update Sample distribution analysis for v15 (#584)

* Change disease_type_new to integrated_diagnosis

* Output updates for v15

* Comment out all analyses from CI but this one

* Revert "Comment out all analyses from CI but this one"

This reverts commit 352ca08.

Co-authored-by: Candace Savonen <cansav09@gmail.com>

analyses/sample-distribution-analysis/01-filter-across-types.R

@@ -29,7 +29,7 @@ location_fn <- function(location) {
   disease_type_vector <- brain_location %>%
     dplyr::arrange(dplyr::desc(n)) %>%
     dplyr::filter(stringr::str_detect(primary_site, location)) %>%
-    dplyr::pull(disease_type_new)
+    dplyr::pull(integrated_diagnosis)
   unique(disease_type_vector)
 }
 
@@ -55,7 +55,7 @@ if (!dir.exists(plots_dir)) {
 histologies_df <-
   readr::read_tsv(file.path(root_dir, "data", "pbta-histologies.tsv")) %>%
   as.data.frame() %>%
-  dplyr::filter(!is.na(disease_type_new))
+  dplyr::filter(!is.na(integrated_diagnosis))
 
 # Filter the histologies file to account for multiple samples from the same
 # individual and the fact that multiple experimental strategies are in this
@@ -68,9 +68,9 @@ histologies_df <- histologies_df %>%
 
 # data.frame with the count of each unique cancer type expression
 disease_expression <- histologies_df %>%
-  # some recurrences can have different disease_type_new values
-  dplyr::distinct(Kids_First_Participant_ID, disease_type_new) %>%
-  dplyr::group_by(disease_type_new) %>%
+  # some recurrences can have different integrated_diagnosis values
+  dplyr::distinct(Kids_First_Participant_ID, integrated_diagnosis) %>%
+  dplyr::group_by(integrated_diagnosis) %>%
   dplyr::count(name = "count") %>%
   dplyr::arrange(dplyr::desc(count))
 
@@ -83,8 +83,8 @@ disease_expression <- disease_expression %>%
   dplyr::mutate(percent = paste0((round(count / sum_count, 4) * 100), "%"))
 
 # Reorder the columns to be displayed in descending order by count on the plot
-disease_expression$disease_type_new <- with(disease_expression,
-                                            reorder(disease_type_new, -count))
+disease_expression$integrated_diagnosis <- with(disease_expression,
+                                            reorder(integrated_diagnosis, -count))
 
 # Write to tsv file
 readr::write_tsv(disease_expression,
@@ -93,7 +93,7 @@ readr::write_tsv(disease_expression,
 
 # Create a bar plot of sample distribution across cancer types
 gg_types <- disease_expression %>%
-  ggplot2::ggplot(ggplot2::aes(x = disease_type_new, y = count, fill = count)) +
+  ggplot2::ggplot(ggplot2::aes(x = integrated_diagnosis, y = count, fill = count)) +
   ggplot2::geom_col() +
   ggplot2::theme_bw() +
   ggplot2::labs(x = "Cancer Types", y = "Count",
@@ -122,10 +122,10 @@ ggplot2::ggsave(
 # data.frame with the location where each cancer type in the dataset is
 # expressed, sorted to show highest expression
 brain_location <- histologies_df %>%
-  dplyr::distinct(Kids_First_Participant_ID, disease_type_new,
+  dplyr::distinct(Kids_First_Participant_ID, integrated_diagnosis,
                   primary_site) %>%
-  dplyr::select(disease_type_new, primary_site) %>%
-  dplyr::group_by(disease_type_new, primary_site) %>%
+  dplyr::select(integrated_diagnosis, primary_site) %>%
+  dplyr::group_by(integrated_diagnosis, primary_site) %>%
   dplyr::tally() %>%
   dplyr::arrange(dplyr::desc(n))
 

