Machine learning screening of bile acid-binding peptides in a peptide database derived from food proteins

Abstract

Bioactive peptides (BPs) are protein fragments that exhibit a wide variety of physicochemical properties, such as basic, acidic, hydrophobic, and hydrophilic properties; thus, they have the potential to interact with a variety of biomolecules, whereas neither carbohydrates nor fatty acids have such diverse properties. Therefore, BP is considered to be a new generation of biologically active regulators. Recently, some BPs that have shown positive benefits in humans have been screened from edible proteins. In the present study, a new BP screening method was developed using BIOPEP-UWM and machine learning. Training data were initially obtained using high-throughput techniques, and positive and negative datasets were generated. The predictive model was generated by calculating the explanatory variables of the peptides. To understand both site-specific and global characteristics, amino acid features (for site-specific characteristics) and peptide global features (for global characteristics) were generated. The constructed models were applied to the peptide database generated using BIOPEP-UWM, and bioactivity was predicted to explore candidate bile acid-binding peptides. Using this strategy, seven novel bile acid-binding peptides (VFWM, QRIFW, RVWVQ, LIRYTK, NGDEPL, PTFTRKL, and KISQRYQ) were identified. Our novel screening method can be easily applied to industrial applications using whole edible proteins. The proposed approach would be useful for identifying bile acid-binding peptides, as well as other BPs, as long as a large amount of training data can be obtained.

In Silico Screening of a Bile Acid Micelle Disruption Peptide for Oral Consumptions from Edible Peptide Database

“…pl/biochemia/index.php/en/biopep (accessed on 23 October 2018). was used for screening peptides [11]. On the date we accessed it (23 October 2018), 710 protein sequences were stored in the database.…”

“…The peptide database created previously from the protein database, BIOPEP-UWM, available at http://www.uwm.edu.pl/biochemia/index.php/en/biopep (accessed on 23 October 2018). was used for screening peptides [11]. On the date we accessed it (23 October 2018), 710 protein sequences were stored in the database.…”

“…A set of 710 proteins was downloaded from BIOPEP-UWM, and sequences were divided into peptide fragments with one residue shift from the N-terminal, resulting in a peptide database. First, the peptides stored in the database were adapted to the RF model created previously [11] and those with scores > 0.5, which are predicted as positive because the probability was a range from 0 to 1, were used for further screening.…”

“…Some bile acid-binding peptides have been screened by the principal component analysis (PCA) model from a randomly designed peptide library, and ExPASy was utilized to identify the peptides which could be isolated by enzyme hydrolysis [9,10]. Furthermore, bile acid-binding peptides from edible proteins were also screened using the RF model and a peptide database created from BIOPEP-UWM [11]. Bile acid-binding peptides can act as suppressors of cholesterol absorption via disruption of bile acid micelles including cholesterol molecules, resulting in a lowering of cholesterol levels in blood.…”

“…Traditional proteins known as safe food sources are preferable for human consumption. In our previous study, a peptide database was constructed from BIOPEP-UWM, which is called an edible peptide database [11]. This database consists of peptide fragments derived from food proteins that have one residue shift from the N-terminal amino acid.…”