# load phenotypes and covariates
phenotype_df, phenotype_pos_df = tensorqtl.read_phenotype_bed(expression_bed)
covariates_df = pd.read_csv(covariates_file, sep='\t', index_col=0).T
pr = genotypeio.PlinkReader(plink_prefix_path, exclude_chrs=excluded_chr_list)
genotype_df = pr.load_genotypes()
variant_df = pr.bim.set_index('snp')[['chrom', 'pos']]
if mode == 'cis':
# cis-QTL: empirical p-values for phenotypes
if excluded_chr_list:
cis_df = cis.map_cis(
genotype_df,
variant_df,
phenotype_df.loc[phenotype_pos_df['chr'] == chr_id],
phenotype_pos_df.loc[phenotype_pos_df['chr'] == chr_id],
covariates_df=covariates_df,
seed=args.seed)
else:
cis_df = cis.map_cis(genotype_df,
variant_df,
phenotype_df,
phenotype_pos_df,
covariates_df=covariates_df,
seed=args.seed)
out_file = os.path.join(args.output_dir, prefix + '.cis_qtl.txt.gz')
cis_df.to_csv(out_file, sep='\t')
elif mode == 'cis_independent':
cis_df = pd.read_csv(in_cis_addr, sep='\t', index_col=0)
#for i in 1:22:
#pairs_df_+i.to_csv('/lustre03/project/6032391/GROUP/sc_rnaseq/tensorqtl/results/chromatin/cis_caqtl_chr'+i+'_nominal.txt',sep='\t')
# all genes
# cis_df = cis.map_cis(genotype_df, variant_df, phenotype_df, phenotype_pos_df, covariates_df)
# genes on chr18
#cis_df = cis.map_cis(genotype_df, variant_df,
# phenotype_df.loc[phenotype_pos_df['chr']=='1'],
# phenotype_pos_df.loc[phenotype_pos_df['chr']=='1'],
# covariates_df=covariates_df, seed=123456)
cis_df = cis.map_cis(genotype_df, variant_df,
phenotype_df.loc[phenotype_pos_df['chr'].isin(['1','2','3','4','5','6','7','8','9','10','11','12','13','14','15','16','17','18','19','20','21','22'])],
phenotype_pos_df.loc[phenotype_pos_df['chr'].isin(['1','2','3','4','5','6','7','8','9','10','11','12','13','14','15','16','17','18','19','20','21','22'])],
covariates_df=covariates_df, seed=123456)
cis_df.to_csv('/lustre03/project/6032391/GROUP/sc_rnaseq/tensorqtl/results/expression/Tcis_eqtl_Bcells_permutations.txt',sep='\t')
trans_df = trans.map_trans(genotype_df, phenotype_df, covariates_df, batch_size=10000,
return_sparse=True, pval_threshold=1e-5, maf_threshold=0.05)
trans_df.to_csv('/lustre03/project/6032391/GROUP/sc_rnaseq/tensorqtl/results/expression/Ttrans_eqtl_Bcells_nominal.txt',sep='\t')
#cis_df.head()
# load genotypes and variants into data frames
genotype_df = pd.DataFrame(pr.load_genotypes(),
index=pr.bim['snp'],
columns=pr.fam['iid'])
variant_df = pr.bim.set_index('snp')[['chrom', 'pos']]
# Subset to Dirk's GMPR SNPs of interest
gmpr = pd.read_csv(outpath + "GMPR_variants_for_lookup_20200717_LS_sorted.txt",
sep='\t')
gmpr_genotype_df = genotype_df.loc[gmpr['rsID']]
gmpr_genotype_df = gmpr_genotype_df[gmpr_genotype_df['110000315494'].notnull()]
gmpr_variant_df = variant_df.loc[gmpr['rsID']]
gmpr_variant_df = gmpr_variant_df[gmpr_variant_df['chrom'].notnull()]
