updated counts.py with wt seq counts

scripts/count.py

@@ -310,3 +310,20 @@ n_stop = tot3/len(meta_data)
 n_stop*100 #0.11
 
 all_tot = n_del*100 + n_ins*100 + n_stop*100 #1.2
+#%% count pncA WT
+
+wt_gene = meta_data.loc[meta_data[dr_muts_col].str.contains('WT', na = False, regex = True, case = False) | meta_data[other_muts_col].str.contains('WT', na = False, regex = True, case = False)  ]
+
+meta_data['muts_and_lineage'] =  meta_data[dr_muts_col] + meta_data[other_muts_col] + meta_data['lineage']
+
+wt_gene_v2 = meta_data.loc[meta_data['muts_and_lineage'].str.contains('*WT*lineage1', na = False, regex = True, case = False)]
+
+
+lin1_wt_gene = wt_gene.loc[wt_gene['lineage'].str.contains('lineage1', na = False, regex = True, case = False)]
+
+dr_lin1 = wt_gene.groupby(['lineage'])[dr_muts_col].apply(lambda x: x[x.str.contains('WT')].count())
+other_lin1 = wt_gene.groupby(['lineage'])[other_muts_col].apply(lambda x: x[x.str.contains('WT')].count())
+
+dr_lin1_v2 = wt_gene.groupby(['lineage'])[dr_muts_col].value_counts()
+
+other_lin1_v2 = wt_gene.groupby(['lineage'])[other_muts_col].value_counts()

scripts/plotting/ggcorr_all_PS_LIG.R

@@ -221,7 +221,8 @@ head(my_ggcorr_ps)
 corr1 <- round(cor(my_ggcorr_ps, method = "spearman", use = "pairwise.complete.obs"), 1)
 
 # p-value matrix
-pmat1 <- cor_pmat(my_ggcorr_ps, method = "spearman", use = "pairwise.complete.obs")
+pmat1 <- cor_pmat(my_ggcorr_ps, method = "spearman", use = "pairwise.complete.obs"
+                  ,   conf.level = 0.99)
 
 corr2 = psych::corr.test(my_ggcorr_ps
                         , method = "spearman"