samples "RACE=1"
+
  vtools phenotype --from_stat 'CEU_totalGD10=#(GT)' 'CEU_numGD10=#(alt)' --genotypes 'DP_geno>10' --samples "RACE=1"
  vtools phenotype --from_stat 'YRI_totalGD10=#(GT)' 'YRI_numGD10=#(alt)' --genotypes 'DP_geno&gt;10' --samples "RACE=0"
+
  vtools phenotype --from_stat 'YRI_totalGD10=#(GT)' 'YRI_numGD10=#(alt)' --genotypes 'DP_geno>10' --samples "RACE=0"
  vtools phenotype --output sample_nameCEU_totalGD10CEU_numGD10YRI_totalGD10YRI_numGD10 --header
+
  vtools phenotype --output sample_name CEU_totalGD10 CEU_numGD10 YRI_totalGD10 YRI_numGD10 --header
 +
vtools select variant 'maf>=0.01' -t variant_MAFge01 'Variants that have MAF >= 0.01'
 +
vtools show tables
 +
vtools execute KING --var_table variant_MAFge01
 +
vtools_report plot_pheno_fields KING_MDS1 KING_MDS2 RACE --dot KING.mds.race.pdf --discrete_color Dark2
 +
vtools_report plot_pheno_fields KING_MDS1 KING_MDS2 panel --dot KING.mds.panel.pdf --discrete_color Dark2
 
  vtools execute ANNOVAR geneanno
 
  vtools execute ANNOVAR geneanno
 
  vtools output variant chr pos ref alt mut_type --limit 20 --header
 
  vtools output variant chr pos ref alt mut_type --limit 20 --header
 
  vtools_report trans_ratio variant -n num
 
  vtools_report trans_ratio variant -n num
 
  vtools_report trans_ratio variant -n numGD10
 
  vtools_report trans_ratio variant -n numGD10
  vtools select variant "DP&lt;15" -t to_remove
+
  vtools select variant "DP<15" -t to_remove
 
  vtools show tables
 
  vtools show tables
 
  vtools remove variants to_remove -v0
 
  vtools remove variants to_remove -v0
 
  vtools show tables
 
  vtools show tables
  vtools remove genotypes "DP_geno&lt;10" -v0
+
  vtools remove genotypes "DP_geno<10" -v0 vtools select variant "mut_type like 'non%' or mut_type like 'stop%' or region_type='splicing'" -t v_funct
vtools select variant "mut_type like 'non%' or mut_type like 'stop%' or region_type='splicing'" -t v_funct  
+
 
  vtools show tables
 
  vtools show tables
 
  vtools show samples --limit 5
 
  vtools show samples --limit 5
Line 51: Line 56:
 
  mkdir -p ceu
 
  mkdir -p ceu
 
  cd ceu
 
  cd ceu
  vtools init ceu --parent ../ --variants CEU --samples "RACE=1" --build hg19 vtools show project
+
  vtools init ceu --parent ../ --variants CEU --samples "RACE=1" --build hg19
  vtools select variant "CEU_mafGD10&gt;=0.05" -t common_ceu
+
vtools show project
  vtools select v_funct "CEU_mafGD10&lt;0.01" -t rare_ceu
+
  vtools select variant "CEU_mafGD10>=0.05" -t common_ceu
vtools use refGene
+
  vtools select v_funct "CEU_mafGD10<0.01" -t rare_ceu vtools use refGene
 
  vtools show annotation refGene
 
  vtools show annotation refGene
 
  vtools associate -h
 
  vtools associate -h
 
  vtools show tests
 
  vtools show tests
 
  vtools show test LinRegBurden
 
  vtools show test LinRegBurden
  vtools associate common_ceu BMI --covariate SEX -m "LinRegBurden --alternative 2" -j1 --to_db EA_CV &gt; EA_CV.asso.res
+
  vtools associate common_ceu BMI --covariate SEX -m "LinRegBurden --alternative 2" -j1 --to_db EA_CV > EA_CV.asso.res
 
