# google-deepmind/alphafold3

AlphaFold 3 inference pipeline.

Repository: https://github.com/google-deepmind/alphafold3
Canonical: https://ross.abutalabs.com/products/alphafold3
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-19T15:43:52+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 83, longevity 47
- inputs: {"age_days": 660, "days_push": 14, "days_rel": 36, "gap_med": 60.5, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8495, forks 1343 (observed 2026-08-28T04:10:23.139142+00:00)

## What it is
Google DeepMind's official implementation of the AlphaFold 3 inference pipeline for predicting biomolecular structures and interactions. It runs protein, nucleic acid, and ligand complex structure predictions using model parameters obtained directly from Google.

## Use cases
- predict 3D structure of a protein complex from amino acid sequence
- model protein-ligand interactions computationally
- run alphafold 3 inference on my own gpu
- predict dna rna protein complex structures
- fold a protein sequence into a pdb structure
- model biomolecular interactions with deep learning

## When to choose
- you need local, reproducible AlphaFold 3 predictions with full control over inputs and outputs
- you want to run the complete data pipeline (MSA and template search) plus inference on your own hardware
- you need to predict complexes involving proteins, nucleic acids, and ligands beyond alphafoldserver.com limits

## When to avoid
- you only need occasional non-commercial predictions without GPU infrastructure - use alphafoldserver.com instead
- you cannot obtain model parameters directly from Google under the terms of use
- you lack GPUs or cannot run the CPU-heavy genetic search pipeline

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-inference
- domain: bioinformatics, deep-learning, machine-learning
- platform: python
- tags: protein-structure-prediction, alphafold, structural-biology, molecular-modeling, inference-pipeline, docker, gpu, linux

## Member repositories
- google-deepmind/alphafold3 (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:23.139142+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 2026-08-29T17:26:43.651930+00:00, confidence not recorded.
  - readme: https://github.com/google-deepmind/alphafold3 (fetched 2026-08-28T04:10:23.139142+00:00, sha cd94396ae71a)
- Data as of 2026-08-30T08:39:29.467469+00:00.