> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/google-deepmind/alphafold3/llms.txt
> Use this file to discover all available pages before exploring further.

# Frequently Asked Questions

> Common questions about AlphaFold 3

## General Questions

<Accordion title="What is AlphaFold 3?">
  AlphaFold 3 is a deep learning system for predicting the 3D structures of biomolecular complexes, including proteins, nucleic acids, ligands, and post-translational modifications. It represents a significant advancement over AlphaFold 2, extending structure prediction beyond proteins to diverse biomolecular interactions.

  The model was published in Nature: [Accurate structure prediction of biomolecular interactions with AlphaFold 3](https://doi.org/10.1038/s41586-024-07487-w).
</Accordion>

<Accordion title="How is AlphaFold 3 different from AlphaFold 2?">
  Key differences include:

  * **Broader scope**: AlphaFold 3 can model proteins, RNA, DNA, ligands, ions, and post-translational modifications
  * **Complex interactions**: Predicts interactions between different biomolecule types
  * **Improved accuracy**: Enhanced performance on protein-ligand and protein-nucleic acid interactions
  * **Covalent modifications**: Supports modeling of covalent bonds and modifications
  * **New architecture**: Uses an updated neural network architecture optimized for diverse biomolecules
</Accordion>

<Accordion title="Can I use AlphaFold 3 for commercial purposes?">
  No, AlphaFold 3 is licensed for **non-commercial use only** under the CC-BY-NC-SA 4.0 license.

  <Warning>
    The AlphaFold 3 source code and model parameters are subject to non-commercial licensing terms. Review the [terms of use](https://github.com/google-deepmind/alphafold3/blob/main/WEIGHTS_TERMS_OF_USE.md) before use.
  </Warning>

  For commercial applications, please contact the AlphaFold team at [alphafold@google.com](mailto:alphafold@google.com).
</Accordion>

<Accordion title="Is there a web server for AlphaFold 3?">
  Yes, AlphaFold 3 is available at [alphafoldserver.com](https://alphafoldserver.com) for non-commercial use.

  However, the server has limitations:

  * More limited set of ligands
  * Fewer covalent modifications supported
  * No ability to customize model parameters

  The local installation provides full functionality and flexibility.
</Accordion>

***

## Model Access and Installation

<Accordion title="How do I get access to the AlphaFold 3 model parameters?">
  To request access to the model parameters:

  1. Complete the [access request form](https://forms.gle/svvpY4u2jsHEwWYS6)
  2. Wait for approval from Google DeepMind (typically 2-3 business days)
  3. You will receive a download link via email

  <Info>
    You may only use AlphaFold 3 model parameters if received directly from Google. Access is granted at Google DeepMind's sole discretion.
  </Info>
</Accordion>

<Accordion title="What hardware do I need to run AlphaFold 3?">
  **Minimum requirements:**

  * **GPU**: NVIDIA GPU with at least 16GB VRAM (e.g., V100, A100, RTX 4090)
  * **RAM**: 32GB+ system RAM
  * **Disk**: Several TB for databases (500GB+ for minimal setup)
  * **CPU**: Multi-core processor for data pipeline

  **Recommended:**

  * **GPU**: A100 80GB or H100 for large complexes
  * **RAM**: 64GB+ system RAM
  * **Disk**: 3-5TB SSD for full databases

  <Note>
    The data pipeline (genetic searches) can run on CPU-only machines without a GPU.
  </Note>
</Accordion>

<Accordion title="Can I run AlphaFold 3 without Docker?">
  While Docker is the officially supported method, technically you can run AlphaFold 3 without Docker by:

  1. Manually installing all dependencies
  2. Setting up the Python environment
  3. Configuring paths for databases and models

  However, this is **not recommended** because:

  * Complex dependency management
  * Potential version conflicts
  * Lack of official support

  Docker ensures a consistent, reproducible environment.
</Accordion>

<Accordion title="How long does installation take?">
  Installation time varies:

