1
|
Xu J, Ruan X, Yang J, Hu B, Li S, Hu J. SME-MFP: A novel spatiotemporal neural network with multiangle initialization embedding toward multifunctional peptides prediction. Comput Biol Chem 2024; 109:108033. [PMID: 38412804 DOI: 10.1016/j.compbiolchem.2024.108033] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/11/2023] [Revised: 01/09/2024] [Accepted: 02/17/2024] [Indexed: 02/29/2024]
Abstract
As a promising alternative to conventional antibiotic drugs in the biomedical field, functional peptide has been widely used in disease treatment owing to its low toxicity, high absorption rate, and biological activity. Recently, several machine learning methods have been developed for functional peptide prediction. However, the main research heavily relies on statistical features and few consider multifunctional peptide identification. So, we propose SME-MFP, a novel predictor in the imbalanced multi-label functional peptide datasets. First, we employ physicochemical and evolutionary information to represent the peptide sequence's initialization features from multiple perspectives. Second, the features are fused and then put into spatial feature extractors, where the residual connection and multiscale convolutional neural network extract more discriminative features of different lengths' peptide sequences. Besides, we also design AFT-based temporal feature extractors to fully capture the global interactions of the sequences. Finally, devising a new loss to replace the traditional cross entropy loss to settle the class imbalance problems. The results show that our framework not only enhances the model's ability to capture sequence features effectively, but also accuracy improves by 3.89% over existing methods on public peptide datasets.
Collapse
Affiliation(s)
- Jing Xu
- State Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, China
| | - Xiaoli Ruan
- State Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, China.
| | - Jing Yang
- State Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, China
| | - Bingqi Hu
- State Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, China
| | - Shaobo Li
- State Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, China
| | - Jianjun Hu
- Department of Computer Science and Engineering, University of South Carolina, Columbia 29208, USA
| |
Collapse
|
2
|
Azad H, Akbar MY, Sarfraz J, Haider W, Riaz MN, Ali GM, Ghazanfar S. G-ACP: a machine learning approach to the prediction of therapeutic peptides for gastric cancer. J Biomol Struct Dyn 2024:1-14. [PMID: 38450672 DOI: 10.1080/07391102.2024.2323141] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2023] [Accepted: 02/15/2024] [Indexed: 03/08/2024]
Abstract
Conventional Gastrointestinal (GI) cancer treatments are quite expensive and have major hazards. Nowadays, a different strategy places more emphasis on creating tiny biologically active peptides that do not cause severe poisoning. Anticancer peptides (ACPs) are found through experimental screening, which is time-dependent and frequently fraught with difficulties. Gastric ACPs are emerging as a promising GI cancer treatment in the current day. It is crucial to identify novel gastric ACPs to have an improved knowledge of their functioning processes and treatment of gastric cancer. As a result of the post-genomic era's massive production of peptide sequences, rapid and effective ACPs using a computational method are essential. Several adaptive statistical techniques for distinguishing ACPs and non-ACPs have recently been developed. A variety of adapted statistically significant methods have been developed to differentiate between ACPs and non-ACPs. Despite significant progress, there is no specific model for the prediction of gastric ACPs because the specific model will predict a particular type of peptide more accurately and quickly. To overcome this, an initiative is taken for the creation of a reliable framework for the accurate identification of gastric ACPs. The current technique in particular contains four possible features along with one hybrid feature encoding mechanisms which are the target-class motif previously indicated by Amino Acid Composition, Dipeptide Composition, Tripeptide Composition (TPC), Pseudo Amino Acid Composition (PAAC), and their Hybrid. Machine Learning algorithms make high-performance and accurate prediction tools. Moreover, highly variable and ideal deep feature selection is done using an ANOVA-based F score for feature pruning. Experiments on a range of algorithms are carried out to identify the optimal operating strategy due to the diverse nature of learning. Following analysis of the empirical results, Naïve Bayes with TPC and Hybrid feature space outperforms other methods with 0.99 accuracy score on the testing dataset. To find the model generalization an external validation is carried out. In external datasets, the Extra Trees with PAAC features outperforms with the accuracy of 0.94. The comparison study shows that our suggested model will predict gastric ACPs more accurately and will be useful in drug development and gastric cancer. The predictive model can be freely accessed at https://github.com/humeraazad10/G-ACP.git.Communicated by Ramaswamy H. Sarma.
