ProtDAT: A Unified Multimodal Cross-Attention Framework for Ab-Initio Amino Acid Sequence Design from Any Protein Text Description

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. Evaluation metrics such as pLDDT, TM-score and RMSD are implemented to evaluate the rationality, functionality, structural similarity, and validity of protein sequences. Experiments on 20,000 text-sequence pairs from Swiss-Prot within the ProtDAT framework demonstrate significant improvements compared to the performance of the best method in the experiments, with a 9.84% increase in pLDDT, a 76.45% increase in TM-score, and a 24.41% reduction in RMSD.