EigenRF is an R package designed to improve the normalization of metabolomics data. It enhances the previous EigenMS method by incorporating a random forest regression model to capture nonlinear biological variations of interest. This method not only eliminates systematic errors but also preserves the biological variations of interest, leading to improved accuracy and reproducibility in metabolomics research.
Advanced Normalization: Integrates random forest regression to address nonlinearities, enhancing the accuracy of data normalization. Data Preservation: Designed to maintain the integrity of biological variations, ensuring that the normalized data reflects true biological differences. Enhanced Reproducibility: The method is developed with a focus on improving the reproducibility of metabolomics studies, allowing for more consistent results across different datasets and experimental conditions.
You can install the EigenRF package directly from GitHub using the following command:
if (!requireNamespace("devtools", quietly = TRUE)) { install.packages("devtools") } devtools::install_github("statisticsinMS/EigenRF")
To use the EigenRF normalization method, simply load the library and apply the Eigen_RF function to your data:
library(EigenRF)
peak <- your_peak_data
groups <- your_group_data
metabolites <- your_metabolites_data
normalized_data <- Eigen_RF(peak, groups, metabolites)
peak: A data frame containing the peak intensity values. groups: A vector indicating the group affiliation of each sample. metabolites: A data frame or vector containing metabolite data.
The Eigen_RF function returns a list with the normalized peak table, facilitating the analysis of differential metabolites with improved reproducibility.
This research was funded by the National Key R&D Program of China and the National Natural Science Foundation of China.
Chencheng Tang, Dongfang Huang, Xudong Xing and Hua Yang.