saving the correct af or script

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: <drug> 0 or 1
 dst = raw_data[[drug]]