Deep learning-optimized multi-enzyme hydrolysis for walnut antihypertensive peptides.

Area of Science:

• Food Science and Technology
• Biotechnology
• Nutraceuticals

Background:

• Hypertension is a major global health concern.
• Dietary peptides offer a promising avenue for blood pressure management.
• Optimizing peptide production requires advanced methodologies.

Purpose of the Study:

• To optimize the production of antihypertensive peptides from walnut protein using deep learning.
• To evaluate the efficacy of these peptides in vitro and in vivo.
• To explore the potential of large language models (LLMs) in functional peptide discovery.

Main Methods:

• Integration of deep learning with in vitro and in vivo experiments.
• Development of a novel multi-enzyme combination method using LLMs for enzyme screening.
• Assessment of angiotensin-converting enzyme (ACE) inhibitory activity and antioxidant properties.
• In vivo studies using spontaneously hypertensive rats (SHRs) and molecular docking analysis.

Main Results:

• Optimized walnut protein hydrolysates (W1) achieved 77.96% ACE inhibition and demonstrated gastrointestinal stability.
• W1 exhibited significant antioxidant activity and effectively reduced blood pressure in SHRs.
• Biomarker analysis revealed improved antioxidant status and vascular protection, with key peptides showing strong binding affinity to ACE.

Conclusions:

• Deep learning and LLMs can effectively optimize functional peptide production.
• Walnut protein-derived peptides present a promising, stable, and bioavailable option for hypertension management.
• This approach offers a novel dietary strategy for controlling blood pressure and improving vascular health.