分类： 05 SNV association analysis

SAIGE开发背景
SAIGE原理简介
	第一步
	第二步
	注意事项
SAIGE使用方法
	安装
	第一步
	第二步
	结果解读
参考

docker pull wzhou88/saige:0.44.2

#For Binary traits:
Rscript step1_fitNULLGLMM.R     \
        --plinkFile=./input/nfam_100_nindep_0_step1_includeMoreRareVariants_poly \
        --phenoFile=./input/pheno_1000samples.txt_withdosages_withBothTraitTypes.txt \
        --phenoCol=y_binary \
        --covarColList=x1,x2 \
        --sampleIDColinphenoFile=IID \
        --traitType=binary        \
        --outputPrefix=./output/example_binary \
        --nThreads=4 \
        --LOCO=FALSE \
        --IsOverwriteVarianceRatioFile ## v0.38. Whether to overwrite the variance ratio file if the file already exists

#For Quantitative traits, if not normally distributed, inverse normalization needs to be specified to be TRUE --invNormalize=TRUE
Rscript step1_fitNULLGLMM.R     \
        --plinkFile=./input/nfam_100_nindep_0_step1_includeMoreRareVariants_poly \
        --phenoFile=./input/pheno_1000samples.txt_withdosages_withBothTraitTypes.txt \
        --phenoCol=y_quantitative \
        --covarColList=x1,x2 \
        --sampleIDColinphenoFile=IID \
        --traitType=quantitative       \
		--invNormalize=TRUE	\
        --outputPrefix=./output/example_quantitative \
        --nThreads=4 \\
        --LOCO=FALSE	\\
	--tauInit=1,0

./output/example_quantitative.rda

#open R
R
#load the model file in R
load("./output/example_quantitative.rda")
names(modglmm)
modglmm$theta

#theta: a vector of length 2. The first element is the dispersion parameter estimate and the second one is the variance component parameter estimate
#coefficients: fixed effect parameter estimates
#linear.predictors: a vector of length N (N is the sample size) containing linear predictors
#fitted.values: a vector of length N (N is the sample size) containing fitted mean values on the original scale
#Y: a vector of length N (N is the sample size) containing final working vector
#residuals: a vector of length N (N is the sample size) containing residuals on the original scale
#sampleID: a vector of length N (N is the sample size) containing sample IDs used to fit the null model

less -S ./output/example_quantitative_30markers.SAIGE.results.txt

less -S ./output/example_quantitative.varianceRatio.txt

#bgen for dosages
Rscript step2_SPAtests.R \
        --bgenFile=./input/genotype_100markers.bgen \
        --bgenFileIndex=./input/genotype_100markers.bgen.bgi \
        --minMAF=0.0001 \ #最小MAF不能低于0.0001
        --minMAC=1 \ #最小MAC不能低于1
        --sampleFile=./input/samplefileforbgen_10000samples.txt \
        --GMMATmodelFile=./output/example.rda \
        --varianceRatioFile=./output/example.varianceRatio.txt \
        --SAIGEOutputFile=./output/example.SAIGE.bgen.txt \
        --numLinesOutput=2 \
        --IsOutputAFinCaseCtrl=TRUE

#VCF containing dosages (--vcfField=DS)
Rscript step2_SPAtests.R \
        --vcfFile=./input/dosage_10markers.vcf.gz \
        --vcfFileIndex=./input/dosage_10markers.vcf.gz.tbi \
        --vcfField=DS \
        --chrom=1 \
        --minMAF=0.0001 \   #最小MAF不能低于0.0001
        --minMAC=1 \   #最小MAC不能低于1
        --sampleFile=./input/sampleIDindosage.txt \
        --GMMATmodelFile=./output/example.rda \
        --varianceRatioFile=./output/example.varianceRatio.txt \
        --SAIGEOutputFile=./output/example.SAIGE.vcf.dosage.txt \
        --numLinesOutput=2 \
        --IsOutputAFinCaseCtrl=TRUE

CHR: chromosome
POS: genome position 
SNPID: variant ID
Allele1: allele 1
Allele2: allele 2
AC_Allele2: allele count of allele 2
AF_Allele2: allele frequency of allele 2
imputationInfo: imputation info. If not in dosage/genotype input file, will output 1
N: sample size
BETA: effect size of allele 2
SE: standard error of BETA
Tstat: score statistic of allele 2

#SPA后的p值
p.value: p value (with SPA applied for binary traits) 

p.value.NA: p value when SPA is not applied (only for binary traits)
Is.SPA.converge: whether SPA is converged or not (only for binary traits)
varT: estimated variance of score statistic with sample relatedness incorporated
varTstar: variance of score statistic without sample relatedness incorporated
AF.Cases: allele frequency of allele 2 in cases (only for binary traits and if --IsOutputAFinCaseCtrl=TRUE)
AF.Controls: allele frequency of allele 2 in controls (only for binary traits and if --IsOutputAFinCaseCtrl=TRUE)
Tstat_cond, p.value_cond, varT_cond, BETA_cond, SE_cond: summary stats for conditional analysis