M2oE: Multimodal Collaborative Expert Peptide Model

TL;DR

The paper introduces M2oE, a multi-modal model that combines peptide sequence and structural data using expert models and cross-attention, significantly enhancing prediction accuracy in complex peptide tasks.

Contribution

It presents a novel multi-modal collaborative expert model that effectively integrates sequence and structural information for improved peptide prediction.

Findings

M2oE outperforms single-modal models in complex tasks.

Multi-modal integration improves prediction accuracy.

Experimental results validate the effectiveness of the proposed approach.

Abstract

Peptides are biomolecules comprised of amino acids that play an important role in our body. In recent years, peptides have received extensive attention in drug design and synthesis, and peptide prediction tasks help us better search for functional peptides. Typically, we use the primary sequence and structural information of peptides for model encoding. However, recent studies have focused more on single-modal information (structure or sequence) for prediction without multi-modal approaches. We found that single-modal models are not good at handling datasets with less information in that particular modality. Therefore, this paper proposes the M2oE multi-modal collaborative expert peptide model. Based on previous work, by integrating sequence and spatial structural information, employing expert model and Cross-Attention Mechanism, the model's capabilities are balanced and improved. Experimental results indicate that the M2oE model performs excellently in complex task predictions.