add new chapters

halbritter-lab · Oct 11, 2023 · f42d5bc · f42d5bc
1 parent babcf37
commit f42d5bc
Show file tree

Hide file tree

Showing 6 changed files with 132 additions and 48 deletions.
diff --git a/analyses/C_AnnotateMergedTable/stringdb_protein_links.2023-10-11.txt.gz b/analyses/C_AnnotateMergedTable/stringdb_protein_links.2023-10-11.txt.gz
diff --git a/edit_docs/01-analyses-tables.Rmd b/edit_docs/01-analyses-tables.Rmd
@@ -8,21 +8,22 @@ This table shows the merged results of all analyses files as a wide table with s
 
 ```{r, echo=FALSE}
 merge_analyses_sources_reformat <- merge_analyses_sources %>%
-  mutate(hgnc_id = paste0('<a href="https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:',
+  mutate(gene = paste0('<a href="https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:',
     hgnc_id,
-    '" target="_blank" >',
-    hgnc_id,
-    '</a>')) %>%
-  mutate(approved_symbol = paste0('<i>',
+    '" target="_blank" ><i>',
     approved_symbol,
-    '</i>'))
+    '</i></a>'),
+    , .before = approved_symbol) %>%
+  select(-hgnc_id, -approved_symbol)
 
 datatable(merge_analyses_sources_reformat,
           filter = 'top', # this argument positions the filtering input at the top of the table
           escape = FALSE, # this argument renders the links as HTML
           extensions = 'Buttons', # this argument adds an extension for download buttons
           options = list(
             dom = 'Blfrtip',
+            scrollX = '400px',
+            scroller = TRUE,
             buttons = c('copy',
               'csv',
               'excel',
@@ -40,14 +41,13 @@ This table shows results of the first analysis searching kidney disease associat
 
 ```{r, echo=FALSE}
 PanelApp_genes_reformat <- PanelApp_genes %>%
-  mutate(hgnc_id = paste0('<a href="https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:',
-    hgnc_id,
-    '" target="_blank" >',
+  mutate(gene = paste0('<a href="https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:',
     hgnc_id,
-    '</a>')) %>%
-  mutate(approved_symbol = paste0('<i>',
+    '" target="_blank" ><i>',
     approved_symbol,
-    '</i>'))
+    '</i></a>'),
+    , .before = approved_symbol) %>%
+  select(-hgnc_id, -approved_symbol, -gene_name_reported)
 
 datatable(PanelApp_genes_reformat,
           filter = 'top', # this argument positions the filtering input at the top of the table
@@ -61,14 +61,13 @@ This table shows results of the second analysis searching kidney disease associa
 
 ```{r, echo=FALSE}
 Literature_genes_reformat <- Literature_genes %>%
-  mutate(hgnc_id = paste0('<a href="https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:',
-    hgnc_id,
-    '" target="_blank" >',
+  mutate(gene = paste0('<a href="https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:',
     hgnc_id,
-    '</a>')) %>%
-  mutate(approved_symbol = paste0('<i>',
+    '" target="_blank" ><i>',
     approved_symbol,
-    '</i>'))
+    '</i></a>'),
+    , .before = approved_symbol) %>%
+  select(-hgnc_id, -approved_symbol, -gene_name_reported)
 
 datatable(Literature_genes_reformat,
           filter = 'top', # this argument positions the filtering input at the top of the table
@@ -82,14 +81,13 @@ This table shows results of the third analysis searching kidney disease associat
 
