remove sample prefix from sample number

removes discrepancies in "sample_" prefix removal
kartva · Jan 31, 2024 · 319dce4 · 319dce4
1 parent 73b44f2
commit 319dce4
Show file tree

Hide file tree

Showing 6 changed files with 22 additions and 22 deletions.
diff --git a/server/scripts/Librarian/.Rhistory b/server/scripts/Librarian/.Rhistory
@@ -85,7 +85,7 @@ mutate(lib_type = gsub("DNase-Hypersensitivity", "DNase-HS", lib_type)) %>%
 ggplot(aes(UMAP1,UMAP2)) +
 geom_point(size = 1.5, aes(colour = lib_type, group = SRR)) +
 geom_point(data = test_coordinates, aes(UMAP1, UMAP2), colour = "black", shape = 1, size = 5, stroke = 3) +
-geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = gsub("sample_","", sample)), size = 6, nudge_x = 1, nudge_y = 1) +
+geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = sample), size = 6, nudge_x = 1, nudge_y = 1) +
 theme_bw(base_size = 14) +
 theme(legend.title = element_text(size = 12)) +
 #ylim(-10, 10) +
@@ -149,7 +149,7 @@ theme(legend.title = element_blank(), axis.title = element_blank(), panel.backgr
 geom_tile(aes(fill = percentage)) +
 scale_fill_viridis_c(option = "inferno", direction = -1) +
 geom_point(data = test_coordinates, aes(UMAP1, UMAP2), fill = "black", colour = "#609CE1", shape = 1, size = 3, stroke = 1 ) +
-geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = gsub("sample_","", sample)), size = 3, nudge_x = 2, nudge_y = 1) +
+geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = sample), size = 3, nudge_x = 2, nudge_y = 1) +
 ggtitle("percent of library per tile") +
 facet_wrap(facets = "library_type", ncol = 5) +
 theme(text = element_text(family = "sans"), aspect.ratio = 0.8, panel.background = element_rect(fill = "#feffe9"), panel.grid = element_blank(), plot.title = element_text(size = 14, hjust = 0.5)) -> umap_grid_tile_long_plot
@@ -169,7 +169,7 @@ pivot_longer(5:last_col(), names_to = "library_type", values_to = "percent") ->
 ## Plotting grid stats as heatmap
 test_percentage %>%
 mutate(library_type = factor(library_type, levels = sort(unique(library_type), decreasing = TRUE))) %>%
-mutate(sample = gsub("sample_", "", sample)) %>%
+mutate(sample = sample) %>%
 ggplot(aes(sample, library_type, fill = percent)) +
 geom_tile() +
 scale_fill_gradient(low = "white", high = "red") +
@@ -251,7 +251,7 @@ mutate(lib_type = gsub("DNase-Hypersensitivity", "DNase-HS", lib_type)) %>%
 ggplot(aes(UMAP1,UMAP2)) +
 geom_point(size = 1.5, aes(colour = lib_type, group = SRR)) +
 geom_point(data = test_coordinates, aes(UMAP1, UMAP2), colour = "black", shape = 1, size = 5, stroke = 3) +
-geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = gsub("sample_","", sample)), size = 6, nudge_x = 1, nudge_y = 1) +
+geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = sample), size = 6, nudge_x = 1, nudge_y = 1) +
 theme_bw(base_size = 14) +
 theme(legend.title = element_text(size = 12)) +
 #ylim(-10, 10) +
@@ -307,7 +307,7 @@ theme(legend.title = element_blank(), axis.title = element_blank(), panel.backgr
 geom_tile(aes(fill = percentage)) +
 scale_fill_viridis_c(option = "inferno", direction = -1) +
 geom_point(data = test_coordinates, aes(UMAP1, UMAP2), fill = "black", colour = "#609CE1", shape = 1, size = 3, stroke = 1 ) +
-geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = gsub("sample_","", sample)), size = 3, nudge_x = 2, nudge_y = 1) +
+geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = sample), size = 3, nudge_x = 2, nudge_y = 1) +
 ggtitle("percent of library per tile") +
 facet_wrap(facets = "library_type", ncol = 5) +
 theme(text = element_text(family = "sans"), aspect.ratio = 0.8, panel.background = element_rect(fill = "#feffe9"), panel.grid = element_blank(), plot.title = element_text(size = 14, hjust = 0.5)) -> umap_grid_tile_long_plot
@@ -321,7 +321,7 @@ left_join(grid_tile_corr_percentages) %>%
 pivot_longer(5:last_col(), names_to = "library_type", values_to = "percent") -> test_percentage
 test_percentage %>%
 mutate(library_type = factor(library_type, levels = sort(unique(library_type), decreasing = TRUE))) %>%
-mutate(sample = gsub("sample_", "", sample)) %>%
+mutate(sample = sample) %>%
 ggplot(aes(sample, library_type, fill = percent)) +
 geom_tile() +
 scale_fill_gradient(low = "white", high = "red") +
@@ -398,7 +398,7 @@ mutate(lib_type = gsub("DNase-Hypersensitivity", "DNase-HS", lib_type)) %>%
 ggplot(aes(UMAP1,UMAP2)) +
 geom_point(size = 1.5, aes(colour = lib_type, group = SRR)) +
 geom_point(data = test_coordinates, aes(UMAP1, UMAP2), colour = "black", shape = 1, size = 5, stroke = 3) +
-geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = gsub("sample_","", sample)), size = 6, nudge_x = 1, nudge_y = 1) +
+geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = sample), size = 6, nudge_x = 1, nudge_y = 1) +
 theme_bw(base_size = 14) +
 theme(legend.title = element_text(size = 12)) +
 #ylim(-10, 10) +
@@ -462,7 +462,7 @@ theme(legend.title = element_blank(), axis.title = element_blank(), panel.backgr
 geom_tile(aes(fill = percentage)) +
 scale_fill_viridis_c(option = "inferno", direction = -1) +
 geom_point(data = test_coordinates, aes(UMAP1, UMAP2), fill = "black", colour = "#609CE1", shape = 1, size = 3, stroke = 1 ) +
-geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = gsub("sample_","", sample)), size = 3, nudge_x = 2, nudge_y = 1) +
+geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = sample), size = 3, nudge_x = 2, nudge_y = 1) +
 ggtitle("percent of library per tile") +
 facet_wrap(facets = "library_type", ncol = 5) +
 theme(text = element_text(family = "sans"), aspect.ratio = 0.8, panel.background = element_rect(fill = "#feffe9"), panel.grid = element_blank(), plot.title = element_text(size = 14, hjust = 0.5)) -> umap_grid_tile_long_plot
@@ -482,7 +482,7 @@ pivot_longer(5:last_col(), names_to = "library_type", values_to = "percent") ->
 ## Plotting grid stats as heatmap
 test_percentage %>%
 mutate(library_type = factor(library_type, levels = sort(unique(library_type), decreasing = TRUE))) %>%
-mutate(sample = gsub("sample_", "", sample)) %>%
+mutate(sample = sample) %>%
 ggplot(aes(sample, library_type, fill = percent)) +
 geom_tile() +
 scale_fill_gradient(low = "white", high = "red") +

