Saved in:
Bibliographic Details
Main Authors: Guo, Xiao-Yu, Li, Yi-Fan, Liu, Yuan, Pan, Xiaoyong, Shen, Hong-Bin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.04069
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917858291744768
author Guo, Xiao-Yu
Li, Yi-Fan
Liu, Yuan
Pan, Xiaoyong
Shen, Hong-Bin
author_facet Guo, Xiao-Yu
Li, Yi-Fan
Liu, Yuan
Pan, Xiaoyong
Shen, Hong-Bin
contents Protein design has become a critical method in advancing significant potential for various applications such as drug development and enzyme engineering. However, protein design methods utilizing large language models with solely pretraining and fine-tuning struggle to capture relationships in multi-modal protein data. To address this, we propose ProtDAT, a de novo fine-grained framework capable of designing proteins from any descriptive protein text input. ProtDAT builds upon the inherent characteristics of protein data to unify sequences and text as a cohesive whole rather than separate entities. It leverages an innovative multi-modal cross-attention, integrating protein sequences and textual information for a foundational level and seamless integration. Experimental results demonstrate that ProtDAT achieves the state-of-the-art performance in protein sequence generation, excelling in rationality, functionality, structural similarity, and validity. On 20,000 text-sequence pairs from Swiss-Prot, it improves pLDDT by 6%, TM-score by 0.26, and reduces RMSD by 1.2 Å, highlighting its potential to advance protein design.
format Preprint
id arxiv_https___arxiv_org_abs_2412_04069
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ProtDAT: A Unified Framework for Protein Sequence Design from Any Protein Text Description
Guo, Xiao-Yu
Li, Yi-Fan
Liu, Yuan
Pan, Xiaoyong
Shen, Hong-Bin
Artificial Intelligence
Protein design has become a critical method in advancing significant potential for various applications such as drug development and enzyme engineering. However, protein design methods utilizing large language models with solely pretraining and fine-tuning struggle to capture relationships in multi-modal protein data. To address this, we propose ProtDAT, a de novo fine-grained framework capable of designing proteins from any descriptive protein text input. ProtDAT builds upon the inherent characteristics of protein data to unify sequences and text as a cohesive whole rather than separate entities. It leverages an innovative multi-modal cross-attention, integrating protein sequences and textual information for a foundational level and seamless integration. Experimental results demonstrate that ProtDAT achieves the state-of-the-art performance in protein sequence generation, excelling in rationality, functionality, structural similarity, and validity. On 20,000 text-sequence pairs from Swiss-Prot, it improves pLDDT by 6%, TM-score by 0.26, and reduces RMSD by 1.2 Å, highlighting its potential to advance protein design.
title ProtDAT: A Unified Framework for Protein Sequence Design from Any Protein Text Description
topic Artificial Intelligence
url https://arxiv.org/abs/2412.04069