 ```{r, echo=FALSE}
 DiagnosticPanels_genes_reformat <- DiagnosticPanels_genes %>%
-  mutate(hgnc_id = paste0('<a href="https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:',
+  mutate(gene = paste0('<a href="https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:',
     hgnc_id,
-    '" target="_blank" >',
-    hgnc_id,
-    '</a>')) %>%
-  mutate(approved_symbol = paste0('<i>',
+    '" target="_blank" ><i>',
     approved_symbol,
-    '</i>'))
+    '</i></a>'),
+    , .before = approved_symbol) %>%
+  select(-hgnc_id, -approved_symbol, -gene_name_reported)
 
 datatable(DiagnosticPanels_genes_reformat,
           filter = 'top', # this argument positions the filtering input at the top of the table
@@ -103,14 +101,13 @@ This table shows results of the fourth analysis searching kidney disease associa
 
 ```{r, echo=FALSE}
 HPO_genes_reformat <- HPO_genes %>%
-  mutate(hgnc_id = paste0('<a href="https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:',
-    hgnc_id,
-    '" target="_blank" >',
+  mutate(gene = paste0('<a href="https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:',
     hgnc_id,
-    '</a>')) %>%
-  mutate(approved_symbol = paste0('<i>',
+    '" target="_blank" ><i>',
     approved_symbol,
-    '</i>'))
+    '</i></a>'),
+    , .before = approved_symbol) %>%
+  select(-hgnc_id, -approved_symbol, -gene_name_reported)
 
 datatable(HPO_genes_reformat,
           filter = 'top', # this argument positions the filtering input at the top of the table
@@ -124,14 +121,13 @@ This table shows results of the fifth analysis searching kidney disease associat
 
 ```{r, echo=FALSE}
 PubTator_genes_reformat <- PubTator_genes %>%
-  mutate(hgnc_id = paste0('<a href="https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:',
-    hgnc_id,
-    '" target="_blank" >',
+  mutate(gene = paste0('<a href="https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:',
     hgnc_id,
-    '</a>')) %>%
-  mutate(approved_symbol = paste0('<i>',
+    '" target="_blank" ><i>',
     approved_symbol,
-    '</i>'))
+    '</i></a>'),
+    , .before = approved_symbol) %>%
+  select(-hgnc_id, -approved_symbol, -gene_name_reported)
 
 datatable(PubTator_genes_reformat,
           filter = 'top', # this argument positions the filtering input at the top of the table

