Bioinformatics and Deep Learning Approach to Discover Food-Derived Active Ingredients for Alzheimer's Disease Therapy

Identification of novel antioxidant peptides from cottonseed meal co-fermented with Lactobacillus mucosae LLK-XR1 and acid proteases: In silico screening, molecular simulation, and in vitro functional analysis

This study is the first to employ a microbe-enzyme synergistic fermentation process to produce bioactive peptides from cottonseed meal (CSM). The peptide profile of the fermented CSM was identified using LC-MS/MS analysis, and common bioactivities were predicted through computational models. Molecular docking, molecular dynamics simulations, and cell experiments were conducted to validate the antioxidant functions and identify the potential best antioxidant peptides (AOP), S-7-H and E-7-H. The top five peptides with the best docking results were F-6-P, D-5-Y, S-7-H, D-5-F, and E-7-H, with binding energies of -10.4, -10.2, -10.1, -10.0, and - 9.8 kcal mol-1, respectively. Molecular dynamics simulations indicated that S-7-H and E-7-H demonstrated the most stable interactions with the Keap1 protein. All five AOPs effectively alleviated oxidative stress-induced damage in macrophages caused by hydrogen peroxide. These findings provide two novel and safe antioxidant peptides, S-7-H and E-7-H, and offer a more reliable screening approach for developing natural plant-derived AOPs.

Multitarget Natural Compounds for Ischemic Stroke Treatment: Integration of Deep Learning Prediction and Experimental Validation

Ischemic stroke's complex pathophysiology demands therapeutic approaches targeting multiple pathways simultaneously, yet current treatments remain limited. We developed an innovative drug discovery pipeline combining a deep learning approach with experimental validation to identify natural compounds with comprehensive neuroprotective properties. Our computational framework integrated SELFormer, a transformer-based deep learning model, and multiple deep learning algorithms to predict NC bioactivity against seven crucial stroke-related targets (ACE, GLA, MMP9, NPFFR2, PDE4D, and eNOS). The pipeline encompassed IC50 predictions, clustering analysis, quantitative structure-activity relationship (QSAR) modeling, and uniform manifold approximation and projection (UMAP)-based bioactivity profiling followed by molecular docking studies and experimental validation. Analysis revealed six distinct NC clusters with unique molecular signatures. UMAP projection identified 11 medium-activity (6 < pIC50 ≤ 7) and 57 high-activity (pIC50 > 7) compounds, with molecular docking confirming strong correlations between binding energies and predicted pIC50 values. In vitro studies using NGF-differentiated PC12 cells under oxygen-glucose deprivation demonstrated significant neuroprotective effects of four high-activity compounds: feruloyl glucose, l-hydroxy-l-tryptophan, mulberrin, and ellagic acid. These compounds enhanced cell viability, reduced acetylcholinesterase activity and lipid peroxidation, suppressed TNF-α expression, and upregulated BDNF mRNA levels. Notably, mulberrin and ellagic acid showed superior efficacy in modulating oxidative stress, inflammation, and neurotrophic signaling. This study establishes a robust deep learning-driven framework for identifying multitarget natural therapeutics for ischemic stroke. The validated compounds, particularly mulberrin and ellagic acid, are promising for stroke treatment development. Our findings demonstrate the effectiveness of integrating computational prediction with experimental validation in accelerating drug discovery for complex neurological disorders.