Collapse
Affiliation(s)
- Humera Azad
- Department of Biosciences (Bioinformatics) Islamabad, Comsats University Islamabad, Pakistan
| | - Muhammad Yasir Akbar
- National Institute for Genomics and Advanced Biotechnology (NIGAB), National Agricultural Research Center (NARC), Pakistan
| | | | - Waseem Haider
- Department of Biosciences (Bioinformatics) Islamabad, Comsats University Islamabad, Pakistan
| | - Muhammad Naeem Riaz
- National Institute for Genomics and Advanced Biotechnology (NIGAB), National Agricultural Research Center (NARC), Pakistan
| | - Ghulam Muhammad Ali
- Department of Biosciences (Bioinformatics) Islamabad, Comsats University Islamabad, Pakistan
| | - Shakira Ghazanfar
- National Institute for Genomics and Advanced Biotechnology (NIGAB), National Agricultural Research Center (NARC), Pakistan
| |
Collapse
|
3
|
Liu M, Wu T, Li X, Zhu Y, Chen S, Huang J, Zhou F, Liu H. ACPPfel: Explainable deep ensemble learning for anticancer peptides prediction based on feature optimization. Front Genet 2024; 15:1352504. [PMID: 38487252 PMCID: PMC10937565 DOI: 10.3389/fgene.2024.1352504] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2023] [Accepted: 02/19/2024] [Indexed: 03/17/2024] Open
Abstract
Background: Cancer is a significant global health problem that continues to cause a high number of deaths worldwide. Traditional cancer treatments often come with risks that can compromise the functionality of vital organs. As a potential alternative to these conventional therapies, Anticancer peptides (ACPs) have garnered attention for their small size, high specificity, and reduced toxicity, making them as a promising option for cancer treatments. Methods: However, the process of identifying effective ACPs through wet-lab screening experiments is time-consuming and requires a lot of labor. To overcome this challenge, a deep ensemble learning method is constructed to predict anticancer peptides (ACPs) in this study. To evaluate the reliability of the framework, four different datasets are used in this study for training and testing. During the training process of the model, integration of feature selection methods, feature dimensionality reduction measures, and optimization of the deep ensemble model are carried out. Finally, we explored the interpretability of features that affected the final prediction results and built a web server platform to facilitate anticancer peptides prediction, which can be used by all researchers for further studies. This web server can be accessed at http://lmylab.online:5001/. Results: The result of this study achieves an accuracy rate of 98.53% and an AUC (Area under Curve) value of 0.9972 on the ACPfel dataset, it has improvements on other datasets as well.
