Multi-Peptide: Multimodality Leveraged Language-Graph Learning of Peptide Properties

Peptides are crucial in biological processes and therapeutic applications. Given their importance, advancing our ability to predict peptide properties is essential. In this study, we introduce Multi-Peptide, an innovative approach that combines transformer-based language models with graph neural networks (GNNs) to predict peptide properties. We integrate PeptideBERT, a transformer model specifically designed for peptide property prediction, with a GNN encoder to capture both sequence-based and structural features. By employing a contrastive loss framework, Multi-Peptide aligns embeddings from both modalities into a shared latent space, thereby enhancing the transformer model's predictive accuracy. Evaluations on hemolysis and nonfouling data sets demonstrate Multi-Peptide's robustness, achieving state-of-the-art 88.057% accuracy in hemolysis prediction. This study highlights the potential of multimodal learning in bioinformatics, paving the way for accurate and reliable predictions in peptide-based research and applications.