Add family size histogram

README.org

@@ -0,0 +1,7 @@
+#+title: Comparative Genomics Project
+#+author: Samuel Ortion
+#+date: 2024-2025
+
+Analysis of Tandemly Arrayed Genes in /Glycine max/ (soy) proteome.
+
+Part of the "Comparative Genomics" teaching unit in M2 GENomics Informatics and Mathematics for Health and Environment (GENIOMHE) at Université d'Évry Paris-Saclay.

environment.yml

@@ -0,0 +1 @@
+ 

renv/.gitignore

@@ -0,0 +1,7 @@
+library/
+local/
+cellar/
+lock/
+python/
+sandbox/
+staging/

renv/settings.json

@@ -0,0 +1,19 @@
+{
+  "bioconductor.version": null,
+  "external.libraries": [],
+  "ignored.packages": [],
+  "package.dependency.fields": [
+    "Imports",
+    "Depends",
+    "LinkingTo"
+  ],
+  "ppm.enabled": null,
+  "ppm.ignored.urls": [],
+  "r.version": null,
+  "snapshot.type": "implicit",
+  "use.cache": true,
+  "vcs.ignore.cellar": true,
+  "vcs.ignore.library": true,
+  "vcs.ignore.local": true,
+  "vcs.manage.ignores": true
+}

src/family_size_hist.R

@@ -0,0 +1,24 @@
+#!/usr/bin/env Rscript
+library(dplyr)
+library(ggplot2)
+
+args <- commandArgs(trailingOnly=TRUE)
+input_file <- args[1]
+output_file <- args[2]
+title <- args[3]
+
+family_df <- read.table(input_file, header=FALSE)
+colnames(family_df) <- c("geneid", "familyid")
+
+count_df <- family_df %>% count(familyid)
+distribution_df <- count_df %>% count(n)
+
+theme_set(theme_grey(base_size=20))
+
+ggplot(distribution_df, aes(x=n, y=nn)) +
+  geom_bar(stat='identity') +
+  labs(title="Duplicate Gene Family Sizes",
+       subtitle=title) +
+  xlab("family size") +
+  ylab("count")
+ggsave(output_file)