# Call cis-eQTLs
cis_df = cis.map_cis(gmpr_genotype_df, gmpr_variant_df, phenotype_df,
phenotype_pos_df, covariates_df)
tensorqtl.calculate_qvalues(cis_df, qvalue_lambda=0.85)
cis_df.to_csv(outpath + "tensorqtl_cis_cisPerGene_chr" + chr + ".csv",
index=True,
index_label="Phenotype")
# Cis nominal mapping
cisnom_df = cis.map_nominal(gmpr_genotype_df,
gmpr_variant_df,
phenotype_df,
phenotype_pos_df,
covariates_df,
prefix=outpath + "tensorqtl_cis_cisNominal_chr" +
chr)
cisnom_df2 = pd.read_parquet(
outpath + "tensorqtl_cis_cisNominal_chr6.cis_qtl_pairs.6.parquet")
index=pr.bim['snp'],
columns=pr.fam['iid'])
variant_df = pr.bim.set_index('snp')[['chrom', 'pos']]
covariates_df = pd.read_csv(covariates_file, sep='\t',
index_col=0).T # samples x covariates
covariates_df = covariates_df[["age_RNA"]]
# Read in genotypes
pr = genotypeio.PlinkReader(plink_prefix_path)
# Limit to 3 phenotypes to test conditional analysis
phenotype_df = all_phenotype_df[0:15]
phenotype_pos_df = all_phenotype_pos_df[0:15]
# Cis gene-level mapping
cis_df = cis.map_cis(genotype_df, variant_df, phenotype_df, phenotype_pos_df,
covariates_df)
tensorqtl.calculate_qvalues(
cis_df, qvalue_lambda=0) # lambda of 0 is equivalent to BH correction
cis_df.to_csv(outpath + "tensorqtl_cis_MAF0.005_cisPerGene_3phenotest_chr" +
chr + ".csv",
index=True,
index_label="Phenotype")
# Cis nominal mapping
#cis.map_nominal(genotype_df, variant_df, phenotype_df, phenotype_pos_df, covariates_df, prefix=outpath + "tensorqtl_cis_MAF0.005_cisNominal_3phenotest_chr" + chr)
#cisnom_df = pd.read_parquet(outpath + "tensorqtl_cis_MAF0.005_cisNominal_3phenotest_chr21.cis_qtl_pairs.21.parquet")
# Conditional analysis
indep_df = cis.map_independent(genotype_df,
variant_df,
cis_df,
plink_prefix_path = "/rds/user/jm2294/rds-jmmh2-projects/interval_rna_seq/analysis/03_tensorqtl/genotypes/INTERVAL_b38_autosomes_RNAseqPhase1_biallelic_all_MAF0.005"
pr = genotypeio.PlinkReader(plink_prefix_path)
genotype_df = pd.DataFrame(pr.get_all_genotypes(),
index=pr.bim['snp'],
columns=pr.fam['iid'])
variant_df = pr.bim.set_index('snp')[['chrom', 'pos']]
# cis
# Cis gene-level mapping
pheno_df_noACE2 = phenotype_df.drop("ENSG00000130234")
phenopos_df_noACE2 = phenotype_pos_df.drop("ENSG00000130234")
pheno_df_noACE2 = pheno_df_noACE2.drop("ENSG00000184012")
phenopos_df_noACE2 = phenopos_df_noACE2.drop("ENSG00000184012")
cis_df = cis.map_cis(genotype_df, variant_df, pheno_df_noACE2,
phenopos_df_noACE2, covariates_peer_df)
tensorqtl.calculate_qvalues(cis_df, qvalue_lambda=0)
cis_df.to_csv(outdir + "tensorqtl_cis_MAF0.005_cisPerGene_chr1.csv",
index=True,
index_label="Phenotype")
# Cis nominal mapping
cisnom_df = cis.map_nominal(genotype_df,
variant_df,
pheno_df_noACE2,
phenopos_df_noACE2,
covariates_peer_df,
prefix=covdir +
"tensorqtl_cis_MAF0.005_cisNominal_covid19")
# Conditional analysis