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

Abstract

Hypertension or elevated blood pressure is a serious medical condition that significantly increases the risks of cardiovascular disease, heart disease, diabetes, stroke, kidney disease, and other health problems, that affect people worldwide. Thus, hypertension is one of the major global causes of premature death. Regarding the prevention and treatment of hypertension with no or few side effects, antihypertensive peptides (AHTPs) obtained from natural sources might be useful as nutraceuticals. Therefore, the search for alternative/novel AHTPs in food or natural sources has received much attention, as AHTPs may be functional agents for human health. AHTPs have been observed in diverse organisms, although many of them remain underinvestigated. The identification of peptides with antihypertensive activity in the laboratory is time- and resource-consuming. Alternatively, computational methods based on robust machine learning can identify or screen potential AHTP candidates prior to experimental verification. In this paper, we propose Ensemble-AHTPpred, an ensemble machine learning algorithm composed of a random forest (RF), a support vector machine (SVM), and extreme gradient boosting (XGB), with the aim of integrating diverse heterogeneous algorithms to enhance the robustness of the final predictive model. The selected feature set includes various computed features, such as various physicochemical properties, amino acid compositions (AACs), transitions, n-grams, and secondary structure-related information; these features are able to learn more information in terms of analyzing or explaining the characteristics of the predicted peptide. In addition, the tool is integrated with a newly proposed composite feature (generated based on a logistic regression function) that combines various feature aspects to enable improved AHTP characterization. Our tool, Ensemble-AHTPpred, achieved an overall accuracy above 90% on independent test data. Additionally, the approach was applied to novel experimentally validated AHTPs, obtained from recent studies, which did not overlap with the training and test datasets, and the tool could precisely predict these AHTPs.

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

“…Proline is highly abundant and more frequently occurs in antihypertensive peptides than in non-antihypertensive peptides. 34 The presence of glycine (N-terminal) and alanine (C-terminal) may exert strong ACE-inhibitory activity according to the peptide sequence of waste protein hydrolysate. 35…”

“…Proline is highly abundant and more frequently occurs in antihypertensive peptides than in non-antihypertensive peptides. 34 The presence of glycine (N-terminal) and alanine (C-terminal) may exert strong ACE-inhibitory activity according to the peptide sequence of waste protein hydrolysate. 35 Conversely, the content of hydroxyproline in small molecular peptides had decreased by approximately 25% compared to that in large molecular peptides.…”

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

“…To evaluate the practical effectiveness of current BP classification methods, CICERON was tested against state-of-the-art (SOTA) classifiers specific to the various peptide functional classes, which were selected upon careful literature inspection [62] , [63] , [64] , [65] , [66] , [67] . The main characteristics of SOTA models and their development dataset are summarized in Table 2 .…”

“… Web tool 503 celiac disease and 503 non-celiac disease peptides 0.47 No limitations [62] CICERON Logistic Regression Threemers (Tripeptide composition) Python package 240 celiac disease and 3750 non-celiac disease peptides 0.923 No limitations This work Antioxidant AnOxPP BiLSTM Neural Network 22 Amino Acids Descriptors (AADs). Web tool 1060 antioxidant and 1060 non-antioxidant peptides -0.005 Applicable on peptide sequences between 2 and 19 AA [64] CICERON Random Forest Threemers (Tripeptide composition) Python package 1001 antioxidant and 2989 non-antioxidant peptides 0.513 No limitations This work Neuropeptides Target-ensC_NP Ensemble of ETC, LGBM, SVM, XGB, and ADA One-hot encoding of single AA Python package 2435 neuropeptides and 2435 non-neuropeptides MCC not available Tool not available for use [65] CICERON Random Forest Dense (One hot encoding) Python package 165 neuropeptides and 3825 non-neuropeptides 0.736 No limitations This work Antihypertensive Ensemble-AHTPpred Ensemble of RF, SVM and XGB 431 numerical features Web tool 913 antihypertensive and 913 non hypertensive peptides MCC not available Tool not available for use [67] CICERON Random Forest BLOMAP Python package 1386 antihypertensive and 2604 non hypertensive peptides 0.665 No limitations This work Antimicrobial Antimicrobial-peptide-generation SeqGAN and BERT BERT tokenization Web tool ...…”

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

“…Above 90%, was achieved on the liberated inspection data using the Ensemble-AHTPpred tool. Furthermore, based on the latest studies, the method was practical for innovative empirically authorized AHTPs that were not overlaid with the test and datasets that are based on training, and these AHTPs might specifically be predicted by the tool ( 119 ).…”