Add EvoDiff to Protein Structure Prediction and Design#50
Conversation
Made-with: Cursor
Summary of ChangesHello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request integrates EvoDiff, a novel discrete diffusion framework for protein sequence generation, into the existing collection of resources. This addition expands the scope of available tools, particularly for sequence-based protein design, complementing current structure-based approaches and enabling the generation of proteins with disordered regions. Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Changelog
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request adds the EvoDiff resource to README.md. However, it is incomplete because the derived data files (data/resources.yml, data/resources.json, data/resources.csv, docs/data/resources.json) have not been updated. These files are generated from README.md via the scripts/sync_resources_from_readme.py script and are used to populate the project's website. Without updating them, the new resource will not be visible on the website, and the repository's data will be inconsistent. Please run the sync script and commit the updated files to complete this pull request.
| - [RoseTTAFold](https://github.com/RosettaCommons/RoseTTAFold) — Three-track neural network for protein structure prediction. | ||
| - [OpenFold](https://github.com/aqlaboratory/openfold) — Trainable, memory-efficient open-source reproduction of AlphaFold2 enabling custom protein structure prediction workflows. | ||
| - [SaProt](https://github.com/westlake-reup/SaProt) — Structure-aware protein language model using structure-aware tokens that encode both sequence and backbone geometry for improved function prediction. | ||
| - [EvoDiff](https://github.com/microsoft/evodiff) — Discrete diffusion framework for protein sequence generation trained on evolutionary-scale data, supporting unconditional generation, disordered region design, and functional motif scaffolding. [ [paper-2023](https://www.biorxiv.org/content/10.1101/2023.09.11.556673v1) ] |
There was a problem hiding this comment.
This addition is incomplete because the data files generated from this README (e.g., data/resources.yml, data/resources.json) have not been updated. Please run the scripts/sync_resources_from_readme.py script and commit the generated file changes. This is necessary to keep the project's data consistent and to ensure the new resource appears on the website.
Made-with: Cursor
|
Hi @Abdeltoto Looks good to me! Thank you for your contribution. |
2 participants
EvoDiff (Microsoft Research, 663+ stars) is a discrete diffusion framework for protein sequence generation trained on 42M+ protein sequences. Unlike structure-based approaches, it operates in sequence space, enabling generation of proteins with disordered regions while supporting functional motif scaffolding. Published as a bioRxiv preprint (2023).
Made with Cursor