Official implementation of pre-training via denoising for TorchMD-NET

🥇Samsung AI Challenge 2021 1등 솔루션입니다🥇

[KDD'22] Source codes of "Graph Rationalization with Environment-based Augmentations"

An atom-bond transformer-based message passing neural network for molecular property prediction.

Predict optical properties of molecules with machine learning.

The official open-source repository for AutoMolDesigner, an easy-to-use Python application dedicated to automated molecular design.

[ICML 2023] Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction

Exploring QSAR Models for Activity-Cliff Prediction

Machine learning desktop application for molecular property prediction and analysis

Code and Data for the paper: Graph Sampling-based Meta-Learning for Molecular Property Prediction [IJCAI2023]

C++ toolkit for post-processing molecular dynamics trajectories, with a focus on high-performance static and dynamic analyses of amorphous/glassy/polymer materials.

An efficient curriculum learning-based strategy for molecular graph learning

UQ4DD: Uncertainty Quantification for Drug Discovery

Subgraph-conditioned Graph Information Bottleneck (S-CGIB) is a novel architecture for pre-training Graph Neural Networks in molecular property prediction and developed by NS Lab, CUK based on pure PyTorch backend.

A GNN model for the prediction of pure component vapor pressures.

Rotationally Equivariant Hypergraph Neural Networks (EquiHGNN)

IUPAC-based large-scale molecular pre-trained model for property prediction and molecular generation

Sort & Slice: A Simple and Superior Alternative to Hash-Based Folding for Extended-Connectivity Fingerprints (ECFPs)

KDD-23 Automated 3D Pre-Training for Molecular Property Prediction

The code base for AWARE, a graph representation learning method published at TMLR

Machine learning for molecular property prediction

3rd place solution for 2022 Samsung AI Challenge (Materials Discovery)

MUBen: Benchmarking the Uncertainty of Molecular Representation Models

The official repository of our paper "Stretch to Generalize in Molecular Representation Learning with SFL"

Package for TwinBooster. Enables fast and powerful zero-shot molecular property prediction.

PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction. IJCAI 2024

From SMILES to Enhanced Molecular Property Prediction: A Unified Multimodal Framework with Predicted 3D Conformers and Contrastive Learning Techniques

Multi-View Conditional Information Bottleneck (MVCIB) is a novel architecture for pre-training Graph Neural Networks on 2D and 3D molecular structures and developed by NS Lab, CUK based on pure PyTorch backend.

About [NeurIPS 2025 D&B] Official implementation and benchmark evaluation repository of <MolVision: Molecular Property Prediction with Vision Language Models>

This repository is a brief tutorial about how Graph convolutional networks and message passing networks work with example code demonstration using pytorch and torch_geometric