analyses/sample-distribution-analysis/02-multilayer-plots.R

@@ -37,21 +37,21 @@ final_df <- histologies_df %>%
   dplyr::filter(sample_type == "Tumor",
                 composition == "Solid Tissue") %>%
   dplyr::distinct(Kids_First_Participant_ID, broad_histology,
-                  short_histology, disease_type_new) %>%
+                  short_histology, integrated_diagnosis) %>%
   # Select our 3 columns of interest
-  dplyr::select(broad_histology, short_histology, disease_type_new) %>%
+  dplyr::select(broad_histology, short_histology, integrated_diagnosis) %>%
   # Remove any row that has an NA
   dplyr::filter(complete.cases(.)) %>%
   # Group by all 3 columns in order to count
-  dplyr::group_by(broad_histology, short_histology, disease_type_new) %>%
+  dplyr::group_by(broad_histology, short_histology, integrated_diagnosis) %>%
   # Add the count to a column named size
   dplyr::add_count(name = "size") %>%
   # Place the value 1 in a column named counter for treemap and sunburt plots
   dplyr::mutate(counter= c(1)) %>%
   # Change the column names
   dplyr::rename(level1 = broad_histology,
                 level2 = short_histology,
-                level3 = disease_type_new) %>%
+                level3 = integrated_diagnosis) %>%
   # Reorder the rows according to the 3 levels
   dplyr::arrange(level1, level2, level3) %>%
   # tbl_df -> data.frame

analyses/sample-distribution-analysis/03-tumor-descriptor-and-assay-count.Rmd

@@ -205,7 +205,7 @@ For `PT_HT4HJXY6`, there is WGS data for both the primary CNS tumor and the seco
 
 ## By histology
 
-We're going to use the `disease_type_new` column here.
+We're going to use the `integrated_diagnosis` column here.
 
 ### Primary only
 
@@ -215,8 +215,8 @@ This table is different than what is plotted upstream in this module because we
 ```{r}
 tumor_df %>%
   filter(tumor_descriptor == "Initial CNS Tumor") %>%
-  distinct(Kids_First_Participant_ID, disease_type_new) %>%
-  group_by(disease_type_new) %>%
+  distinct(Kids_First_Participant_ID, integrated_diagnosis) %>%
+  group_by(integrated_diagnosis) %>%
   tally() %>%
   arrange(desc(n)) %>% 
   regulartable() %>%
@@ -228,7 +228,7 @@ tumor_df %>%
 ```{r}
 disease_types_descriptors <- tumor_df %>%
   group_by(Kids_First_Participant_ID) %>%
-  summarize(disease_types = paste(sort(unique(disease_type_new)),
+  summarize(disease_types = paste(sort(unique(integrated_diagnosis)),
                                   collapse = ", "),
             descriptors = paste(sort(unique(tumor_descriptor)),
                                 collapse = ", ")) %>%