  * **Docker build**: 30-60 minutes (depending on network speed)
  * **Database download**: Several hours to days (depending on which databases and network speed)
  * **Model parameters**: 15-30 minutes (depending on network speed)

  Total setup time: Typically **1-3 days** for a complete installation.
</Accordion>

***

## Running Predictions

<Accordion title="How long does a prediction take?">
  Prediction time depends on several factors:

  **Data pipeline** (genetic searches):

  * Simple proteins: 1-4 hours
  * Complex proteins: 4-24 hours
  * Very large complexes: 24-48+ hours

  **Inference** (GPU):

  * Small proteins (\<200 residues): 5-15 minutes
  * Medium proteins (200-500 residues): 15-45 minutes
  * Large complexes (>500 residues): 45 minutes - 2 hours

  <Info>
    You can run data pipeline and inference separately using `--run_data_pipeline` and `--run_inference` flags.
  </Info>
</Accordion>

<Accordion title="Can I run multiple predictions in parallel?">
  Yes, with caveats:

  * **Data pipeline**: Can run multiple in parallel if you have enough CPU and RAM
  * **Inference**: Limited by GPU memory - typically 1-2 predictions per GPU depending on complex size

  For maximum efficiency:

  1. Run data pipeline on CPU-only machines in parallel
  2. Run inference sequentially or on multiple GPUs
</Accordion>

<Accordion title="What is a model seed and how many should I use?">
  A model seed controls the random initialization of the neural network. Using multiple seeds generates diverse predictions.

  **Recommendations:**

  * **Standard use**: 5 seeds (`"modelSeeds": [1, 2, 3, 4, 5]`)
  * **Quick testing**: 1 seed
  * **High confidence needed**: 10+ seeds

  The model ranks all predictions, with the best one typically selected.
</Accordion>

<Accordion title="Can I stop and resume a prediction?">
  **Data pipeline**: Cannot be easily resumed - must restart if interrupted

  **Inference**: Cannot be resumed - must rerun if interrupted

  <Warning>
    Save your data pipeline outputs to avoid rerunning expensive genetic searches.
  </Warning>

  Best practices:

  * Run data pipeline separately with `--run_data_pipeline=true --run_inference=false`
  * Save MSA and template outputs
  * Run inference later with pre-computed data
</Accordion>

***

## Input and Output

<Accordion title="What types of molecules can AlphaFold 3 model?">
  AlphaFold 3 supports:

  * **Proteins**: Any amino acid sequence
  * **RNA**: Nucleotide sequences
  * **DNA**: Nucleotide sequences
  * **Ligands**: Small molecules (via SMILES or CCD codes)
  * **Ions**: Common ions (via CCD codes)
  * **Post-translational modifications**: Glycans, phosphorylation, etc.
  * **Covalent bonds**: Disulfide bridges, peptide bonds to ligands, etc.

  See the [Input Format](/guides/input-format) documentation for details.
</Accordion>

<Accordion title="How do I interpret the confidence scores?">
  AlphaFold 3 provides several confidence metrics:

  **pLDDT** (per-residue confidence):

  * > 90: Very high confidence
  * 70-90: Generally reliable
  * 50-70: Low confidence
  * \<50: Should not be interpreted

  **Ranking score**:

  * Higher scores indicate better overall model quality
  * Compares different model seeds
  * Score of -99 or lower indicates severe problems

  <Info>
    Always inspect structures visually and validate predictions experimentally when possible.
  </Info>
</Accordion>

<Accordion title="What output files does AlphaFold 3 produce?">
  For each prediction:

  * **CIF files**: 3D structure coordinates (mmCIF format)
  * **JSON files**: Confidence scores and metadata
  * **Ranking file**: Comparison of different model seeds
  * **Data pipeline outputs**: MSAs, templates (if run)

  See the [Output Format](/guides/output-format) documentation for details.
</Accordion>

<Accordion title="Can I use AlphaFold 3 for protein design?">
  AlphaFold 3 is primarily a **structure prediction** tool, not a design tool. However:

