| --- |
| language: |
| - en |
| tags: |
| - biology |
| - protein |
| --- |
| |
| ## Model Card for Pinal: Toward De Novo Protein Design from Natural Language |
|
|
| <a href="https://www.biorxiv.org/content/10.1101/2024.08.01.606258"><img src="https://img.shields.io/badge/Paper-bioRxiv-green" style="max-width: 100%;"></a> <a href="http://www.denovo-pinal.com/"><img src="https://img.shields.io/badge/Pinal-red?label=Server" style="max-width: 100%;"></a> <a href="https://github.com/westlake-repl/Denovo-Pinal"><img src="https://img.shields.io/badge/Github-Code-blue?logo=github" style="max-width: 100%;"></a> |
|
|
| Pinal is an advanced protein design framework that translates human design intent into novel protein sequences. It utilizes a two-stage process: first generating protein structures from language instructions, then designing sequences based on those structures. With a substantial parameter count of 16 billion and trained on a diverse dataset comprising 1.7 billion protein-text pairs, Pinal demonstrates marked improvements in both performance and generalization capabilities for novel protein structures. |
|
|
|  |
|
|
| For more information, please refer to our [preprint](https://www.biorxiv.org/content/10.1101/2024.08.01.606258). |
|
|
| ### SaProt-T(ext) and SaProt-O(mni) |
|
|
| SaProt-T was specifically developed for **protein reverse folding** within the Pinal framework, whereas SaProt-O is trained with configurable inputs (optional textual prompts and structural features) to accommodate real-world research scenarios. |
|
|
| ## Usage |
|
|
| Please refer to the README.md in the [Github repository](https://github.com/westlake-repl/Denovo-Pinal) for details on how to use the model. |
