olsson-group / RL-GraphINVENT
RL-GraphINVENT is a platform for graph-based targeted molecular generation using graph neural networks and reinforcement learning. RL-GraphINVENT uses a Gated Graph Neural Network -based model fine-tuned using reinforcement learning to probabilistically generate new molecules with desired property profiles.
☆69Updated last year
Related projects ⓘ
Alternatives and complementary repositories for RL-GraphINVENT
- Fragment-based generative RL with Explorative Experience replay for Drug design (FREED)☆51Updated 2 years ago
- MCMG_V1☆69Updated last year
- A PyTorch Implementation of "Optimization of Molecules via Deep Reinforcement Learning".☆74Updated last year
- ☆52Updated last year
- ☆57Updated 3 years ago
- ☆63Updated 3 years ago
- The implementation of Modof for Molecule Optimization☆27Updated last year
- Code accompanying the paper "Deep reinforcement learning for multiparameter optimization in de novo drug design"☆67Updated 3 years ago
- ☆68Updated 2 years ago
- A novel hybrid method for generating molecules with desired property scores.☆41Updated 3 years ago
- Implementation of the method proposed in the paper "Efficient Multi-Objective Molecular Optimization in a Continuous Latent Space" by Rob…☆76Updated 3 years ago
- Pytorch implementation of the paper "Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules"☆63Updated 3 years ago
- generative model for drug discovery☆58Updated last year
- Graph neural network (GNN) for molecular property prediction (3D structure)☆93Updated 3 years ago
- Code for the paper "A Deep Generative Model for Fragment-Based Molecule Generation" (AISTATS 2020)☆66Updated 2 years ago
- ☆117Updated 2 years ago
- Implementation of Retrosynthesis Prediction with Conditional Graph Logic Network☆118Updated last year
- Multi-Objective Molecule Generation using Interpretable Substructures (ICML 2020)☆140Updated 2 years ago
- Supporting code for the paper «Generative molecular design in low data regimes»☆64Updated 3 years ago
- Supporting code for the paper "Bidirectional Molecule Generation with Recurrent Neural Networks" (J. Chem. Inf. 2020, 60, 3).☆53Updated 4 years ago
- This repository contains code for the paper: Beyond Generative Models: Superfast Traversal, Optimization, Novelty, Exploration and Discov…☆121Updated 3 months ago
- Baselines models for GuacaMol benchmarks☆135Updated 9 months ago
- Structure-based Drug Design; Reinforcement Learning and Genetic Algorithm☆69Updated last year
- Code for paper "TrimNet: learning molecular representation from triplet messages for biomedicine "☆51Updated last year
- Official implementation of "Generating 3D Molecules for Target Protein Binding" [ICML2022 Long Presentation]☆103Updated last year
- An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming (ICML'21)☆51Updated 3 years ago
- An E(3) Equivariant Variational Autoencoder for Molecular Linker Design☆45Updated 2 years ago
- Recurrent Neural Network using randomized SMILES strings to generate molecules☆87Updated 4 years ago
- ☆37Updated 4 years ago
- Predicting Organic Reactivity with LocalTransform☆37Updated 4 months ago