How do I install REINVENT on Windows or Mac?

REINVENT is tested only on Linux and requires Cuda-enabled GPUs, so installation on Windows or Mac may need virtualization or significant tweaks, and the Conda setup could be more complex due to platform-specific issues.

What's the difference between REINVENT and DeepChem for drug discovery?

REINVENT focuses on reinforcement learning for de novo molecular generation with property optimization, while DeepChem offers a broader toolkit for cheminformatics and ML, making REINVENT more specialized but less versatile for general tasks.

How can I customize property scoring in REINVENT?

Property scoring is configured via editable JSON templates; modify these files to define scoring functions based on target properties, as demonstrated in the Jupyter notebooks from the ReinventCommunity repo.

Is REINVENT still being developed or should I use version 4?

REINVENT 3.2 is archived and no longer maintained; all further development is on REINVENT 4, so new users should consider migrating to the updated version for ongoing support and features.

Can REINVENT run without a GPU for smaller experiments?

While technically possible, REINVENT is optimized for Cuda-enabled GPUs to handle the computational load of RL and molecular generation, so CPU-only runs may be impractically slow for most use cases.

REINVENT — RL Framework for Drug Design

What is REINVENT?

REINVENT is a reinforcement learning framework for de novo drug design that generates novel molecular structures with optimized properties. It combines generative models with property prediction to efficiently explore chemical space and discover potential drug candidates. The framework addresses the challenge of finding new chemical entities by using RL to optimize molecules toward specific biological activities and chemical properties.

Target Audience

Computational chemists, drug discovery researchers, and machine learning scientists working on AI-driven molecular design and generative chemistry applications.

Value Proposition

Developers choose REINVENT because it provides a specialized reinforcement learning pipeline specifically tailored for drug discovery, with configurable templates and integration with chemical informatics tools. Its unique approach treats molecular generation as an optimization problem, enabling efficient exploration of chemical space for novel drug candidates.

Overview

REINVENT is a reinforcement learning framework specifically designed for de novo drug design, enabling the generation of novel molecular structures with optimized properties. It addresses the challenge of discovering new chemical entities by combining generative models with property prediction to explore chemical space efficiently.

Key Features

Reinforcement Learning Pipeline — Uses RL to optimize molecular structures toward desired chemical properties and biological activities
De Novo Molecular Generation — Creates entirely new molecular entities rather than modifying existing compounds
Property Optimization — Incorporates scoring functions to guide generation toward molecules with specific target properties
Template-Based Execution — Provides configurable JSON templates for different running modes and experiments
TensorBoard Integration — Enables real-time monitoring and visualization of training logs and progress

Philosophy

REINVENT applies reinforcement learning principles to drug discovery, treating molecular generation as an optimization problem where the agent learns to propose molecules that maximize desired chemical and biological properties.

REINVENT

What is REINVENT?

Overview

Key Features

Philosophy

Related Projects

Found a gem we're missing?

Use Cases

Best For

Not Ideal For

Pros & Cons

Pros

Cons

Frequently Asked Questions