  grep -i error *.log
 
  grep -i error *.log
 
  less EA_CV.asso.res
 
  less EA_CV.asso.res
 
  sort -g -k7 EA_CV.asso.res | head
 
  sort -g -k7 EA_CV.asso.res | head
 
  vtools show fields
 
  vtools show fields
  vtools associate rare_ceu BMI --covariate SEX -m "LinRegBurden --alternative 2" -g refGene.name2 -j1 --to_db EA_RV &gt; EA_RV.asso.res
+
  vtools associate rare_ceu BMI --covariate SEX -m "LinRegBurden --alternative 2" -g refGene.name2 -j1 --to_db EA_RV > EA_RV.asso.res
 
  grep -i error *.log | tail -10
 
  grep -i error *.log | tail -10
 
  less EA_RV.asso.res
 
  less EA_RV.asso.res
 
  sort -g -k6 EA_RV.asso.res | head
 
  sort -g -k6 EA_RV.asso.res | head
  vtools associate rare_ceu BMI --covariate SEX -m "VariableThresholdsQt --alternative 2 -p 100000 --adaptive 0.0005" -g refGene.name2 -j1 --to_db EA_RV &gt; EA_RV_VT.asso.res
+
  vtools associate rare_ceu BMI --covariate SEX -m "VariableThresholdsQt --alternative 2 -p 100000 --adaptive 0.0005" -g refGene.name2 -j1 --to_db EA_RV > EA_RV_VT.asso.res
 
  grep -i error *.log | tail -10
 
  grep -i error *.log | tail -10
 
  less EA_RV_VT.asso.res
 
  less EA_RV_VT.asso.res
 
  sort -g -k6 EA_RV_VT.asso.res | head
 
  sort -g -k6 EA_RV_VT.asso.res | head
 
  vtools select rare_ceu "refGene.name2='ABCC1'" -o chr pos ref alt CEU_mafGD10 numGD10 mut_type --header
 
  vtools select rare_ceu "refGene.name2='ABCC1'" -o chr pos ref alt CEU_mafGD10 numGD10 mut_type --header
  cd ..
+
  vtools_report plot_association qq -o QQRV -b --label_top 2 -f 6 < EA_RV.asso.res
 +
vtools_report plot_association manhattan -o MHRV -b --label_top 5 --color Dark2 --chrom_prefix None -f 6 < EA_RV.asso.res vtools associate rare_ceu BMI --covariate SEX KING_MDS1 KING_MDS2 -m "LinRegBurden --name RVMDS2 --alternative 2" -g refGene.name2 -j1 --to_db EA_RV > EA_RV_MDS2.asso.res
 +
vtools_report plot_association qq -o QQRV_MDS2 -b --label_top 2 -f 6 < EA_RV_MDS2.asso.res cd ..
 
  vtools select variant --samples "RACE=0" -t YRI
 
  vtools select variant --samples "RACE=0" -t YRI
  mkdir -p yri
+
  mkdir -p yri; cd yri
cd yri
+
  vtools init yri --parent ../ --variants YRI --samples "RACE=0" --build hg19
  vtools init yri --parent ../ --variants YRI --samples "RACE=0" --build hg19 vtools select variant "YRI_mafGD10&gt;=0.05" -t common_yri vtools select v_funct "YRI_mafGD10&lt;0.01" -t rare_yri
+
vtools select variant "YRI_mafGD10>=0.05" -t common_yri
vtools use refGene
+
vtools select v_funct "YRI_mafGD10<0.01" -t rare_yri vtools use refGene
  vtools associate common_yri BMI --covariate SEX -m "LinRegBurden --alternative 2" -j1 --to_db YA_CV &gt; YA_CV.asso.res
+
  vtools associate common_yri BMI --covariate SEX -m "LinRegBurden --alternative 2" -j1 --to_db YA_CV > YA_CV.asso.res
  vtools associate rare_yri BMI --covariate SEX -m "LinRegBurden --alternative 2" -g refGene.name2 -j1 --to_db YA_RV &gt; YA_RV.asso.res vtools associate rare_yri BMI --covariate SEX -m "VariableThresholdsQt --alternative 2 -p 100000 --adaptive 0.0005" -g refGene.name2 -j1 --to_db YA_RV &gt; YA_RV_VT.asso.res
+
  vtools associate rare_yri BMI --covariate SEX -m "LinRegBurden --alternative 2" -g refGene.name2 -j1 --to_db YA_RV > YA_RV.asso.res
 +
vtools associate rare_yri BMI --covariate SEX -m "VariableThresholdsQt --alternative 2 -p 100000 --adaptive 0.0005" -g refGene.name2 -j1 --to_db YA_RV > YA_RV_VT.asso.res
 
  cd ..
 
