A prediction method of interaction based on Bilinear Attention Networks for designing polyphenol-protein complexes delivery systems

Polyphenol-protein complexes delivery systems are gaining attention for their potential health benefits and food industry development. However, creating an ideal delivery system requires extensive wet-lab experimentation. To address this, we collected 525 ligand-protein interaction data pairs and established an interaction prediction model using Bilinear Attention Networks. We utilized 10-fold cross validation to address potential overfitting issues in the model, resulting in showed higher average AUROC (0.8443), AUPRC (0.7872), and F1 (0.8164). The optimal threshold (0.3739) was selected for the model to be used for subsequent analysis. Based on the model prediction results and optimal threshold, by verifying experimental analysis, the interaction of paeonol with the following proteins was obtained, including bovine serum albumin (lgKa = 6.2759), bovine β-lactoglobulin (lgKa = 6.7479), egg ovalbumin (lgKa = 5.1806), zein (lgKa = 6.0122), bovine α-lactalbumin (lgKa = 3.9170), bovine lactoferrin (lgKa = 4.5380), the first four proteins are consistent with the predicted results of the model, with lgKa >5. The established model can accurately and rapidly predict the interaction of polyphenol-protein complexes. This study is the first to combine open ligand-protein interaction experiments with Deep Learning algorithms in the food industry, greatly improving research efficiency and providing a novel perspective for future complex delivery system construction.

Change in thermal stability and molecular structure characteristics of whey protein beta-lactoglobulin upon the interaction with levamisole hydrochloride

The interaction between beta-lactoglobulin (BLG) and anthelmintic compounds including levamisole (LEV) is a matter of great concern as it not only poses potential health and environmental risks but also has significant implications for food processing and production. The mechanisms of LEV-BLG interaction were investigated through spectral and molecular modeling approaches. Fluorescence and UV-Visible investigations indicated the formation of a spontaneous and stable LEV-BLG complex. Structural changes of BLG were revealed by circular dichroism and Fourier transform infrared studies. The thermal stability of BLG increased in the presence of LEV. Molecular docking studies indicated the best mode of LEV-BLG interaction and molecular dynamics simulation confirmed the stability of the LEV-BLG complex. In conclusion, our study sheds light on the potential of BLG to interact with deleterious substances such as anthelmintic agents, thus highlighting the necessity of further research in this field to assure food safety and prevent any health hazards.

Structural modification of whey protein isolate by cinnamaldehyde and stabilization effect on β-carotene-loaded emulsions and emulsion gels

The effect of cinnamaldehyde (CA) on the structure and properties of whey protein isolate (WPI) was investigated. The resultant WPI/CA complex was used as stabilizer to form emulsions and emulsion gels, which were used for the delivery and protection of β-carotene. The particle size and hydrophobicity of WPI solution increased and then decreased with the addition of CA. Circular dichroism showed that CA mainly changed the secondary structure of WPI, with increasing β-fold content from 47.2% to 72.9%. The fluorescence spectra showed that both tryptophan and tyrosine in WPI were involved in the interaction with CA. WPI/CA complex as the stabilizer could form the stable emulsions and emulsion gels, which showed better protection effect on β-carotene, and helped enhance its bioaccessibility. The knowledge provides insights into the development of new multifunctional food ingredients and the enhancement of protein modification in food system.