This repository contains RanDepict, an easy-to-use utility to generate a big variety of chemical structure depictions (random depiction styles and image augmentations) based on RDKit, CDK, Indigo and PIKAChU.
$ git clone https://github.com/OBrink/RanDepict.git
$ cd RanDepict
$ python -m pip install -U pip #Upgrade pip
$ pip install .
$ python -m pip install -U pip #Upgrade pip
$ pip install git+https://github.com/OBrink/RanDepict.git
$ pip install RanDepict
Note We recommend using RanDepict inside a Conda environment to facilitate the installation of the dependencies.
$ wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
$ bash Miniconda3-latest-Linux-x86_64.sh
$ echo -e "channels:\n - conda-forge\n - nodefaults" > ~/.condarc
$ conda update conda
$ conda install conda-libmamba-solver
$ conda config --set experimental_solver libmamba
$ conda create --name RanDepict python=3.8
$ conda activate RanDepict
# pypi has rdkit so not necessary to install it using conda
# $ conda install -c rdkit rdkit
$ pip install -e ".[dev]" # will install pytest and tox
# To run tests for python 3.8
$ tox -e py38
from RanDepict import RandomDepictor
smiles = "CN1C=NC2=C1C(=O)N(C(=O)N2C)C"
with RandomDepictor() as depictor:
image = depictor(smiles)
Have a look at the examples in our demo notebook. A more detailed documentation is provided here.
Here are some examples of depictions of caffeine without augmentations (left) and with augmentations (right) that were automatically created using RanDepict.