AIRI-Institute/nablaDFT

nablaDFT: Large-Scale Conformational Energy and Hamiltonian Prediction benchmark and dataset

48
/ 100
Emerging

This project provides a comprehensive collection of data and tools for computational chemists working with drug-like molecules. It includes a vast dataset of molecular structures, their energies, forces, and other quantum chemical properties, along with relaxation trajectories. Researchers can use this to train and evaluate neural network potentials for predicting molecular behavior, enabling faster and more scalable drug discovery and chemical science research.

227 stars.

Use this if you are a computational chemist or drug discovery scientist looking for a large, high-quality dataset to develop and benchmark machine learning models for predicting molecular properties or optimizing molecular conformations.

Not ideal if you are looking for an out-of-the-box software for direct molecular simulation without needing to train or evaluate neural network potentials.

computational chemistry drug discovery molecular simulation quantum chemistry materials science
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

227

Forks

26

Language

Python

License

MIT

Last pushed

Dec 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AIRI-Institute/nablaDFT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.