diff --git a/edit_docs/03-high-evidence-curation.Rmd b/edit_docs/03-high-evidence-curation.Rmd
@@ -0,0 +1,33 @@
+# Curation of high evidence genes {#manual-curation}
+
+## Table of high evidence genes
+
+This table shows the annotated high evidence genes.
+
+```{r, echo=FALSE, warning=FALSE, out.width = "100%"}
+high_evidence_annotated_table_reformat <- high_evidence_annotated_table %>%
+  mutate(gene = paste0('<a href="https://www.genenames.org/data/gene-symbol-report/#!/hgnc_id/HGNC:',
+    hgnc_id,
+    '" target="_blank" ><i>',
+    approved_symbol,
+    '</i></a>'),
+    , .before = approved_symbol) %>%
+  select(-hgnc_id, -approved_symbol)
+
+datatable(high_evidence_annotated_table_reformat,
+          filter = 'top', # this argument positions the filtering input at the top of the table
+          escape = FALSE, # this argument renders the links as HTML
+          extensions = 'Buttons', # this argument adds an extension for download buttons
+          options = list(
+            dom = 'Blfrtip',
+            scrollX = '400px',
+            scroller = TRUE,
+            buttons = c('copy',
+              'csv',
+              'excel',
+              'pdf'), # here we add the download buttons for different formats
+            lengthMenu = list(c(10, 30, 50, -1), 
+                              c('10', '30', '50', 'All')) # here we change the selection options
+          )
+        )
+```
diff --git a/edit_docs/04-additional-analyses.Rmd b/edit_docs/04-additional-analyses.Rmd
@@ -0,0 +1,43 @@
+# Additional analyses {#additional-analyses}
+
+## Diagnostic panels content overlap
+
+> Below you can see a bar plot of the diagnostic panels content overlap.
+
+We used ten common diagnostic panels that can be ordered for kidney disease analysis and extracted the screened genes from them.
+Here we show the overlap of the genes in the different panels.
+
+```{r, echo=FALSE, warning=FALSE, out.width = "100%"}
+# Summarize the data
+count_data <- DiagnosticPanels_genes %>%
+  group_by(source_count) %>%
+  summarise(n = n())
+
+# Calculate the total number of genes
+total_genes <- sum(count_data$n)
+
+# Calculate the percentage of genes
+count_data <- count_data %>%
+  mutate(percentage = (n / total_genes) * 100)
+
+# Create a new column for fill color based on source_count values
+count_data <- count_data %>%
+  mutate(fill_color = case_when(
+    source_count == 1 ~ "Red",
+    source_count == 10 ~ "Green",
+    TRUE ~ "Gray"
+  ))
+
+# Create the plot
+diagnostic_panels_overlap_plot <- ggplot(count_data, aes(x = source_count, y = n, fill = fill_color)) +
+  geom_col(show.legend = FALSE) +
+  geom_text(aes(label = paste0(round(percentage, 1), "%")), vjust = -0.5) +
+  scale_x_continuous(breaks = seq(min(count_data$source_count), max(count_data$source_count), by = 1)) +
+  scale_fill_identity() +
+  labs(x = "Count of panels", y = "Number of Genes",
+       title = paste0("Number of genes in 10 clinical diagnostic panels for kidney disease (n = ", total_genes, ")")) +
+  theme_minimal()
+
+# convert to interactive using ggplotly
+ggplotly(diagnostic_panels_overlap_plot)
+```
diff --git a/edit_docs/_bookdown.yml b/edit_docs/_bookdown.yml
@@ -5,6 +5,8 @@ rmd_files:
     - "index.Rmd"
     - "01-analyses-tables.Rmd"
     - "02-analyses-plots.Rmd"
+    - "03-high-evidence-curation.Rmd"
+    - "04-additional-analyses.Rmd"
     - "references.Rmd"
 delete_merged_file: true
 language:

diff --git a/edit_docs/index.Rmd b/edit_docs/index.Rmd
@@ -18,13 +18,14 @@ url: https://halbritter-lab.github.io/kidney-genetics/
 ```{r setup, include=FALSE}
 knitr::opts_chunk$set(echo = TRUE)
 ## Load libraries
-library(readr) # needed to import CSV result files
-library(tidyverse) # needed to transform the tables
-library(DT) # needed to generate nice data tables in html
-library(plotly) # needed for upset plots
-library(knitr) # needed for draw.io files
-library(knitrdrawio) # needed for draw.io files
-library(config) # needed to load the config file
+library(readr)        # needed to import CSV result files
+library(tidyverse)    # needed to transform the tables
+library(DT)           # needed to generate nice data tables in html
+library(plotly)       # needed for upset plots
+library(knitr)        # needed for draw.io files
+library(knitrdrawio)  # needed for draw.io files
+library(config)       # needed to load the config file
+library(ggplot2)      # needed for plots
 ```
 