  cd ..
  vtools_report meta_analysis ceu/EA_RV_VT.asso.res yri/YA_RV_VT.asso.res --beta 5 --pval 6 --se 7 -n 2 --link 1 &gt; ME\ TA_RV_VT.asso.res
+
  vtools_report meta_analysis ceu/EA_RV_VT.asso.res yri/YA_RV_VT.asso.res --beta 5 --pval 6 --se 7 -n 2 --link 1 > META_RV_VT.asso.res
 
  cut -f1,3 META_RV_VT.asso.res | head
 
  cut -f1,3 META_RV_VT.asso.res | head
 
</pre>
 
</pre>

Revision as of 20:39, 7 June 2018

VAT Commands in Exercise

 
 vtools -h
 vtools init VATDemo
 vtools import *.vcf.gz --var_info DP filter --geno_info DP_geno --build hg18 -j1
 vtools liftover hg19
 head phenotypes.csv
 vtools phenotype --from_file phenotypes.csv --delimiter ","
 vtools show project
 vtools show tables
 vtools show table variant
 vtools show samples
 vtools show genotypes
 vtools show fields
 vtools select variant --count
 vtools show genotypes > GenotypeSummary.txt
 head GenotypeSummary.txt
 vtools output variant "max(DP)" "min(DP)" "avg(DP)" "stdev(DP)" "lower_quartile(DP)" "upper_quartile(DP)" --header
 vtools select variant "filter='PASS'" --count
 vtools select variant "filter='PASS'" -o "max(DP)" "min(DP)" "avg(DP)" "stdev(DP)" "lower_quartile(DP)" "upper_quartile(DP)" --header
 vtools update variant --from_stat 'total=#(GT)' 'num=#(alt)' 'het=#(het)' 'hom=#(hom)' 'other=#(other)' 'minDP=min(DP_geno)' 'maxDP=max(DP_geno)' 'meanDP=avg(DP_geno)' 'maf=maf()'
 vtools show fields
 vtools show table variant
 vtools update variant --from_stat 'totalGD10=#(GT)' 'numGD10=#(alt)' 'hetGD10=#(het)' 'homGD10=#(hom)' 'otherGD10=#(other)' 'mafGD10=maf()' --genotypes "DP_geno > 10"
 vtools show fields
 vtools show table variant
 vtools output variant chr pos maf mafGD10 --header --limit 20
 vtools phenotype --set "RACE=0" --samples "filename like 'YRI%'"
 vtools phenotype --set "RACE=1" --samples "filename like 'CEU%'"
 vtools show samples --limit 10
 vtools update variant --from_stat 'CEU_mafGD10=maf()' --genotypes 'DP_geno>10' --samples "RACE=1"
 vtools update variant --from_stat 'YRI_mafGD10=maf()' --genotypes 'DP_geno>10' --samples "RACE=0"
 vtools output variant chr pos mafGD10 CEU_mafGD10 YRI_mafGD10 --header --limit 10
 vtools phenotype --from_stat 'CEU_totalGD10=#(GT)' 'CEU_numGD10=#(alt)' --genotypes 'DP_geno>10' --samples "RACE=1"
 vtools phenotype --from_stat 'YRI_totalGD10=#(GT)' 'YRI_numGD10=#(alt)' --genotypes 'DP_geno>10' --samples "RACE=0"
 vtools phenotype --output sample_name CEU_totalGD10 CEU_numGD10 YRI_totalGD10 YRI_numGD10 --header
 vtools select variant 'maf>=0.01' -t variant_MAFge01 'Variants that have MAF >= 0.01'
 vtools show tables
 vtools execute KING --var_table variant_MAFge01
 vtools_report plot_pheno_fields KING_MDS1 KING_MDS2 RACE --dot KING.mds.race.pdf --discrete_color Dark2
 vtools_report plot_pheno_fields KING_MDS1 KING_MDS2 panel --dot KING.mds.panel.pdf --discrete_color Dark2
 vtools execute ANNOVAR geneanno
 vtools output variant chr pos ref alt mut_type --limit 20 --header
