Merge pull request #588 from d3b-center/zzgeng/supp_table

Update manuscript: Generate tables

tables/output_tables.Rmd → tables/01-output_tables.Rmd

@@ -7,7 +7,7 @@ output:
     toc: TRUE
     toc_float: TRUE
 params:
-  release: v14
+  release: v15
 ---
 
 Code adapted from: https://github.com/AlexsLemonade/OpenPBTA-analysis/blob/master/tables/output_tables.Rmd
@@ -46,7 +46,7 @@ histology_file <- file.path(data_dir, "histologies.tsv")
 
 # Define output files and sheet names, when appropriate
 ```{r}
-table_s1_file <- file.path(results_dir, "histologies.xlsx")
+table_s1_file <- file.path(results_dir, "SuppTable1-Histologies.xlsx")
 ```
 
 # Read files

tables/02-molecular_subtype_table.R

@@ -0,0 +1,50 @@
+library(tidyverse)
+library(openxlsx)
+
+## set directories
+root_dir <- rprojroot::find_root(rprojroot::has_dir(".git"))
+input_dir <- file.path(root_dir, "data")
+output_dir <- file.path(root_dir, "tables", "results")
+
+## read file
+hist <- read_tsv(file.path(input_dir, "histologies.tsv"))
+
+## all molecular subtype ##
+hist_sample <- hist %>% 
+  filter(sample_type == "Tumor") %>%
+  select(match_id, broad_histology, molecular_subtype) %>% 
+  filter(!is.na(molecular_subtype)) %>% 
+  distinct() %>% 
+  group_by(broad_histology, molecular_subtype) %>% 
+  tally() %>% 
+  dplyr::rename("Tumors" = "n")
+
+hist_patient <- hist %>% 
+  filter(sample_type == "Tumor") %>%
+  select(Kids_First_Participant_ID, broad_histology, molecular_subtype) %>% 
+  filter(!is.na(molecular_subtype)) %>% 
+  distinct() %>% 
+  group_by(broad_histology, molecular_subtype) %>% 
+  tally() %>% 
+  dplyr::rename("Patients" = "n")
+
+hist_combined <- hist_sample %>% 
+  left_join(hist_patient) %>% 
+  dplyr::rename("Broad Histologies" = "broad_histology", 
+                "OpenPedCan Molecular Subtype" = "molecular_subtype")
+hist_combined <- hist_combined %>% 
+  ungroup() %>%
+  add_row(`Broad Histologies` = "", 
+          `OpenPedCan Molecular Subtype` = "Total", 
+          Tumors = sum(hist_combined$Tumors), 
+          Patients = sum(hist_combined$Patients))
+
+## MB subtype 
+## change the directory once the PR is merged ##
+MB_subtype <- read_tsv(file.path(output_dir, "mb_shh_molecular_subtypes.tsv"))
+
+## fianl table
+final_table <- list(histologies_summary = hist_combined, 
+                    MB_SHH_subtype = MB_subtype)
+write.xlsx(final_table, 
+           file.path(output_dir, "SuppTable2-Molecular-Subtype-Table.xlsx"))

tables/software_version.Rmd → tables/03-software_version.Rmd

@@ -119,5 +119,5 @@ list_package_table <- list(r_packages = r_packages,
                            python_libraries = python_libraries, 
                            cli_tools = cli_tools)
 
-openxlsx::write.xlsx(list_package_table, "results/list_package_table.xlsx")
+openxlsx::write.xlsx(list_package_table, "results/SuppTable3-List_Package_Table.xlsx")
 ```

tables/software_version.html → tables/03-software_version.html

@@ -1629,16 +1629,17 @@ <h4 class="date">2024-05-30</h4>
 
 
 <pre class="r"><code>library(tidyverse)</code></pre>
-<pre><code>## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
+<pre><code>## ── Attaching core tidyverse packages ─────────────────────────────────────────────────────────── tidyverse 2.0.0 ──
 ## ✔ dplyr     1.1.4     ✔ readr     2.1.5
 ## ✔ forcats   1.0.0     ✔ stringr   1.5.1
 ## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
 ## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
 ## ✔ purrr     1.0.2     
-## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
+## ── Conflicts ───────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
 ## ✖ dplyr::filter() masks stats::filter()
 ## ✖ dplyr::lag()    masks stats::lag()
 ## ℹ Use the conflicted package (&lt;http://conflicted.r-lib.org/&gt;) to force all conflicts to become errors</code></pre>
+<pre class="r"><code>library(openxlsx)</code></pre>
 <div id="generate-softwarepackages-table" class="section level2">
 <h2>generate <code>software/packages</code> table</h2>
 <div id="r-packages" class="section level3">
@@ -1759,7 +1760,7 @@ <h3>combine all together</h3>
                            python_libraries = python_libraries, 
                            cli_tools = cli_tools)
 
-openxlsx::write.xlsx(list_package_table, &quot;results/list_package_table.xlsx&quot;)</code></pre>
+openxlsx::write.xlsx(list_package_table, &quot;results/SuppTable3-List_Package_Table.xlsx&quot;)</code></pre>
 </div>
 </div>