Collapse
Affiliation(s)
- Mingyou Liu
- School of Biology and Engineering (School of Health Medicine Modern Industry), Guizhou Medical University, Guiyang, China
- Engineering Research Center of Health Medicine Biotechnology of Guizhou Province, Guizhou Medical University, Guiyang, China
| | - Tao Wu
- School of Biology and Engineering (School of Health Medicine Modern Industry), Guizhou Medical University, Guiyang, China
| | - Xue Li
- School of Biology and Engineering (School of Health Medicine Modern Industry), Guizhou Medical University, Guiyang, China
- Engineering Research Center of Health Medicine Biotechnology of Guizhou Province, Guizhou Medical University, Guiyang, China
| | - Yingxue Zhu
- School of Biology and Engineering (School of Health Medicine Modern Industry), Guizhou Medical University, Guiyang, China
- Engineering Research Center of Health Medicine Biotechnology of Guizhou Province, Guizhou Medical University, Guiyang, China
| | - Sen Chen
- School of Biology and Engineering (School of Health Medicine Modern Industry), Guizhou Medical University, Guiyang, China
| | - Jian Huang
- School of Life Science and Technology, University of Electronic Science and Technology, Chengdu, China
- School of Healthcare Technology, Chengdu Neusoft University, Chengdu, China
| | - Fengfeng Zhou
- School of Biology and Engineering (School of Health Medicine Modern Industry), Guizhou Medical University, Guiyang, China
- College of Computer Science and Technology, and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China
| | - Hongmei Liu
- School of Biology and Engineering (School of Health Medicine Modern Industry), Guizhou Medical University, Guiyang, China
- Engineering Research Center of Health Medicine Biotechnology of Guizhou Province, Guizhou Medical University, Guiyang, China
- College of Computer Science and Technology, and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China
| |
Collapse
|
4
|
Purohit K, Reddy N, Sunna A. Exploring the Potential of Bioactive Peptides: From Natural Sources to Therapeutics. Int J Mol Sci 2024; 25:1391. [PMID: 38338676 PMCID: PMC10855437 DOI: 10.3390/ijms25031391] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Revised: 01/18/2024] [Accepted: 01/21/2024] [Indexed: 02/12/2024] Open
Abstract
Bioactive peptides, specific protein fragments with positive health effects, are gaining traction in drug development for advantages like enhanced penetration, low toxicity, and rapid clearance. This comprehensive review navigates the intricate landscape of peptide science, covering discovery to functional characterization. Beginning with a peptidomic exploration of natural sources, the review emphasizes the search for novel peptides. Extraction approaches, including enzymatic hydrolysis, microbial fermentation, and specialized methods for disulfide-linked peptides, are extensively covered. Mass spectrometric analysis techniques for data acquisition and identification, such as liquid chromatography, capillary electrophoresis, untargeted peptide analysis, and bioinformatics, are thoroughly outlined. The exploration of peptide bioactivity incorporates various methodologies, from in vitro assays to in silico techniques, including advanced approaches like phage display and cell-based assays. The review also discusses the structure-activity relationship in the context of antimicrobial peptides (AMPs), ACE-inhibitory peptides (ACEs), and antioxidative peptides (AOPs). Concluding with key findings and future research directions, this interdisciplinary review serves as a comprehensive reference, offering a holistic understanding of peptides and their potential therapeutic applications.
Collapse
Affiliation(s)
- Kruttika Purohit
- School of Natural Sciences, Macquarie University, Sydney, NSW 2109, Australia;
- Australian Research Council Industrial Transformation Training Centre for Facilitated Advancement of Australia’s Bioactives (FAAB), Sydney, NSW 2109, Australia;
| | - Narsimha Reddy
- Australian Research Council Industrial Transformation Training Centre for Facilitated Advancement of Australia’s Bioactives (FAAB), Sydney, NSW 2109, Australia;
- School of Science, Parramatta Campus, Western Sydney University, Penrith, NSW 2751, Australia
| | - Anwar Sunna
- School of Natural Sciences, Macquarie University, Sydney, NSW 2109, Australia;
- Australian Research Council Industrial Transformation Training Centre for Facilitated Advancement of Australia’s Bioactives (FAAB), Sydney, NSW 2109, Australia;
- Biomolecular Discovery Research Centre, Macquarie University, Sydney, NSW 2109, Australia
| |
Collapse
|
5
|
Zuo W, Kwok HF. Design of Bioengineered Peptides/Proteases as Anti-cancer Reagents with Integrated Omics and Machine Learning Approaches. Methods Mol Biol 2024; 2747:295-309. [PMID: 38038948 DOI: 10.1007/978-1-0716-3589-6_22] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/02/2023]
Abstract
Cancer is a heterogeneous disorder of uncontrolled growth of cells, which has proven to be a major burden worldwide. Many treatment options are available for cancer therapy, yet side effects and drug resistance remain major hurdles. Therefore, it is necessary to develop novel drugs for cancer therapy. Anti-cancer peptides (ACPs) are attractive candidates with remarkable potency, low toxicity, and high specificity advantages. However, traditional experimental identification of ACPs is time-consuming and expensive. Integrated omics combined with machine learning (ML) is considered a new powerful and cost-effective strategy to discover ACPs from natural products. In this chapter, we describe in detail experimental procedures for collecting both transcriptomic and proteomic data from venoms, followed by descriptive approaches to ML prediction.
