njchoma / DGAPN
This repository implements Distilled Graph Attention Policy Networks (DGAPNs), a curiosity-driven reinforcement learning model to generate novel graph-structured chemical representations.
☆21Updated 2 years ago
Related projects: ⓘ
- ☆37Updated this week
- Inverse Reinforcement Learning-based Structural Evolution of Small Molecules☆9Updated last year
- Comparing graph representations for molecular features prediction☆20Updated last year
- Materials for KDD2023 tutorial: Knowledge-augmented Graph Machine Learning for Drug Discovery: from Precision to Interpretability☆18Updated last year
- RL-GraphINVENT is a platform for graph-based targeted molecular generation using graph neural networks and reinforcement learning. RL-Gra…☆66Updated last year
- Source code for ICLR 2021 paper: "Molecule Optimization by Explainable Evolution"☆28Updated 3 years ago
- Bayesian MPNNs for Molecular Property Prediction☆27Updated 3 years ago
- Repository for Autobahn: Automorphism Based Graph Neural Networks☆30Updated 2 years ago
- Code to accompany the paper "Constrained Bayesian Optimisation for Automatic Chemical Design" https://pubs.rsc.org/en/content/articlehtml…☆49Updated last year
- Structure-based Drug Design; Reinforcement Learning and Genetic Algorithm☆66Updated last year
- ☆11Updated 4 years ago
- Research repository for the proposed equivariant graph attention network that operates on large biomolecules proposed by Le et al. (2022)☆17Updated last year
- AAAI 2020: Chemically Interpretable Graph Interaction Network for Prediction of Pharmacokinetic Properties of Drug-like Molecules☆35Updated 2 years ago
- Synthetic coordinates for GNNs, as proposed in "Directional Message Passing on Molecular Graphs via Synthetic Coordinates" (NeurIPS 2021)☆28Updated last year
- A PyTorch Implementation of "Optimization of Molecules via Deep Reinforcement Learning".☆73Updated last year
- Implementation of the paper - Automatic chemical design using a data-driven continuous representation of molecules☆43Updated 3 years ago
- A novel hybrid method for generating molecules with desired property scores.☆39Updated 2 years ago
- Fragment-based generative RL with Explorative Experience replay for Drug design (FREED)☆49Updated 2 years ago
- An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming (ICML'21)☆51Updated 3 years ago
- Recent application of graph neural network in drug discovery☆10Updated 4 years ago
- Implementation of GEFA: Early Fusion Approach in Drug-Target Affinity Prediction☆20Updated 3 years ago
- coming soon☆28Updated last year
- ☆55Updated 3 years ago
- ☆14Updated last year
- MIMOSA: Multi-constraint Molecule Sampling for Molecule Optimization (AAAI 21')☆25Updated last year
- Code and analyses related to the ExaLearn drug design efforts☆12Updated 3 years ago
- Generative model for molecular distance geometry☆39Updated last year
- Code for "Molecular Hypergraph Grammar with Its Application to Molecular Optimization"☆38Updated 4 years ago
- The implementation of Modof for Molecule Optimization☆27Updated last year
- ☆24Updated 3 years ago