Type:	Package
Title:	Probability of Sporulation Potential in MAGs
Version:	0.1.0
Description:	Implements an ensemble machine learning approach to predict the sporulation potential of metagenome-assembled genomes (MAGs) from uncultivated Firmicutes based on the presence/absence of sporulation-associated genes.
License:	Artistic-2.0
Encoding:	UTF-8
Imports:	dplyr, tidyr, tibble, stats
RoxygenNote:	7.3.2
Suggests:	testthat (≥ 3.0.0), caret, kernlab, randomForest, readr
Config/testthat/edition:	3
NeedsCompilation:	no
Packaged:	2025-05-27 12:19:32 UTC; douglas
Author:	Douglas Terra Machado [aut, cre], Otávio José Bernardes Brustolini [ctb], Ellen dos Santos Corrêa [ctb], Ana Tereza Ribeiro Vasconcelos [ctb]
Maintainer:	Douglas Terra Machado <dougterra@gmail.com>
Depends:	R (≥ 3.5.0)
Repository:	CRAN
Date/Publication:	2025-05-29 18:20:09 UTC

Build binary presence/absence matrix of sporulation genes

Description

Transforms the output of sporulation_gene_name() into a wide-format matrix indicating the presence (1) or absence (0) of each sporulation-associated gene per genome.

Usage

build_binary_matrix(df)

Arguments

Value

A wide-format binary matrix with genomes in rows and genes in columns.

Examples

# Load package
library(SpoMAG)

# Load example annotation tables
file_spor <- system.file("extdata", "one_sporulating.csv.gz", package = "SpoMAG")
file_aspo <- system.file("extdata", "one_asporogenic.csv.gz", package = "SpoMAG")

# Read files
df_spor <- readr::read_csv(file_spor, show_col_types = FALSE)
df_aspo <- readr::read_csv(file_aspo, show_col_types = FALSE)

# Step 1: Extract sporulation-related genes
genes_spor <- sporulation_gene_name(df_spor)
genes_aspo <- sporulation_gene_name(df_aspo)

# Step 2: Convert to binary matrix
bin_spor <- build_binary_matrix(genes_spor)
bin_aspo <- build_binary_matrix(genes_aspo)

Predict Sporulation Potential

Description

This function predicts the sporulation potential of MAGs using an ensemble learning model. It uses probabilities from Random Forest and SVM classifiers as inputs to a meta-model.

Usage

predict_sporulation(binary_matrix)

Arguments

Value

A tibble with predicted class and probability of sporulation for each genome.

Examples

# Load package
library(SpoMAG)

# Load example annotation tables
file_spor <- system.file("extdata", "one_sporulating.csv.gz", package = "SpoMAG")
file_aspo <- system.file("extdata", "one_asporogenic.csv.gz", package = "SpoMAG")

# Read files
df_spor <- readr::read_csv(file_spor, show_col_types = FALSE)
df_aspo <- readr::read_csv(file_aspo, show_col_types = FALSE)

# Step 1: Extract sporulation-related genes
genes_spor <- sporulation_gene_name(df_spor)
genes_aspo <- sporulation_gene_name(df_aspo)

# Step 2: Convert to binary matrix
bin_spor <- build_binary_matrix(genes_spor)
bin_aspo <- build_binary_matrix(genes_aspo)

# Step 3: Predict using ensemble model (preloaded in package)

result_spor <- predict_sporulation(bin_spor)
result_aspo <- predict_sporulation(bin_aspo)

 

Identify Sporulation-Associated Genes

Description

This function identifies sporulation-associated genes in a genome annotation data frame. It searches for gene names and KEGG Orthology identifiers related to sporulation steps and returns a data frame with annotated sporulation genes and a consensus name.

Usage

sporulation_gene_name(df)

Arguments

Value

A data frame of sporulation-associated genes with standardized names and spo_process tags.

Examples

# Load package
library(SpoMAG)
# Load example annotation tables
file_spor <- system.file("extdata", "one_sporulating.csv.gz", package = "SpoMAG")
file_aspo <- system.file("extdata", "one_asporogenic.csv.gz", package = "SpoMAG")

# Read files
df_spor <- readr::read_csv(file_spor, show_col_types = FALSE)
df_aspo <- readr::read_csv(file_aspo, show_col_types = FALSE)

# Step 1: Extract sporulation-related genes
genes_spor <- sporulation_gene_name(df_spor)
genes_aspo <- sporulation_gene_name(df_aspo)