Exploring Latent Space for Generating Peptide Analogs Using Protein Language Models
This addresses the challenge of limited datasets in peptide generation for drug discovery and biotechnology, though it appears incremental as it builds on existing protein language model approaches.
The researchers tackled the problem of generating peptides with desired properties for drug discovery by developing a method that uses protein language models and autoencoders to explore embedding spaces, requiring only a single sequence input instead of large datasets. Their method showed significant improvements over baselines in similarity indicators for peptide structures, descriptors, and bioactivities, validated through Molecular Dynamics simulations on TIGIT inhibitors.
Generating peptides with desired properties is crucial for drug discovery and biotechnology. Traditional sequence-based and structure-based methods often require extensive datasets, which limits their effectiveness. In this study, we proposed a novel method that utilized autoencoder shaped models to explore the protein embedding space, and generate novel peptide analogs by leveraging protein language models. The proposed method requires only a single sequence of interest, avoiding the need for large datasets. Our results show significant improvements over baseline models in similarity indicators of peptide structures, descriptors and bioactivities. The proposed method validated through Molecular Dynamics simulations on TIGIT inhibitors, demonstrates that our method produces peptide analogs with similar yet distinct properties, highlighting its potential to enhance peptide screening processes.