 <!-- here we load the config file -->
@@ -57,20 +58,29 @@ source("../analyses/functions/string-functions.R", local = TRUE)
 <!-- here we load the result csv file and compute numbers to update the diagrams -->
 ```{r, echo=FALSE, message=FALSE, warning=FALSE}
 ## load the CSV data
-## load and filter (newest) the files automatically
+## load and filter the (newest) files automatically
+
+# the merge_analyses_sources table
 merge_analyses_sources <- read_csv(get_newest_file("A_MergeAnalysesSources", "../analyses/A_MergeAnalysesSources/results"))
+
+# the other analyses tables
 PanelApp_genes <- read_csv(get_newest_file("01_PanelApp_genes", "../analyses/01_PanelApp/results"))
 Literature_genes <- read_csv(get_newest_file("02_Literature_genes", "../analyses/02_Literature/results"))
 DiagnosticPanels_genes <- read_csv(get_newest_file("03_DiagnosticPanels_genes", "../analyses/03_DiagnosticPanels/results"))
 HPO_genes <- read_csv(get_newest_file("04_HPO_genes", "../analyses/04_HPO/results"))
 PubTator_genes <- read_csv(get_newest_file("05_PubTator_genes", "../analyses/05_PubTator/results"))
 
+# the high_evidence_annotated_table
+high_evidence_annotated_table <- read_csv(get_newest_file("C_high_evidence_annotated_csv_table", "../analyses/C_AnnotateMergedTable/results"))
+
 # compute numbers for the diagrams
 all_genes <- merge_analyses_sources %>%
     nrow()
 
 high_evidence_genes <- merge_analyses_sources %>%
-    filter(evidence_count > 2) %>%
+    filter(evidence_count > 2)
+    
+high_evidence_genes_count <- high_evidence_genes %>%
     nrow()
 
 clingen_genes <- "XXX"
@@ -79,7 +89,7 @@ manualscoring_genes <- "YYY"
 replace_strings("static/img/figures/raw/curation_flow_diagram_raw.drawio",
     "static/img/figures/updated/curation_flow_diagram_current.drawio",
     c("ALL_GENES", "HIGHEVIDENCE_GENES", "CLINGEN_GENES", "MANUALSCORING_GENES"),
-    c(all_genes, high_evidence_genes, clingen_genes, manualscoring_genes))
+    c(all_genes, high_evidence_genes_count, clingen_genes, manualscoring_genes))
 
 # compute per source numbers with placeholders
 summary_counts <- merge_analyses_sources %>%
@@ -185,8 +195,8 @@ To automatically group the genes, we will present the results of phenotypic and
 <!-- TODO: Provide clustering and grouping results with numbers and proportions -->
 
 The number of genes extracted from the five analyzed sources of information is as follows: (1) `r format_number(summary_counts$count_01_PanelApp)`, (2) `r format_number(summary_counts$count_02_Literature)`, (3) `r format_number(summary_counts$count_03_DiagnosticPanels)`, (4) `r format_number(summary_counts$count_04_HPO)`, and (5) `r format_number(summary_counts$count_05_PubTator)`  
-Notably, **`r format_number(high_evidence_genes)`** genes (`r percent(high_evidence_genes / all_genes, digits = 1)`) of the **total `r format_number(all_genes)`** genes are present in three or more of the analyzed information sources, thus meeting our evidence criteria, indicating high confidence and their potential for diagnostic use.
-Of these high evidence genes, **`r format_number(genes_at_least_one_diagnostic_panel)`** (`r percent(genes_at_least_one_diagnostic_panel / high_evidence_genes, digits = 1)`) are present in at least one, and **`r format_number(genes_all_diagnostic_panels)`** (`r percent(genes_all_diagnostic_panels / high_evidence_genes, digits = 1)`) are present in all 10 comprehensive diagnostic laboratory panels.
+Notably, **`r format_number(high_evidence_genes_count)`** genes (`r percent(high_evidence_genes_count / all_genes, digits = 1)`) of the **total `r format_number(all_genes)`** genes are present in three or more of the analyzed information sources, thus meeting our evidence criteria, indicating high confidence and their potential for diagnostic use.
+Of these high evidence genes, **`r format_number(genes_at_least_one_diagnostic_panel)`** (`r percent(genes_at_least_one_diagnostic_panel / high_evidence_genes_count, digits = 1)`) are present in at least one, and **`r format_number(genes_all_diagnostic_panels)`** (`r percent(genes_all_diagnostic_panels / high_evidence_genes_count, digits = 1)`) are present in all 10 comprehensive diagnostic laboratory panels.
 
 To ensure currency, Kidney-Genetics will be updated regularly and automatically at XXX week intervals. We will also provide phenotypic and functional clustering results to facilitate gene grouping.  
 <!-- TODO: Provide information about the planned update framework -->