Ensemble-AHTPpred: A Robust Ensemble Machine Learning Model Integrated With a New Composite Feature for Identifying Antihypertensive Peptides

Classification of bioactive peptides: A systematic benchmark of models and encodings

Bioactive peptides are short amino acid chains possessing biological activity and exerting physiological effects relevant to human health. Despite their therapeutic value, their identification remains a major problem, as it mainly relies on time-consuming in vitro tests. While bioinformatic tools for the identification of bioactive peptides are available, they are focused on specific functional classes and have not been systematically tested on realistic settings. To tackle this problem, bioactive peptide sequences and functions were here gathered from a variety of databases to generate a unified collection of bioactive peptides from microbial fermentation. This collection was organized into nine functional classes including some previously studied and some unexplored such as immunomodulatory, opioid and cardiovascular peptides. Upon assessing their sequence properties, four alternative encoding methods were tested in combination with a multitude of machine learning algorithms, from basic classifiers like logistic regression to advanced algorithms like BERT. Tests on a total of 171 models showed that, while some functions are intrinsically easier to detect, no single combination of classifiers and encoders worked universally well for all classes. For this reason, we unified all the best individual models for each class and generated CICERON (Classification of bIoaCtive pEptides fRom micrObial fermeNtation), a classification tool for the functional classification of peptides. State-of-the-art classifiers were found to underperform on our realistic benchmark dataset compared to the models included in CICERON. Altogether, our work provides a tool for real-world peptide classification and can serve as a benchmark for future model development.

pLM4ACE: A protein language model based predictor for antihypertensive peptide screening

Angiotensin-I converting enzyme (ACE) regulates the renin-angiotensin system and is a drug target in clinical treatment for hypertension. This study aims to develop a protein language model (pLM) with evolutionary scale modeling (ESM-2) embeddings that is trained on experimental data to screen peptides with strong ACE inhibitory activity. Twelve conventional peptide embedding approaches and five machine learning (ML) modeling methods were also tested for performance comparison. Among the 65 classifiers tested, logistic regression with ESM-2 embeddings showed the best performance, with balanced accuracy (BACC), Matthews correlation coefficient (MCC), and area under the curve of 0.883 ± 0.017, 0.77 ± 0.032, and 0.96 ± 0.009, respectively. Multilayer perceptron and support vector machine also exhibited great compatibility with ESM-2 embeddings. The ESM-2 embeddings showed superior performance in enhancing the prediction model compared to the 12 traditional embedding methods. A user-friendly webserver (https://sqzujiduce.us-east-1.awsapprunner.com) with the top three models is now freely available.

The targeted development of collagen-active peptides based on composite enzyme hydrolysis: a study on the structure-activity relationship

Fish collagen, derived from sustainable sources, offers a valuable substrate for generating peptides with diverse biofunctionalities. In this study, alkaline, papain, and ginger protease were used to enzymatically hydrolyze fish skin collagen. The peptide molecular weight distribution and sequence were measured using HPLC and ICP-MS-MS, with papain/alkaline protease (AP) and papain/alkaline/ginger protease (APG) hydrolyzed samples compared. As the results showed, the incorporation of ginger protease was useful for increasing the degree of hydrolysis, with the content of <400 Da peptides increasing from 49.82% to 58.56%. The identified peptide sequence in the APG sample had more proline at the C-terminal. The peptides were separated into two components (different in molecular weight) using gel column chromatography. The molecular weight distribution, amino acid composition, ACE inhibitory activity, and fibroblast proliferation activity of the collected components were measured. In comparison, the contents of proline and hydroxyproline in the larger peptides decreased obviously after combined hydrolysis by ginger protease, reflecting the formation of a peptide sequence of smaller molecular weight containing glycine and hydroxyproline. The combined hydrolysis of ginger protease was beneficial for the improvement of the ACE inhibitory activity of the sample. However, the fibroblast proliferation activity of AP was higher than that of APG, indicating that further hydrolysis by ginger protease may destroy the hydroxyproline at the end of the peptide sequence. This study proposed a creative directional hydrolysis method and provided practical guidance for the production of collagen peptides with enhanced functional activity.

Recent advances in exploring and exploiting soybean functional peptides-a review

Soybeans are rich in proteins and phytochemicals such as isoflavones and phenolic compounds. It is an excellent source of peptides with numerous biological functions, including anti-inflammatory, anticancer, and antidiabetic activities. Soy bioactive peptides are small building blocks of proteins that are released after fermentation or gastrointestinal digestion as well as by food processing through enzymatic hydrolysis, often in combination with novel food processing techniques (i.e., microwave, ultrasound, and high-pressure homogenization), which are associated with numerous health benefits. Various studies have reported the potential health benefits of soybean-derived functional peptides, which have made them a great substitute for many chemical-based functional elements in foods and pharmaceutical products for a healthy lifestyle. This review provides unprecedented and up-to-date insights into the role of soybean peptides in various diseases and metabolic disorders, ranging from diabetes and hypertension to neurodegenerative disorders and viral infections with mechanisms were discussed. In addition, we discuss all the known techniques, including conventional and emerging approaches, for the prediction of active soybean peptides. Finally, real-life applications of soybean peptides as functional entities in food and pharmaceutical products are discussed.