Collapse
Affiliation(s)
- Weimin Zuo
- Cancer Centre, Faculty of Health Sciences, University of Macau, Avenida de Universidade, Taipa, Macau SAR, China
- School of Biomedical Sciences, Faculty of Health Sciences, University of Macau, Avenida de Universidade, Taipa, Macau SAR, China
| | - Hang Fai Kwok
- Cancer Centre, Faculty of Health Sciences, University of Macau, Avenida de Universidade, Taipa, Macau SAR, China.
- School of Biomedical Sciences, Faculty of Health Sciences, University of Macau, Avenida de Universidade, Taipa, Macau SAR, China.
- MoE Frontiers Science Center for Precision Oncology, University of Macau, Avenida de Universidade, Taipa, Macau SAR, China.
| |
Collapse
|
6
|
Chang L, Mondal A, Singh B, Martínez-Noa Y, Perez A. Revolutionizing Peptide-Based Drug Discovery: Advances in the Post-AlphaFold Era. WILEY INTERDISCIPLINARY REVIEWS. COMPUTATIONAL MOLECULAR SCIENCE 2024; 14:e1693. [PMID: 38680429 PMCID: PMC11052547 DOI: 10.1002/wcms.1693] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/06/2023] [Accepted: 09/18/2023] [Indexed: 05/01/2024]
Abstract
Peptide-based drugs offer high specificity, potency, and selectivity. However, their inherent flexibility and differences in conformational preferences between their free and bound states create unique challenges that have hindered progress in effective drug discovery pipelines. The emergence of AlphaFold (AF) and Artificial Intelligence (AI) presents new opportunities for enhancing peptide-based drug discovery. We explore recent advancements that facilitate a successful peptide drug discovery pipeline, considering peptides' attractive therapeutic properties and strategies to enhance their stability and bioavailability. AF enables efficient and accurate prediction of peptide-protein structures, addressing a critical requirement in computational drug discovery pipelines. In the post-AF era, we are witnessing rapid progress with the potential to revolutionize peptide-based drug discovery such as the ability to rank peptide binders or classify them as binders/non-binders and the ability to design novel peptide sequences. However, AI-based methods are struggling due to the lack of well-curated datasets, for example to accommodate modified amino acids or unconventional cyclization. Thus, physics-based methods, such as docking or molecular dynamics simulations, continue to hold a complementary role in peptide drug discovery pipelines. Moreover, MD-based tools offer valuable insights into binding mechanisms, as well as the thermodynamic and kinetic properties of complexes. As we navigate this evolving landscape, a synergistic integration of AI and physics-based methods holds the promise of reshaping the landscape of peptide-based drug discovery.
