阅读中文

REINVENT is a molecular design tool for de novo design, scaffold hopping, R-group replacement, linker design, molecule optimization, and other small molecule design tasks. At its heart, REINVENT uses a Reinforcement Learning (RL) algorithm to generate optimized molecules compliant with a user defined property profile defined as a multi-component score. Transfer Learning (TL) can be used to create or pre-train a model that generates molecules closer to a set of input molecules.

A preprint with more details is available on ChemRxiv: REINVENT4: Modern AI-Driven Generative Molecule Design. See AUTHORS.md for references to previous papers.

REINVENT is being developed on and for Linux but is also known to work on MacOSX. Windows is not directly supported but so far we know that all run modes work on the CPU.

The code is written in Python 3 (>= 3.10). The list of dependencies can be found in the repository (see also Installation below).

A GPU is not strictly necessary but strongly recommended for performance reasons especially for transfer learning/model training. It should be noted that reinforcement learning (RL) requires the computation of scores. Most scoring components run on the CPU thus a GPU is of less importance for RL depending on how much time is spent on the CPU.

Note that if no GPU is installed in your computer the code will run on the CPU automatically. REINVENT supports NVIDIA and also some AMD GPUs. For most design tasks a memory of about 8 GiB for both CPU main memory and GPU memory is sufficient.

1. Clone this Git repository.
2. Install a compatible version of Python, for example with Conda (other virtual environments like Docker, pyenv, or the system package manager would work too).

   conda create --name reinvent4 python=3.10
   conda activate reinvent4

3. Change directory into the repository and install the dependencies from the lockfile:

   pip install -r requirements-linux-64.lock

4. Optional: if you want to use AMD GPUs on Linux you would need to install the ROCm PyTorch version manually after installation of the dependencies in point 3, e.g.

   pip install torch==1.13.1+rocm5.2 torchvision==0.14.1+rocm5.2 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/rocm5.2

5. Install the tool. The dependencies were already installed in the previous step, so there is no need to install them again (flag `--no-deps). If you want to install in editable mode (changes to the code are automatically picked up) add -e before the dot.

   pip install --no-deps . 

6. Test the tool. The installer has added a script reinvent to your PATH.

   reinvent --help

REINVENT is a command line tool and works principally as follows

reinvent -l sampling.log sampling.toml

This writes logging information to the file sampling.log. If you wish to write this to the screen, leave out the -l sampling.log part. sampling.toml is the configuration file. The main user format is TOML as it tends to be more use friendly. JSON can be used too, add -f json, but a specialised editor is recommended as the format is very sensitive to minor changes.

Sample configuration files for all run modes are located in config/toml of the repository and file paths therein would need to be adjusted to your local installation. In particular, ready made prior models are located in priors and you would choose a model and the appropriate run mode depending on the research problem you are trying to address. There is additional information in config/toml in several *.md files with instructions on how to configure the TOML file.

NOTE: these will be updated at a later time!

Update the lock files with pip-tools (please, do not edit the files manually):

pip-compile --extra-index-url=https://download.pytorch.org/whl/cu113 --extra-index-url=https://pypi.anaconda.org/OpenEye/simple --resolver=backtracking pyproject.toml

To update a single package, use pip-compile --upgrade-package somepackage (see the documentation for pip-tools).

The scoring subsystem uses a simple plugin mechanism (Python native namespace packages). If you wish to write your own plugin, follow the instructions below. The public repository contains a contrib directory with some useful examples.

1. Create /top/dir/somewhere/reinvent\_plugins/components where /top/dir/somewhere is a convenient location for you.
2. Do not place a __init__.py in either reinvent_plugins or components as this would break the mechanism. It is fine to create normal packages within components as long as you import those correctly.
3. Place a file whose name starts with comp_* into reinvent_plugins/components. Files with different names will be ignored i.e. not imported. The directory will be searched recursively so structure your code as needed but directory/package names must be unique.
4. Tag the scoring component class(es) in that file with the @add_tag decorator. More than one component class can be added to the same comp_ file. See existing code.
5. Tag at most one dataclass as parameter in the same file, see existing code. This is optional.
6. There is no need to touch any of the REINVENT code.
7. Set or add /top/dir/somewhere to the PYTHONPATH environment variable or use any other mechanism to extend sys.path.
8. The scoring component should now be automatically picked up by REINVENT.

This is primarily for developers and admins/users who wish to ensure that the installation principally works. The information here is not relevant to the practical use of REINVENT. Please refer to Basic Usage for instructions on how to use the reinvent command.

The REINVENT project uses the pytest framework for its tests. Before you run them you first have to create a configuration file which the tests will use.

In the project directory, create a config.json file in the configs/ directory. You can use the example config example.config.json as a base. Make sure that you set MAIN_TEST_PATH to a non-existent directory. That is where temporary files will be written during the tests. If it is set to an existing directory, that directory will be removed once the tests have finished.

Some tests require a proprietary OpenEye license. You have to set up a few things to make the tests read your license. The simple way is to just set the OE_LICENSE environment variable to the path of the file containing the license.

Once you have a configuration and your license can be read, you can run the tests.

$ pytest tests