| Title: | Automated Analysis of Phenotypic Data |
| Version: | 2.1.0 |
| Description: | Provides functions to analyze and visualize meristic and mensural phenotypic data in a comparative framework. The package implements an automated pipeline that summarizes traits, identifies diagnostic variables among groups, performs multivariate and univariate statistical analyses, and produces publication-ready graphics. Earlier implementation are described in Torres (2025) <doi:10.64898/2025.12.18.695244> (v1.0.0) and Torres (2026) <doi:10.1002/ece3.73111> (v2.0.0). |
| URL: | https://github.com/metalofis/Orangutan-R |
| BugReports: | https://github.com/metalofis/Orangutan-R/issues |
| License: | MIT + file LICENSE |
| Repository: | CRAN |
| Encoding: | UTF-8 |
| RoxygenNote: | 7.3.3 |
| Imports: | adegenet, dplyr, dunn.test, ggplot2, multcompView, RColorBrewer, rlang, scales, tidyr, vegan, withr |
| Suggests: | ragg |
| NeedsCompilation: | no |
| Packaged: | 2026-03-31 19:55:01 UTC; jtorreslopez2 |
| Author: | Javier Torres [aut, cre] |
| Maintainer: | Javier Torres <metalofis@gmail.com> |
| Date/Publication: | 2026-03-31 20:10:02 UTC |
Categorical Data Analysis
Description
Performs Chi-squared tests and generates proportional bar plots for categorical variables.
Usage
categorical_analyses(
data,
cat_vars,
output_dir,
palette_name = "Paired",
custom_colors = NULL
)
Arguments
data |
Data frame containing the variables |
cat_vars |
Character vector of categorical variable names |
output_dir |
Directory to save results |
palette_name |
RColorBrewer palette name for categorical fills (default: "Paired") |
custom_colors |
Optional named vector of colors for species (not used for categorical fills) |
Value
A data frame with Chi-squared test results
Generate HTML interpretation report
Description
Generate HTML interpretation report
Usage
generate_html_report(output_dir)
Arguments
output_dir |
Directory where output files are saved. |
Run multivariate statistical tests
Description
Performs beta-dispersion and PERMANOVA analyses.
Usage
multivariate_tests(df, output_dir, seed_disp = NULL, seed_perm = NULL)
Arguments
df |
A cleaned data frame containing morphometric traits. |
output_dir |
Directory where results will be written. |
seed_disp |
Optional integer; if provided, sets the random seed immediately before beta-dispersion permutation tests to ensure reproducibility. |
seed_perm |
Optional integer; if provided, sets the random seed immediately before PERMANOVA permutation tests to ensure reproducibility. |
Value
A list containing multivariate test results.
Run Orangutan
Description
Runs the full Orangutan morphometric analysis pipeline.
Usage
run_orangutan(
data_path,
output_dir = file.path(dirname(data_path), paste0("orangutan_outputs_",
format(Sys.time(), "%Y%m%d_%H%M%S"))),
apply_allometry = FALSE,
allometry_var = NULL,
remove_outliers = FALSE,
outlier_vars = NULL,
outlier_tail_pct = 0.05,
palette_name = "Paired",
custom_colors = NULL,
species_to_encircle = character(0),
seeds = list(betadisper = 123, permanova = 456),
point_aes = list(point_size = 3.5, jitter_width = 0.1, jitter_alpha = 0.8, jitter_shape
= 21, jitter_color = "black", jitter_stroke = 0.35),
mean_aes = list(size = 1.8, shape = 21, fill = "white", color = "black", stroke = 0.6),
violin_aes = list(alpha = 0.4),
box_aes = list(alpha = 0.4, width = 0.15),
label_aes = list(text_size = 6, axis_text_size = 10, title_size = 12, label_offset =
0.05),
label_templates = NULL,
verbose = FALSE
)
Arguments
data_path |
Path to input CSV file |
output_dir |
Output directory for results |
apply_allometry |
Logical; apply allometric correction |
allometry_var |
Character; size variable for allometry |
remove_outliers |
Logical; remove outliers |
outlier_vars |
Variables used for outlier detection |
outlier_tail_pct |
Tail proportion for Tukey filtering |
palette_name |
RColorBrewer palette name |
custom_colors |
Optional named vector of hex colors for species (e.g., |
species_to_encircle |
Species to encircle in multivariate plots |
seeds |
A named list of integer seeds for reproducibility, with elements:
|
point_aes |
List of point aesthetics |
mean_aes |
List of mean-point aesthetics |
violin_aes |
List of violin aesthetics |
box_aes |
List of boxplot aesthetics |
label_aes |
List of label/text aesthetics |
label_templates |
Optional plot label templates |
verbose |
Logical; if TRUE, print progress messages. Defaults to FALSE. |
Value
A list containing results from all analyses
Examples
# Create a tiny example dataset in a temporary file
tmp <- tempfile(fileext = ".csv")
toy_data <- data.frame(
species = c("A", "A", "B", "B", "C", "C"),
trait1 = c(1, 2, 5, 6, 9, 10),
trait2 = c(3, 4, 7, 8, 11, 12),
trait3 = c(2, 3, 6, 7, 10, 11)
)
write.csv(toy_data, tmp, row.names = FALSE)
# Create a temporary output directory
out_dir <- tempdir()
# Set a named list of seeds for reproducibility
seeds <- list(betadisper = 123, permanova = 456)
# Run Orangutan on the toy dataset
res <- run_orangutan(
data_path = tmp,
output_dir = out_dir,
seeds = seeds,
verbose = FALSE
)
# Inspect returned object
str(res)
# Clean up temporary dataset file
unlink(tmp)