  **Possible uses:**

  * Validate designed sequences by predicting their structures
  * Screen multiple design candidates
  * Predict effects of mutations

  **Not designed for:**

  * Inverse folding (sequence design from structure)
  * Optimizing sequences for specific functions

  Consider tools specifically designed for protein design (e.g., ProteinMPNN, RFdiffusion).
</Accordion>

***

## Ligands and Small Molecules

<Accordion title="How do I add a ligand to my prediction?">
  Ligands can be specified in two ways:

  **1. Using SMILES:**

  ```json theme={null}
  {
    "ligand": {
      "id": ["L"],
      "smiles": "CC(C)CC1=CC=C(C=C1)C(C)C(=O)O"
    }
  }
  ```

  **2. Using CCD codes:**

  ```json theme={null}
  {
    "ligand": {
      "id": ["L"],
      "ccdCodes": ["ATP"]
    }
  }
  ```

  See the [Input Format](/guides/input-format) documentation for complete examples.
</Accordion>

<Accordion title="What if my ligand isn't in the CCD?">
  For non-standard ligands:

  1. **Use SMILES notation**: Define the molecule with a SMILES string
  2. **Include stereochemistry**: Ensure stereochemistry is explicit in SMILES
  3. **Specify covalent bonds**: Use `bondedAtomPairs` if needed

  <Info>
    See the [Community Tools](/resources/community-tools) page for tools like JAAG that help generate ligand inputs.
  </Info>
</Accordion>

<Accordion title="How do I model glycans?">
  Glycan modeling requires:

  1. **Correct CCD codes**: Use SNFG nomenclature
  2. **Bonded atom pairs**: Specify glycosidic bonds
  3. **Proper JSON structure**: Follow the glycan format

  <Info>
    See the paper [Modeling glycans with AlphaFold 3](https://doi.org/10.1093/glycob/cwaf048) for:

    * Step-by-step tutorials
    * Ready-to-run scripts
    * Comprehensive CCD tables
    * Discussion of limitations
  </Info>

  Tools like [JAAG](https://biofgreat.org/JAAG) automate glycan input generation.
</Accordion>

***

## Troubleshooting

<Accordion title="Why is my prediction quality poor?">
  Common causes:

  1. **Input errors**: Check sequences and ligand definitions
  2. **Hardware issues**: See [Known Issues](/resources/known-issues) for GPU-specific problems
  3. **Inherent uncertainty**: Some targets are genuinely difficult to predict
  4. **Insufficient data**: Limited homologs in genetic databases
  5. **Complex interactions**: Novel or unusual binding modes

  See the [Troubleshooting](/resources/troubleshooting) page for detailed solutions.
</Accordion>

<Accordion title="Where can I get help?">
  Support resources:

  1. **Documentation**: Check the [official documentation](/introduction)
  2. **Known Issues**: Review the [Known Issues](/resources/known-issues) page
  3. **GitHub**: Search the [issues tracker](https://github.com/google-deepmind/alphafold3/issues)
  4. **Community**: See [Community Tools](/resources/community-tools) for community resources
  5. **Email**: Contact [alphafold@google.com](mailto:alphafold@google.com)

  When reporting issues, include:

  * Hardware configuration
  * Error messages
  * Input JSON
  * Steps to reproduce
</Accordion>

***

## Citation and Publication

<Accordion title="How do I cite AlphaFold 3?">
  See the [Citation](/resources/citation) page for the complete citation information.

  <Note>
    Any publication using AlphaFold 3 source code, model parameters, or outputs **must** cite the AlphaFold 3 paper.
  </Note>
</Accordion>

<Accordion title="Can I share AlphaFold 3 predictions publicly?">
  Yes, you can share predictions, but:

  * Must cite the AlphaFold 3 paper
  * Must acknowledge the non-commercial license
  * Cannot use for commercial purposes
  * Must include appropriate disclaimers about prediction confidence

  <Warning>
    Predictions are for theoretical modeling only and not validated for clinical use.
  </Warning>
</Accordion>