TastepepAI, An artificial intelligence platform for taste peptide de novo design
🤖 AI Summary
The de novo discovery of natural taste-active peptides (sweet, salty, umami) faces bottlenecks including lengthy development cycles, low efficiency, and delayed safety assessment—hindering their practical application in food. Method: We developed the first AI platform dedicated to food functional peptide design, featuring a novel Loss-supervised Adaptive Variational Autoencoder (LA-VAE) that jointly models taste preference and aversion for multi-objective, condition-guided flavor-directed generation; integrated with SpepToxPred, an in-house deep learning model for end-to-end toxicity prediction. Contribution/Results: Through latent-space sequence optimization, the platform generated 73 novel peptide sequences computationally validated for both potent taste activity and low toxicity—significantly expanding the chemical space of flavor peptides and establishing a scalable, rational design framework for efficient and safe functional peptides.
Application Category
📝 Abstract
Taste peptides have emerged as promising natural flavoring agents attributed to their unique organoleptic properties, high safety profile, and potential health benefits. However, the de novo identification of taste peptides derived from animal, plant, or microbial sources remains a time-consuming and resource-intensive process, significantly impeding their widespread application in the food industry. Here, we present TastePepAI, a comprehensive artificial intelligence framework for customized taste peptide design and safety assessment. As the key element of this framework, a loss-supervised adaptive variational autoencoder (LA-VAE) is implemented to efficiently optimizes the latent representation of sequences during training and facilitates the generation of target peptides with desired taste profiles. Notably, our model incorporates a novel taste-avoidance mechanism, allowing for selective flavor exclusion. Subsequently, our in-house developed toxicity prediction algorithm (SpepToxPred) is integrated in the framework to undergo rigorous safety evaluation of generated peptides. Using this integrated platform, we successfully identified 73 peptides exhibiting sweet, salty, and umami, significantly expanding the current repertoire of taste peptides. This work demonstrates the potential of TastePepAI in accelerating taste peptide discovery for food applications and provides a versatile framework adaptable to broader peptide engineering challenges.
Problem
Research questions and friction points this paper is trying to address.
Design taste peptides efficiently
Overcome resource-intensive identification process
Ensure safety of generated peptides
Innovation
Methods, ideas, or system contributions that make the work stand out.
LA-VAE optimizes peptide sequences
Taste-avoidance mechanism excludes flavors
SpepToxPred evaluates peptide safety
🔎 Similar Papers