diff --git a/server/scripts/Librarian/Librarian_offline_analysis.Rmd b/server/scripts/Librarian/Librarian_offline_analysis.Rmd
@@ -120,7 +120,7 @@ compositions_umap_results %>%
   ggplot(aes(UMAP1,UMAP2)) +
   geom_point(size = 1.5, aes(colour = lib_type, group = SRR)) +
   geom_point(data = test_coordinates, aes(UMAP1, UMAP2), colour = "black", shape = 1, size = 5, stroke = 3) +
-  geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = gsub("sample_","", sample)), size = 6, nudge_x = 1, nudge_y = 1) +
+  geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = sample), size = 6, nudge_x = 1, nudge_y = 1) +
   theme_bw(base_size = 14) +
   theme(legend.title = element_text(size = 12)) +
   #ylim(-10, 10) +
@@ -204,7 +204,7 @@ umap_grid_tile_long %>%
   geom_tile(aes(fill = percentage)) +
   scale_fill_viridis_c(option = "inferno", direction = -1) +
   geom_point(data = test_coordinates, aes(UMAP1, UMAP2), fill = "black", colour = "#609CE1", shape = 1, size = 3, stroke = 1 ) +
-  geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = gsub("sample_","", sample)), size = 3, nudge_x = 2, nudge_y = 1) +
+  geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = sample), size = 3, nudge_x = 2, nudge_y = 1) +
   ggtitle("percent of library per tile") +
   facet_wrap(facets = "library_type", ncol = 5) +
   theme(text = element_text(family = "sans"), aspect.ratio = 0.8, panel.background = element_rect(fill = "#feffe9"), panel.grid = element_blank(), plot.title = element_text(size = 14, hjust = 0.5)) -> umap_grid_tile_long_plot
@@ -236,7 +236,7 @@ test_grid %>%
 
