From 400ca776e0b0081b9ef7bf6392b1265743f556ff Mon Sep 17 00:00:00 2001
From: Elias Projahn <elias@johrpan.de>
Date: Mon, 16 Aug 2021 17:21:01 +0200
Subject: [PATCH] Simplify data format and correct scale labels

---
 data.R         | 18 ++++++++++++++----
 scatter_plot.R | 32 ++++++++------------------------
 2 files changed, 22 insertions(+), 28 deletions(-)

diff --git a/data.R b/data.R
index b75801c..a38bf04 100644
--- a/data.R
+++ b/data.R
@@ -41,7 +41,11 @@ load_data <- function(path) {
         median_distance = numeric()
     )
 
-    distances <- data.table(geneid = integer())
+    distances <- data.table(
+        species = character(),
+        gene = integer(),
+        distance = integer()
+    )
 
     # Each file will contain data on one species.
     file_names <- list.files(paste(path, "genomes", sep = "/"))
@@ -63,13 +67,19 @@ load_data <- function(path) {
                 median_distance = median(species_distances[, dist])
             )))
 
-            # Column names have to be unique for each species.
-            setnames(species_distances, "dist", species_id)
+            species_distances <- data.table(
+                species = species_id,
+                gene = species_distances[, geneid],
+                distance = species_distances[, dist]
+            )
 
-            distances <- merge(distances, species_distances, all = TRUE)
+            distances <- rbindlist(list(distances, species_distances))
         }
     }
 
+    # Order species by there median distance.
+    setorder(species, median_distance)
+
     list(
         genes = genes,
         species = species,
diff --git a/scatter_plot.R b/scatter_plot.R
index 6cf8f10..1ed1e25 100644
--- a/scatter_plot.R
+++ b/scatter_plot.R
@@ -3,44 +3,28 @@ library(ggplot2)
 
 #' Draw a scatter plot containing gene positions.
 scatter_plot <- function(gene_ids, data) {
-    species <- data$species
-    setorder(species, median_distance)
-
-    distances <- data$distances[geneid %in% gene_ids]
-
     plot <- ggplot() +
-        scale_x_continuous(
+        scale_x_discrete(
             name = "Species",
-            breaks = seq_len(nrow(species)),
-            labels = species$label
+            breaks = data$species$id,
+            labels = data$species$label
         ) +
-        scale_y_continuous(name = "Distance to telomeres [Mbp]") +
-        geom_line(
-            species,
-            mapping = aes(
-                x = as.numeric(rownames(species)),
-                y = median_distance / 1000000
-            )
-        )
+        scale_y_continuous(name = "Distance to telomeres [Mbp]")
 
     colors <- rainbow(length(gene_ids))
 
     for (i in seq_len(length(gene_ids))) {
         gene_id <- gene_ids[i]
 
-        gene_distances <- data.table(
-            index = as.numeric(rownames(species)),
-            distance = unlist(distances[geneid == gene_id, -1])
-        )
-
         plot <- plot +
             geom_point(
-                gene_distances,
+                data$distances[gene == gene_id],
                 mapping = aes(
-                    x = index,
+                    x = species,
                     y = distance / 1000000,
                 ),
-                color = colors[i]
+                color = colors[i],
+                size = 4
             )
     }