Collapse
Affiliation(s)
- Liwei Chang
- Department of Chemistry, University of Florida, Gainesville, FL 32611
| | - Arup Mondal
- Department of Chemistry, University of Florida, Gainesville, FL 32611
| | - Bhumika Singh
- Department of Chemistry, University of Florida, Gainesville, FL 32611
| | | | - Alberto Perez
- Department of Chemistry and Quantum Theory Project, University of Florida, Gainesville, FL 32611
| |
Collapse
|
7
|
Lee YJ. Examining the functional space of gut microbiome-derived peptides. Microbiologyopen 2023; 12:e1393. [PMID: 38129980 PMCID: PMC10714122 DOI: 10.1002/mbo3.1393] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2023] [Revised: 12/04/2023] [Accepted: 12/05/2023] [Indexed: 12/23/2023] Open
Abstract
The human gut microbiome contains thousands of small, novel peptides that could play a role in microbe-microbe and host-microbe interactions, contributing to human health and disease. Although these peptides have not yet been systematically characterized, computational tools can be used to elucidate the bioactivities they may have. This article proposes probing the functional space of gut microbiome-derived peptides (MDPs) using in silico approaches for three bioactivities: antimicrobial, anticancer, and nucleomodulins. Machine learning programs that support peptide and protein queries are provided for each bioactivity. Considering the biases of an activity-centric approach, activity-agnostic tools using structural and chemical similarity and target prediction are also described. Gut MDPs represent a vast functional space that can not only contribute to our understanding of microbiome interactions but potentially even serve as a source of life-changing therapeutics.
Collapse
Affiliation(s)
- Ying‐Chiang J. Lee
- Department of Molecular BiologyPrinceton UniversityPrincetonNew JerseyUSA
| |
Collapse
|
8
|
Sun M, Hu H, Pang W, Zhou Y. ACP-BC: A Model for Accurate Identification of Anticancer Peptides Based on Fusion Features of Bidirectional Long Short-Term Memory and Chemically Derived Information. Int J Mol Sci 2023; 24:15447. [PMID: 37895128 PMCID: PMC10607064 DOI: 10.3390/ijms242015447] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2023] [Revised: 09/10/2023] [Accepted: 10/20/2023] [Indexed: 10/29/2023] Open
Abstract
Anticancer peptides (ACPs) have been proven to possess potent anticancer activities. Although computational methods have emerged for rapid ACPs identification, their accuracy still needs improvement. In this study, we propose a model called ACP-BC, a three-channel end-to-end model that utilizes various combinations of data augmentation techniques. In the first channel, features are extracted from the raw sequence using a bidirectional long short-term memory network. In the second channel, the entire sequence is converted into a chemical molecular formula, which is further simplified using Simplified Molecular Input Line Entry System notation to obtain deep abstract features through a bidirectional encoder representation transformer (BERT). In the third channel, we manually selected four effective features according to dipeptide composition, binary profile feature, k-mer sparse matrix, and pseudo amino acid composition. Notably, the application of chemical BERT in predicting ACPs is novel and successfully integrated into our model. To validate the performance of our model, we selected two benchmark datasets, ACPs740 and ACPs240. ACP-BC achieved prediction accuracy with 87% and 90% on these two datasets, respectively, representing improvements of 1.3% and 7% compared to existing state-of-the-art methods on these datasets. Therefore, systematic comparative experiments have shown that the ACP-BC can effectively identify anticancer peptides.
Collapse
Affiliation(s)
- Mingwei Sun
- Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, China; (M.S.); (H.H.)
| | - Haoyuan Hu
- Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, China; (M.S.); (H.H.)
| | - Wei Pang
- School of Mathematical and Computer Sciences, Heriot-Watt University, Edinburgh EH14 4AS, UK;
| | - You Zhou
- Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, China; (M.S.); (H.H.)
