# deepmodeling/Uni-Mol

Official Repository for the Uni-Mol Series Methods

Repository: https://github.com/deepmodeling/Uni-Mol
Canonical: https://ross.abutalabs.com/products/uni-mol
Language: Python
License: MIT
License Family: permissive
Topics: molecular-modeling, pre-trained-model, pretraining, deep-learning
Last push: 2025-05-29T07:41:36+00:00

## Health v2 (maintenance only)
Score: 34/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 24, release rhythm 8, longevity 100
- inputs: {"age_days": 1564, "days_push": 461, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1155, forks 181 (observed 2026-08-28T04:03:47.936453+00:00)

## What it is
Uni-Mol is a collection of 3D molecular representation learning frameworks and pretrained models for tasks like molecule property prediction, quantum chemical modeling, and protein-ligand docking. It includes easy-to-use Python wrappers (unimol-tools) and scalable pretrained models up to 1.1 billion parameters.

## Use cases
- predict molecular properties from SMILES
- predict protein-ligand binding poses
- generate and optimize molecular conformations
- predict quantum chemical properties of molecules
- fine-tune a pretrained molecular model on my dataset
- embed molecules as 3D representations for ML

## When to choose
- you need state-of-the-art 3D molecular property prediction or docking
- you want pretrained molecular models with fine-tuning support
- you work in drug discovery or computational chemistry with Python

## When to avoid
- you need general-purpose NLP or vision models
- you lack GPU resources for large pretrained models
- you need a GUI-only workflow without Python

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-training
- domain: deep-learning, machine-learning, bioinformatics, chemistry
- platform: python
- tags: molecular-modeling, pretrained-model, molecular-representation-learning, drug-discovery, property-prediction, protein-ligand-docking, transformers, linux, docker

## Member repositories
- deepmodeling/Uni-Mol (main) score 34

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:47.936453+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:32:12.463327+00:00, confidence not recorded.
  - readme: https://github.com/deepmodeling/Uni-Mol (fetched 2026-08-28T04:03:47.936453+00:00, sha d9ade9a9b6bc)
- Data as of 2026-08-30T08:39:29.467469+00:00.