Combining statistical, machine learning and experimental approaches for screening of novel antimicrobial peptides of calf cruor hydrolysates

Producing bioactive peptides through enzymatic hydrolysis is one of the most promising strategies for valorizing food by-products such as slaughterhouse blood. However, identifying the peptides responsible for the bioactivity of raw hydrolysates is difficult due to the large number of peptide sequences released during the enzymatic process. This study presents for the first time an integration of conventional statistical and machine learning tools to discover new antimicrobial peptides from calf cruor (C-cru), based on experimental data of the antimicrobial activity of raw hydrolysates and their peptide population. Pearson correlation (P-corr), linear regression (LR), and Random Forest (RF) were used to explain the relationship between peptide population abundance and antimicrobial activities (antibacterial, anti-mold, and anti-yeast) of raw hydrolysates of C-cru peptides. Peptides having greater importance in explaining the antimicrobial activities of hydrolysates were selected and their in vitro antimicrobial activity was further assessed by chemical synthesis. As a result, three new peptide sequences with fungicidal effect were identified: α(87–98), β(126–145), and β(128–145). This innovative approach can accelerate the discovery of new antimicrobial peptides from hemoglobin hydrolysates, which could be useful for further separation and application of peptides in food biopreservation. • Statistical/ML method proposed to elucidate bioactive peptides in raw hydrolysates. • This approach identified potential antimicrobial peptides from C-cru hydrolysates. • Three new antifungal peptide α(87–98), β(126–145), and β(128–145) were identified.