 vtools_report trans_ratio variant -n num
 vtools_report trans_ratio variant -n numGD10
 vtools select variant "DP<15" -t to_remove
 vtools show tables
 vtools remove variants to_remove -v0
 vtools show tables
 vtools remove genotypes "DP_geno<10" -v0 vtools select variant "mut_type like 'non%' or mut_type like 'stop%' or region_type='splicing'" -t v_funct
 vtools show tables
 vtools show samples --limit 5
 vtools select variant --samples "RACE=1" -t CEU
 mkdir -p ceu
 cd ceu
 vtools init ceu --parent ../ --variants CEU --samples "RACE=1" --build hg19
 vtools show project
 vtools select variant "CEU_mafGD10>=0.05" -t common_ceu
 vtools select v_funct "CEU_mafGD10<0.01" -t rare_ceu vtools use refGene
 vtools show annotation refGene
 vtools associate -h
 vtools show tests
 vtools show test LinRegBurden
 vtools associate common_ceu BMI --covariate SEX -m "LinRegBurden --alternative 2" -j1 --to_db EA_CV > EA_CV.asso.res
 grep -i error *.log
 less EA_CV.asso.res
 sort -g -k7 EA_CV.asso.res | head
 vtools show fields
 vtools associate rare_ceu BMI --covariate SEX -m "LinRegBurden --alternative 2" -g refGene.name2 -j1 --to_db EA_RV > EA_RV.asso.res
 grep -i error *.log | tail -10
 less EA_RV.asso.res
 sort -g -k6 EA_RV.asso.res | head
 vtools associate rare_ceu BMI --covariate SEX -m "VariableThresholdsQt --alternative 2 -p 100000 --adaptive 0.0005" -g refGene.name2 -j1 --to_db EA_RV > EA_RV_VT.asso.res
 grep -i error *.log | tail -10
 less EA_RV_VT.asso.res
 sort -g -k6 EA_RV_VT.asso.res | head
 vtools select rare_ceu "refGene.name2='ABCC1'" -o chr pos ref alt CEU_mafGD10 numGD10 mut_type --header
 vtools_report plot_association qq -o QQRV -b --label_top 2 -f 6 < EA_RV.asso.res
 vtools_report plot_association manhattan -o MHRV -b --label_top 5 --color Dark2 --chrom_prefix None -f 6 < EA_RV.asso.res vtools associate rare_ceu BMI --covariate SEX KING_MDS1 KING_MDS2 -m "LinRegBurden --name RVMDS2 --alternative 2" -g refGene.name2 -j1 --to_db EA_RV > EA_RV_MDS2.asso.res
 vtools_report plot_association qq -o QQRV_MDS2 -b --label_top 2 -f 6 < EA_RV_MDS2.asso.res cd ..
 vtools select variant --samples "RACE=0" -t YRI
 mkdir -p yri; cd yri
 vtools init yri --parent ../ --variants YRI --samples "RACE=0" --build hg19
 vtools select variant "YRI_mafGD10>=0.05" -t common_yri
 vtools select v_funct "YRI_mafGD10<0.01" -t rare_yri vtools use refGene
 vtools associate common_yri BMI --covariate SEX -m "LinRegBurden --alternative 2" -j1 --to_db YA_CV > YA_CV.asso.res
 vtools associate rare_yri BMI --covariate SEX -m "LinRegBurden --alternative 2" -g refGene.name2 -j1 --to_db YA_RV > YA_RV.asso.res
 vtools associate rare_yri BMI --covariate SEX -m "VariableThresholdsQt --alternative 2 -p 100000 --adaptive 0.0005" -g refGene.name2 -j1 --to_db YA_RV > YA_RV_VT.asso.res
 cd ..
 vtools_report meta_analysis ceu/EA_RV_VT.asso.res yri/YA_RV_VT.asso.res --beta 5 --pval 6 --se 7 -n 2 --link 1 > META_RV_VT.asso.res
 cut -f1,3 META_RV_VT.asso.res | head