 test_percentage %>% 
   mutate(library_type = factor(library_type, levels = sort(unique(library_type), decreasing = TRUE))) %>% 
-  mutate(sample = gsub("sample_", "", sample)) %>% 
+  mutate(sample = sample) %>% 
   ggplot(aes(sample, library_type, fill = percent)) +
   geom_tile() +
   scale_fill_gradient(low = "white", high = "red") +

diff --git a/server/scripts/Librarian/librarian_offline_analysis.R b/server/scripts/Librarian/librarian_offline_analysis.R
@@ -111,7 +111,7 @@ compositions_umap_results %>%
   ggplot(aes(UMAP1,UMAP2)) +
   geom_point(size = 1.5, aes(colour = lib_type, group = SRR)) +
   geom_point(data = test_coordinates, aes(UMAP1, UMAP2), colour = "black", shape = 1, size = 5, stroke = 3) +
-  geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = gsub("sample_","", sample)), size = 6, nudge_x = 1, nudge_y = 1) +
+  geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = sample), size = 6, nudge_x = 1, nudge_y = 1) +
   theme_bw(base_size = 14) +
   theme(legend.title = element_text(size = 12)) +
   #ylim(-10, 10) +
@@ -195,7 +195,7 @@ umap_grid_tile_long %>%
   geom_tile(aes(fill = percentage)) +
   scale_fill_viridis_c(option = "inferno", direction = -1) +
   geom_point(data = test_coordinates, aes(UMAP1, UMAP2), fill = "black", colour = "#609CE1", shape = 1, size = 3, stroke = 1 ) +
-  geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = gsub("sample_","", sample)), size = 3, nudge_x = 2, nudge_y = 1) +
+  geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = sample), size = 3, nudge_x = 2, nudge_y = 1) +
   ggtitle("percent of library per tile") +
   facet_wrap(facets = "library_type", ncol = 5) +
   theme(text = element_text(family = "sans"), aspect.ratio = 0.8, panel.background = element_rect(fill = "#feffe9"), panel.grid = element_blank(), plot.title = element_text(size = 14, hjust = 0.5)) -> umap_grid_tile_long_plot
@@ -227,7 +227,7 @@ test_grid %>%
 
 test_percentage %>% 
   mutate(library_type = factor(library_type, levels = sort(unique(library_type), decreasing = TRUE))) %>% 
-  mutate(sample = gsub("sample_", "", sample)) %>% 
+  mutate(sample = sample) %>% 
   ggplot(aes(sample, library_type, fill = percent)) +
   geom_tile() +
   scale_fill_gradient(low = "white", high = "red") +

diff --git a/server/scripts/Librarian_analysis.Rmd b/server/scripts/Librarian_analysis.Rmd
@@ -117,7 +117,7 @@ compositions_umap_results %>%
   ggplot(aes(UMAP1,UMAP2)) +
   geom_point(size = 1.5, aes(colour = lib_type, group = SRR)) +
   geom_point(data = test_coordinates, aes(UMAP1, UMAP2), colour = "black", shape = 1, size = 5, stroke = 3) +
-  geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = gsub("sample_","", sample)), size = 6, nudge_x = 1, nudge_y = 1) +
+  geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = sample), size = 6, nudge_x = 1, nudge_y = 1) +
   theme_bw(base_size = 14) +
   theme(legend.title = element_text(size = 12)) +
   #ylim(-10, 10) +
@@ -199,7 +199,7 @@ umap_grid_tile_long %>%
   geom_tile(aes(fill = percentage)) +
   scale_fill_viridis_c(option = "inferno", direction = -1) +
   geom_point(data = test_coordinates, aes(UMAP1, UMAP2), fill = "black", colour = "#609CE1", shape = 1, size = 3, stroke = 1 ) +
-  geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = gsub("sample_","", sample)), size = 3, nudge_x = 2, nudge_y = 1) +
+  geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = sample), size = 3, nudge_x = 2, nudge_y = 1) +
   ggtitle("percent of library per tile") +
   facet_wrap(facets = "library_type", ncol = 5) +
   theme(text = element_text(family = "sans"), aspect.ratio = 0.8, panel.background = element_rect(fill = "#feffe9"), panel.grid = element_blank(), plot.title = element_text(size = 14, hjust = 0.5)) -> umap_grid_tile_long_plot
@@ -226,7 +226,7 @@ test_grid %>%
 
