From 587be435e99a4e3e7604a97414f446b7b8386f0e Mon Sep 17 00:00:00 2001 From: Tanushree Tunstall Date: Fri, 11 Jun 2021 13:26:28 +0100 Subject: [PATCH] saving the correct af or script --- scripts/af_or_calcs.R | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) mode change 100755 => 100644 scripts/af_or_calcs.R diff --git a/scripts/af_or_calcs.R b/scripts/af_or_calcs.R old mode 100755 new mode 100644 index a0f439d..4e30f85 --- a/scripts/af_or_calcs.R +++ b/scripts/af_or_calcs.R @@ -71,6 +71,10 @@ cat(paste0('Output file with full path:', outfile_af_or)) ######################################################### raw_data_all = read.csv(infile_master, stringsAsFactors = F) +# building cols to extract +dr_muts_col = paste0('dr_mutations_', drug) +other_muts_col = paste0('other_mutations_', drug) + cat('Extracting columns based on variables:\n' , drug , '\n' @@ -149,8 +153,8 @@ print(paste('Dim of', deparse(substitute(gene_metadata)), ':')); print(dim(gene_ rm(in_filename_metadata, infile_metadata) # count na in drug column -tot_pza_na = sum(is.na(gene_metadata[[drug]])) -expected_rows = nrow(gene_metadata) - tot_pza_na +tot_drug_na = sum(is.na(gene_metadata[[drug]])) +expected_rows = nrow(gene_metadata) - tot_drug_na # drop na from the drug column gene_snps_or = gene_metadata[!is.na(gene_metadata[[drug]]),] @@ -213,23 +217,19 @@ pval_logistic = summary(model)$coefficients[2,4] print(paste0('logistic pval:', pval_logistic)) #===================================== -# OR calcs using the following 4 -#1) logistic -#2) custom chisq.test -#3) fisher -#4) chisq.test - -# adjusted logistic (NO good) -# kinship (separate script) -#====================================== -# TEST FOR a few muts: sapply and df -#====================================== -#snps <- gene_snps_unique[1:2]# reassign so you test with subset of muts +#OR calcs using the following 4 +#1) chisq.test +#2) fisher +#3) modified chisq.test +#4) logistic +#5) adjusted logistic? +#6) kinship (separate script) +#===================================== +#snps <- gene_snps_unique[1:2]# TEST FOR a few muts snps <- gene_snps_unique -cat(paste0('Running calculations for:' - , length(snps), ' nssnps\n' - , 'gene: ', gene - , '\ndrug: ', drug )) +cat(paste0('Running calculations for:', length(snps), ' nssnps\n' +, 'gene: ', gene +, '\ndrug: ', drug )) # DV: 0 or 1 dst = raw_data[[drug]]