torch-molecule is a deep learning package for molecular discovery, designed with an sklearn-style interface for property prediction, inverse design and representation learning.

Chemical representation learning paper in Digital Discovery

PaddleMaterials is a data-mechanism dual-driven, foundation model development and deployment, end to end toolkit based on PaddlePaddle deep learning framework for materials science and engineering.

CrysXPP: An Explainable Property Predictor for Crystalline Materials (NPJ Computational Materials - 2022)

Open Knowledge Enrichment for Long-tail Entities, WWW 2020

Predicting properties of small molecules using MPNN on QM9 dataset

An integrated Python package for molecular descriptor generation, data processing, model training, and hyper-parameter optimization.

EGAT - Edge Featured Graph Attention Networks for Property Prediction

Machine learning algorithm implementation in materials science

Pittsburgh Single Family Home Prediction with Non-Conventional Data Streams

Smart, user-friendly property valuation app leveraging bulk price prediction, market summaries, feature insights, and top picks ,powered by Streamlit and machine learning.

ML for predicting the compressive strength of SCMs

🧭 Australian Property Orientation Finder

P2MAT - A python based user interface to predict melting point and boiling point of chemical compounds.

A Python toolkit for evaluating Large Language Models (LLMs) in materials science workflows

A TensorFlow-based machine learning framework for predicting zeolite properties—particularly framework density—using neural networks and composite building unit fingerprints