- College of Software, Jilin University, Changchun 130012, China
| |
Collapse
|
9
|
Yao L, Zhang Y, Li W, Chung C, Guan J, Zhang W, Chiang Y, Lee T. DeepAFP: An effective computational framework for identifying antifungal peptides based on deep learning. Protein Sci 2023; 32:e4758. [PMID: 37595093 PMCID: PMC10503419 DOI: 10.1002/pro.4758] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2023] [Revised: 08/02/2023] [Accepted: 08/10/2023] [Indexed: 08/20/2023]
Abstract
Fungal infections have become a significant global health issue, affecting millions worldwide. Antifungal peptides (AFPs) have emerged as a promising alternative to conventional antifungal drugs due to their low toxicity and low propensity for inducing resistance. In this study, we developed a deep learning-based framework called DeepAFP to efficiently identify AFPs. DeepAFP fully leverages and mines composition information, evolutionary information, and physicochemical properties of peptides by employing combined kernels from multiple branches of convolutional neural network with bi-directional long short-term memory layers. In addition, DeepAFP integrates a transfer learning strategy to obtain efficient representations of peptides for improving model performance. DeepAFP demonstrates strong predictive ability on carefully curated datasets, yielding an accuracy of 93.29% and an F1-score of 93.45% on the DeepAFP-Main dataset. The experimental results show that DeepAFP outperforms existing AFP prediction tools, achieving state-of-the-art performance. Finally, we provide a downloadable AFP prediction tool to meet the demands of large-scale prediction and facilitate the usage of our framework by the public or other researchers. Our framework can accurately identify AFPs in a short time without requiring significant human and material resources, and hence can accelerate the development of AFPs as well as contribute to the treatment of fungal infections. Furthermore, our method can provide new perspectives for other biological sequence analysis tasks.
Collapse
Affiliation(s)
- Lantian Yao
- Kobilka Institute of Innovative Drug Discovery, School of MedicineThe Chinese University of Hong KongShenzhenChina
- School of Science and EngineeringThe Chinese University of Hong KongShenzhenChina
| | - Yuntian Zhang
- School of MedicineThe Chinese University of Hong KongShenzhenChina
| | - Wenshuo Li
- School of Science and EngineeringThe Chinese University of Hong KongShenzhenChina
| | - Chia‐Ru Chung
- Department of Computer Science and Information EngineeringNational Central UniversityTaoyuanTaiwan
| | - Jiahui Guan
- School of MedicineThe Chinese University of Hong KongShenzhenChina
| | - Wenyang Zhang
- School of MedicineThe Chinese University of Hong KongShenzhenChina
| | - Ying‐Chih Chiang
- Kobilka Institute of Innovative Drug Discovery, School of MedicineThe Chinese University of Hong KongShenzhenChina
- School of MedicineThe Chinese University of Hong KongShenzhenChina
| | - Tzong‐Yi Lee
- Institute of Bioinformatics and Systems BiologyNational Yang Ming Chiao Tung UniversityHsinchuTaiwan
- Center for Intelligent Drug Systems and Smart Bio‐devices (IDS2B)National Yang Ming Chiao Tung UniversityHsinchuTaiwan
| |
Collapse
|
10
|
Yan J, Zhang B, Zhou M, Campbell-Valois FX, Siu SWI. A deep learning method for predicting the minimum inhibitory concentration of antimicrobial peptides against Escherichia coli using Multi-Branch-CNN and Attention. mSystems 2023; 8:e0034523. [PMID: 37431995 PMCID: PMC10506472 DOI: 10.1128/msystems.00345-23] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2023] [Accepted: 05/31/2023] [Indexed: 07/12/2023] Open
Abstract
Antimicrobial peptides (AMPs) are a promising alternative to antibiotics to combat drug resistance in pathogenic bacteria. However, the development of AMPs with high potency and specificity remains a challenge, and new tools to evaluate antimicrobial activity are needed to accelerate the discovery process. Therefore, we proposed MBC-Attention, a combination of a multi-branch convolution neural network architecture and attention mechanisms to predict the experimental minimum inhibitory concentration of peptides against Escherichia coli. The optimal MBC-Attention model achieved an average Pearson correlation coefficient (PCC) of 0.775 and a root mean squared error (RMSE) of 0.533 (log μM) in three independent tests of randomly drawn sequences from the data set. This results in a 5-12% improvement in PCC and a 6-13% improvement in RMSE compared to 17 traditional machine learning models and 2 optimally tuned models using random forest and support vector machine. Ablation studies confirmed that the two proposed attention mechanisms, global attention and local attention, contributed largely to performance improvement. IMPORTANCE Antimicrobial peptides (AMPs) are potential candidates for replacing conventional antibiotics to combat drug resistance in pathogenic bacteria. Therefore, it is necessary to evaluate the antimicrobial activity of AMPs quantitatively. However, wet-lab experiments are labor-intensive and time-consuming. To accelerate the evaluation process, we develop a deep learning method called MBC-Attention to regress the experimental minimum inhibitory concentration of AMPs against Escherichia coli. The proposed model outperforms traditional machine learning methods. Data, scripts to reproduce experiments, and the final production models are available on GitHub.
