tidychem

Read, preprocess, and featurize chemical data using RDKit.

A lightweight R interface for accessing RDKit via the RDKit Python API.

Installation

You can install tidychem from GitHub:

remotes::install_github("nanxstats/tidychem")

Install rdkit

A simple way to install the Python package rdkit that tidychem can discover easily, is to run the helper function tidychem::install_rdkit(). By default, it installs rdkit into an virtual environment named r-rdkit.

tidychem::install_rdkit()

This follows the best practices suggested by the reticulate vignette Managing an R Package’s Python Dependencies. There are also recommendations in the vignette on how to manage multiple R packages with different Python dependencies.

Usage

library("tidychem")

"smi-multiple.smi" |>
  tidychem_example() |>
  read_smiles() |>
  fp_morgan()