Stars
React-OT is a generative transition state search model developed by DeepPrinciple, which uses Optimal Transport (OT) methods to generate deterministic transition state structures from reactants and…
MatterSim: A deep learning atomistic model across elements, temperatures and pressures.
A library that scrapes Linkedin for user data
MoFlow: an invertible flow model for generating molecular graphs
A simple tool to predict the general toxicity and calculate the synthesize accessibility (SA) score for small molecules.
Implementations of different GNNs from scratch for chemists
QSARtuna: QSAR model building with the optuna framework
GPT (Generative Pre-trained Transformer) for de novo molecular design by enforcing specified targets
Implementation of a graph transformer one-shot decoder for molecular generation. Investigates graph matching precision on training behavior and generation capabilities.
The official codes and implementations of HiPM model in paper:"Adapting Differential Molecular Representation with Hierarchical Prompts for Multi-label Property Prediction"
[ICML 2023] Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction
Diffusing on Two Levels and Optimizing for Multiple Properties: A Novel Approach to Generating Molecules with Desirable Properties
a Large-Scale Multi-Modal Dataset Containing 20 Million Descriptions
The code for "Graph Diffusion Transformer for Multi-Conditional Molecular Generation"
CrySPY is a crystal structure prediction tool written in Python.
The official codebase of the paper "Chemical language modeling with structured state space sequence models"
Using a joint AE and property prediction model to estimate OOD molecules and quantify uncertainty
A PyTorch Implementation of "Optimization of Molecules via Deep Reinforcement Learning".
Guided Diffusion Model for Molecular Inverse Design