OmegaFold

Description

OmegaFold is a cutting-edge AI model designed for high-resolution de novo protein structure prediction, directly from primary amino acid sequences. This release code provides access to the model described in the paper "High-resolution de novo structure prediction from primary sequence." The project aims for continuous optimization, focusing on reducing GRAM requirements for inferencing long proteins and releasing more powerful models.

Key advancements in OmegaFold include significant GRAM reduction, enabling the inference of protein sequences up to 4096 residues on an NVIDIA A100 GPU with 80 GB of memory when using specific `--subbatch_size` settings. The model's sensitivity to `--subbatch_size` is highlighted, offering a trade-off between computation time and memory usage. Users can adjust this parameter to manage GPU memory limitations, with a suggestion to halve the value if memory issues arise.

For macOS users, OmegaFold supports MPS (Apple Silicon) acceleration, provided the latest nightly version of PyTorch is installed. The current code requires macOS users to clone the repository and run the model using `python main.py`. The setup process involves installing the tool via pip or cloning the repository and running `python setup.py install`. The input format is a standard FASTA file, and the output includes one PDB file per sequence, with confidence values embedded in the b-factor column of the PDB files.

OmegaFold offers flexibility in balancing prediction quality and resource usage. Users can modify `--subbatch_size` to trade computation time for GRAM, or adjust `--num_cycle` to trade computation time for average prediction quality. Further details and options can be accessed via the `omegifold --help` command. The project encourages citation of the associated research paper for its utility.

The developers are committed to improving ease of use and expanding the model's capabilities. Future updates are expected to further enhance performance and accessibility for a wider range of users and computational environments. This open-source release facilitates research and development in structural biology and drug discovery.

OmegaFold Highlights

• High-resolution de novo protein structure prediction from primary sequence

• Significant GRAM reduction for inferencing long proteins

• Supports protein sequences up to 4096 residues on NVIDIA A100 (80GB)

• Adjustable `--subbatch_size` for memory-time trade-off

• MPS (Apple Silicon) acceleration support for macOS users

• Confidence values provided in PDB b-factor column

• Option to trade computation time for prediction quality via `--num_cycle`

• Command-line interface for running predictions

• Open-source release code available on GitHub

• Model 2 available via `--model 2` command-line argument

• Requires PyTorch and biopython for basic functionality

Getting Started with OmegaFold

1. 1

   Set up environment: Install OmegaFold via pip or clone repository and run setup.py

2. 2

   Prepare input: Create a FASTA file with protein sequences

3. 3

   Run prediction: Execute `omegifold INPUT_FILE.fasta OUTPUT_DIRECTORY` or `python main.py INPUT_FILE.fasta OUTPUT_DIRECTORY`

4. 4

   Configure parameters: Adjust `--subbatch_size` for memory optimization or `--num_cycle` for quality trade-off

5. 5

   Access results: Retrieve generated PDB files from the output directory

6. 6

   Utilize macOS acceleration: Install latest PyTorch nightly and use `python main.py`

7. 7

   Explore options: Run `omegifold --help` for detailed command-line arguments

OmegaFold's Use Cases

• Protein Structure Prediction
• Structural Biology Research
• Drug Discovery
• Bioinformatics Analysis
• Computational Chemistry
• Genomic Research

FAQ from OmegaFold

• What is OmegaFold used for?

  OmegaFold is used for high-resolution de novo protein structure prediction, generating 3D protein structures directly from primary amino acid sequences.

• How does OmegaFold reduce GRAM usage?

  OmegaFold has been optimized to reduce GRAM usage, allowing inference of longer protein sequences on GPUs with less memory, particularly through adjustable `--subbatch_size` settings.

• Can OmegaFold run on macOS?

  Yes, OmegaFold supports MPS (Apple Silicon) acceleration on macOS if the latest nightly version of PyTorch is installed. Users need to clone the repository and run via `python main.py`.

• What is the maximum protein sequence length OmegaFold can handle?

  With specific configurations (e.g., NVIDIA A100 80GB, `--subbatch_size` 448), OmegaFold can infer protein sequences as long as 4096 residues.

• How can I adjust the trade-off between speed and memory with OmegaFold?

  You can adjust the `--subbatch_size` parameter to trade computation time for GRAM usage. A lower `--subbatch_size` requires less memory but may take longer.

• What output does OmegaFold provide?

  OmegaFold produces one PDB file for each input sequence, saved in a specified output directory. Confidence values are included in the b-factor column of the PDB files.

• How do I install OmegaFold?

  You can install OmegaFold using pip: `pip install git+https://github.com/HeliXonProtein/OmegaFold.git`, or by cloning the repository and running `python setup.py install`.

• What are the dependencies for running OmegaFold?

  Basic functionality requires installing the latest PyTorch and biopython. For macOS, the latest nightly PyTorch is recommended for MPS acceleration.

• Can I influence the prediction quality?

  Yes, you can trade computation time for average prediction quality by changing the `--num_cycle` parameter.

• Where can I find more information on OmegaFold parameters?

  You can find more information on OmegaFold parameters by running `omegifold --help` in your terminal.

• How should I cite OmegaFold if I use it?

  You should cite the paper: Wu, Ruidong, et al. "High-resolution de novo structure prediction from primary sequence." bioRxiv (2022).

• What is Model 2 in OmegaFold?

  Model 2 is an updated version of the OmegaFold model that can be used by setting `--model 2` in the command line, offering potential improvements.