#3131st of 42 in Open modelsFor image, video and design, science, health and research
alphafold
Protein structure prediction inference pipeline from AlphaFold v2, including Multimer
- Stars
- 14.9k
- License
- Apache-2.0
- Last commit
- Apr 2026
- Last release
- Apr 2023
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Runs the AlphaFold v2 inference pipeline: takes FASTA sequences, searches genetic databases for MSAs and templates, and predicts 3D structures with monomer, pTM and Multimer model presets. It is driven by a Docker wrapper (run_docker.py) and requires a Linux machine with an NVIDIA GPU. Code is Apache-2.0; the model parameters are CC BY 4.0.
Who it is for: Structural biologists running protein structure prediction on own GPUs
Strengths
- Presets for monomer, CASP14 ensemble, pTM and AlphaFold-Multimer complexes
- Reduced_dbs preset runs with 8 CPU cores, 8 GB RAM and 600 GB disk
- Download scripts fetch databases and parameters; MSAs can be reused via --use_precomputed_msas
- README publishes A100 runtimes by residue count, from 4.9 s at 100 to 18,824 s at 5,000
Weaknesses
- Full databases need about 556 GB download and 2.62 TB unpacked
- Linux only; requires a modern NVIDIA GPU and the NVIDIA Container Toolkit
- Last release was 2023-04-05; Multimer described as work in progress
- Model parameters are CC BY 4.0, separate from the Apache-2.0 code
What it needs
- RAM ≥ 8 GB
- GPU required
- Needs Docker, NVIDIA Container Toolkit, aria2c, rsync, BFD, MGnify, PDB70, PDB mmCIF, UniRef30, UniRef90, UniProt
- Models: AlphaFold v2 monomer, monomer_casp14, monomer_ptm, AlphaFold-Multimer
Also in Open models
See all 42| Rank | Project | Score |
|---|---|---|
| 1 | llmfitRust tool that checks which LLMs fit your RAM, CPU and GPU | 87 out of 100 |
| 2 | layaSingle-pass multilingual classifier for typed choice, score and yes/no decisions | 86 out of 100 |
| 3 | timesfmPretrained time-series foundation model for zero-shot forecasting from Google Research | 76 out of 100 |
| #4 | speechPyTorch toolkit for training and deploying ASR, TTS and speech LLM models | 73 out of 100 |
| #5 | yueLyrics-to-song model that writes an editable melody and chord score first | 69 out of 100 |