analyses/sample-distribution-analysis/results/disease_expression.tsv

@@ -1,70 +1,63 @@
-disease_type_new	count	percent
-Low-grade glioma;astrocytoma (WHO grade I/II)	239	24.92%
-Medulloblastoma	119	12.41%
-High-grade glioma;astrocytoma (WHO grade III/IV)	101	10.53%
-Ependymoma	86	8.97%
-Ganglioglioma	46	4.8%
-Brainstem glioma- Diffuse intrinsic pontine glioma	45	4.69%
-Craniopharyngioma	39	4.07%
-Atypical Teratoid Rhabdoid Tumor	28	2.92%
-Meningioma	27	2.82%
-Dysembryoplastic neuroepithelial tumor	25	2.61%
-Neurofibroma;Plexiform	19	1.98%
-Choroid plexus papilloma	16	1.67%
-Schwannoma	16	1.67%
-Supratentorial or Spinal Cord PNET	16	1.67%
-Dysplasia;Gliosis	14	1.46%
-Teratoma	8	0.83%
-Ewings Sarcoma	7	0.73%
-Metastatic secondary tumors	5	0.52%
-Adenoma	4	0.42%
-Choroid plexus carcinoma	4	0.42%
-Cyst	4	0.42%
-Germinoma	4	0.42%
-Glial-neuronal tumor NOS	4	0.42%
-Langerhans Cell histiocytosis	4	0.42%
-Malignant peripheral nerve sheath tumor	4	0.42%
-Neuroblastoma	4	0.42%
-Pineoblastoma	4	0.42%
-Sarcoma	4	0.42%
+integrated_diagnosis	count	percent
+Low-grade astrocytic tumor	239	24.59%
+Medulloblastoma	118	12.14%
+High-grade glioma	90	9.26%
+Ependymoma	84	8.64%
+Diffuse midline glioma	56	5.76%
+Ganglioglioma	45	4.63%
+Craniopharyngioma	39	4.01%
+Atypical Teratoid Rhabdoid Tumor	28	2.88%
+Dysembryoplastic neuroepithelial tumor	27	2.78%
+Meningioma	27	2.78%
+CNS Embryonal Tumor	20	2.06%
+Neurofibroma	19	1.95%
+Choroid plexus papilloma	16	1.65%
+Schwannoma	16	1.65%
+Brainstem glioma- Diffuse intrinsic pontine glioma	14	1.44%
+Dysplasia	14	1.44%
+Teratoma	8	0.82%
+Ewings Sarcoma	7	0.72%
+Embryonal tumor with multilayer rosettes	6	0.62%
+Germinoma	5	0.51%
+Metastatic secondary tumors	5	0.51%
+Adenoma	4	0.41%
+Choroid plexus carcinoma	4	0.41%
+Cyst	4	0.41%
+Glial-neuronal tumor NOS	4	0.41%
+Langerhans Cell histiocytosis	4	0.41%
+Malignant peripheral nerve sheath tumor	4	0.41%
+Neuroblastoma	4	0.41%
+Sarcoma	4	0.41%
 Chordoma	3	0.31%
 Dermoid Cyst	3	0.31%
 Meningioangiomatosis	3	0.31%
 Neurocytoma	3	0.31%
-Subependymal Giant Cell Astrocytoma (SEGA)	3	0.31%
+Pineoblastoma	3	0.31%
+Subependymal Giant Cell Astrocytoma	3	0.31%
 Cavernoma	2	0.21%
-Ganglioneuroblastoma	2	0.21%
 Gliomatosis Cerebri	2	0.21%
 Hemangioblastoma	2	0.21%
-Non-Langerhans Histiocytosis;JXG	2	0.21%
+JXG- Non-Langerhans Histiocytosis	2	0.21%
+Low-grade mixed tumor	2	0.21%
 Oligodendroglioma	2	0.21%
 Osteoblastoma	2	0.21%
 Rhabdomyosarcoma	2	0.21%
 Brain arteriovenous malformation	1	0.1%
 Chondrosarcoma	1	0.1%
 Choroid plexus cyst	1	0.1%
-CNS embryonal tumor	1	0.1%
+CNS Neuroblastoma	1	0.1%
 Cortical Tubers	1	0.1%
-Dysembryoplastic neuroepithelial tumor (DNET);Dysplasia/Gliosis;Ganglioglioma	1	0.1%
-Dysembryoplastic neuroepithelial tumor (DNET);Ganglioglioma	1	0.1%
-Dysplasia;Gliosis;Glial-neuronal tumor NOS	1	0.1%
-Embryonal tumor with multilayer rosettes NOS	1	0.1%
-Ependymoblastoma	1	0.1%
 Fibroma	1	0.1%
 Fibromyxoid Tumor	1	0.1%
-Ganglioglioma;Low-grade glioma/astrocytoma (WHO grade I/II)	1	0.1%
 Ganglioneuroma	1	0.1%
-Germinoma;Teratoma	1	0.1%
 Hamartoma	1	0.1%
 Intraneural perineurioma	1	0.1%
 Malignant melanocytic neoplasm	1	0.1%
-Medulloepithelioma	1	0.1%
-Metastatic secondary tumors;Neuroblastoma	1	0.1%
 Myeloid Sarcoma	1	0.1%
 Myofibroblastoma	1	0.1%
 Myxoid spindle cell tumor	1	0.1%
 NeuroInflammatory systemic disease	1	0.1%
-Non-germinomatous germ cell tumor;Teratoma	1	0.1%
+Non-germinomatous germ cell tumor- Teratoma	1	0.1%
 Ossifying Fibroma	1	0.1%
 Papillary glioneuronal tumor	1	0.1%
 Primary CNS lymphoma	1	0.1%