molecular-property-prediction 开源项目推荐（122 个）

shehzaidi /pre-training-via-denoising

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

affjljoo3581 /Samsung-AI-Challenge-for-Scientific-Discovery

🥇三星AI挑战赛2021第一🥇解决方案

liugangcode /GREA

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

learningmatter-mit /uvvisml

Predict optical properties of molecules with machine learning.

LCY02 /ABT-MPNN

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

taoshen99 /AutoMolDesigner

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

dssimmons-codes /AMDAT

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

gmh14 /Geo-DEG

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

MarkusFerdinandDablander /QSAR-activity-cliff-experiments

Exploring QSAR Models for Activity-Cliff Prediction

aravindhnivas /ChemXploreML

Machine learning desktop application for molecular property prediction and analysis

gu-yaowen /CurrMG

An efficient curriculum learning-based strategy for molecular graph learning

HICAI-ZJU /GS-Meta

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

marco-hoffmann /HANNA

A machine-learning excess Gibbs energy model that enables the prediction of phase equilibria (VLE and LLE) in multi-component mixtures.

MolecularAI /uq4dd

UQ4DD: Uncertainty Quantification for Drug Discovery

golab-ai /Suiren-Foundation-Model

A molecular foundation model for quantum property prediction.

BattModels /mist

Training and applying MIST (Molecular Insight SMILES Transformer) foundation models to chemical problems.

blazejba /Monroe

Monroe: A Molecular Foundation Model for In-Context Probabilistic Inference

marco-hoffmann /GRAPPA

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

NSLab-CUK /S-CGIB

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.

HySonLab /EquiHGNN

Rotationally Equivariant Hypergraph Neural Networks (EquiHGNN)