| Title: | QSAR Modeling with Multiple Algorithms: MLR, PLS, and Random Forest |
| Version: | 1.0.0 |
| Description: | Quantitative Structure-Activity Relationship (QSAR) modeling is a valuable tool in computational chemistry and drug design, where it aims to predict the activity or property of chemical compounds based on their molecular structure. In this vignette, we present the 'rQSAR' package, which provides functions for variable selection and QSAR modeling using Multiple Linear Regression (MLR), Partial Least Squares (PLS), and Random Forest algorithms. |
| License: | MIT + file LICENSE |
| Encoding: | UTF-8 |
| RoxygenNote: | 7.2.3 |
| Depends: | R (≥ 3.6.0), dplyr, corrplot, tibble, gridExtra |
| Imports: | utils, rcdk (≥ 3.8.1), ggplot2, caret, pls,randomForest, leaps, stats |
| VignetteBuilder: | knitr |
| NeedsCompilation: | no |
| Packaged: | 2024-04-02 08:26:12 UTC; USER |
| Author: | Oche Ambrose George
 [aut, cre] |
| Maintainer: | Oche Ambrose George <ocheab1@gmail.com> |
| Repository: | CRAN |
| Date/Publication: | 2024-04-02 13:22:04 UTC |
| Suggests: | rmarkdown,knitr |
Build QSAR models with k-fold cross-validation
Description
This function builds QSAR (Quantitative Structure-Activity Relationship) models using multiple algorithms such as Multiple Linear Regression (MLR), Partial Least Squares (PLS), and Random Forest with k-fold cross-validation.
Usage
build_qsar_models(data_file, k = 5)
Arguments
data_file |
The file path of the dataset. |
k |
The number of folds for cross-validation (default is 5). |
Value
A list containing MLR, PLS, and Random Forest models with their predictions, actuals, and formulas.
Create correlation plots for QSAR models
Description
This function creates correlation plots for QSAR models, showing the relationship between predicted and actual values with a correlation coefficient.
Usage
correlation_plots(model_results)
Arguments
model_results |
A list containing QSAR model results. |
Value
A list of correlation plots for each QSAR model.
Generate Molecular Descriptors from SDF File
Description
This function reads an SDF (Structure Data File) containing molecular structures and calculates molecular descriptors for each molecule.
Usage
generate_descriptors_from_sdf(sdf_file)
Arguments
sdf_file |
Path to the SDF file. |
Value
A matrix containing molecular descriptors for each molecule in the SDF file.
Perform variable selection using regression subsets
Description
This function performs variable selection using regression subsets method.
Usage
perform_variable_selection(file_path, outcome_col, des_sel_meth = "exhaustive")
Arguments
file_path |
The file path of the dataset. |
outcome_col |
The name of the outcome column. |
des_sel_meth |
The method for variable selection (default is "exhaustive"). |
Value
A data frame containing the selected variables and the outcome.
Function to create residual plots with model type labels
Description
Function to create residual plots with model type labels
Usage
residual_plots(model_results)
Arguments
model_results |
A list containing model results |
Value
A list of ggplot objects representing residual plots