 test_percentage %>% 
   mutate(library_type = factor(library_type, levels = sort(unique(library_type), decreasing = TRUE))) %>% 
-  mutate(sample = gsub("sample_", "", sample)) %>% 
+  mutate(sample = sample) %>% 
   ggplot(aes(sample, library_type, fill = percent)) +
   geom_tile() +
   scale_fill_gradient(low = "white", high = "red") +

diff --git a/server/scripts/librarian_plotting_test_samples_server_220623.R b/server/scripts/librarian_plotting_test_samples_server_220623.R
@@ -99,7 +99,7 @@ compositions_umap_results %>%
   ggplot(aes(UMAP1,UMAP2)) +
   geom_point(size = 1.5, aes(colour = lib_type, group = SRR)) +
   geom_point(data = test_coordinates, aes(UMAP1, UMAP2), colour = "black", shape = 1, size = 5, stroke = 3) +
-  geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = gsub("sample_","", sample)), size = 6, nudge_x = 1, nudge_y = 1) +
+  geom_text(data = test_coordinates, aes(UMAP1, UMAP2, label = sample), size = 6, nudge_x = 1, nudge_y = 1) +
   theme_bw(base_size = 14) +
   theme(legend.title = element_text(size = 12)) +
   #ylim(-10, 10) +
@@ -180,7 +180,7 @@ umap_grid_tile_long %>%
   geom_tile(aes(fill = percentage)) +
   scale_fill_viridis_c(option = "inferno", direction = -1) +
   geom_point(data = test_coordinates, aes(UMAP1, UMAP2), fill = "black", colour = "#609CE1", shape = 1, size = 3, stroke = 1 ) +
-  geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = gsub("sample_","", sample)), size = 3, nudge_x = 2, nudge_y = 1) +
+  geom_text(data = test_coordinates, aes(x=UMAP1, y=UMAP2, label = sample), size = 3, nudge_x = 2, nudge_y = 1) +
   ggtitle("percent of library per tile") +
   facet_wrap(facets = "library_type", ncol = 5) +
   theme(text = element_text(family = "sans"), aspect.ratio = 0.8, panel.background = element_rect(fill = "#feffe9"), panel.grid = element_blank(), plot.title = element_text(size = 14, hjust = 0.5)) -> umap_grid_tile_long_plot
@@ -207,7 +207,7 @@ test_grid %>%
 
 test_percentage %>% 
   mutate(library_type = factor(library_type, levels = sort(unique(library_type), decreasing = TRUE))) %>% 
-  mutate(sample = gsub("sample_", "", sample)) %>% 
+  mutate(sample = sample) %>% 
   ggplot(aes(sample, library_type, fill = percent)) +
   geom_tile() +
   scale_fill_gradient(low = "white", high = "red") +

diff --git a/server/src/lib.rs b/server/src/lib.rs
@@ -135,7 +135,7 @@ pub fn serialize_comps_for_script(comp: Vec<FileComp>) -> String {
         // substitute tabs in sample names with spaces
         c.name = c.name.replace('\t', " ");
 
-        write!(&mut ser, "sample_{:02}\t{}\t", i + 1, c.name).unwrap(); // this unwrap never fails
+        write!(&mut ser, "{:02}\t{}\t", i + 1, c.name).unwrap(); // this unwrap never fails
         c.comp
             .lib
             .into_iter()