Collapse
Affiliation(s)
- Jielu Yan
- PAMI Research Group, Department of Computer and Information Science, University of Macau, Taipa, Macau, China
| | - Bob Zhang
- PAMI Research Group, Department of Computer and Information Science, University of Macau, Taipa, Macau, China
| | - Mingliang Zhou
- School of Computer Science, Chongqing University, Shapingba, Chongqing, China
| | - François-Xavier Campbell-Valois
- Host-Microbe Interactions Laboratory, Center for Chemical and Synthetic Biology, Department of Chemistry and Biomolecular Sciences, University of Ottawa, Ottawa, Ontario, Canada
- Centre for Infection, Immunity, and Inflammation, University of Ottawa, Ottawa, Ontario, Canada
- Department of Biochemistry, Microbiology and Immunology, University of Ottawa, Ottawa, Ontario, Canada
| | - Shirley W. I. Siu
- Institute of Science and Environment, University of Saint Joseph, Macau, China
| |
Collapse
|
11
|
Saini S, Rathore A, Sharma S, Saini A. Exploratory data analysis of physicochemical parameters of natural antimicrobial and anticancer peptides: Unraveling the patterns and trends for the rational design of novel peptides. BIOIMPACTS : BI 2023; 14:26438. [PMID: 38327633 PMCID: PMC10844588 DOI: 10.34172/bi.2023.26438] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/06/2022] [Revised: 11/04/2022] [Accepted: 12/04/2022] [Indexed: 02/09/2024]
Abstract
Introduction Peptide-based research has attained new avenues in the antibiotics and cancer drug resistance era. The basis of peptide design research lies in playing with or altering physicochemical parameters. Here in this work, we have done exploratory data analysis (EDA) of physicochemical parameters of antimicrobial peptides (AMPs) and anticancer peptides (ACPs), two promising therapeutics for microbial and cancer drug resistance to deduce patterns and trends. Methods Briefly, we have captured the natural AMPs and ACPs data from the APD3 database. After cleaning the data manually and by CD-HIT web server, further data analysis has been done using Python-based packages, modlAMP and Pandas. We have extracted the descriptive statistics of 10 physicochemical parameters of AMPs and ACPs to build a comprehensive dataset containing all major parameters. The global analysis of datasets has been done using modlAMP to find the initial patterns in global data. The subsets of AMPs and ACPs were curated based on the length of the peptides and were analyzed by Pandas package to deduce the graphical profile of AMPs and ACPs. Results EDA of AMPs and ACPs shows selectivity in the length and amino acid compositions. The distribution of physicochemical parameters in defined quartile ranges was observed in the descriptive statistical and graphical analysis. The preferred length range of AMPs and ACPs was found to be 21-30 amino acids, whereas few outliers in each parameter were evident after EDA analysis. Conclusion The derived patterns from natural AMPs and ACPs can be used for the rational design of novel peptides. The statistical and graphical data distribution findings will help in combining the different parameters for potent design of novel AMPs and ACPs.
Collapse
Affiliation(s)
- Sandeep Saini
- Department of Biophysics, Panjab University, Sector 25, Chandigarh 160014, India
- Department of Bioinformatics, Goswami Ganesh Dutta Sanatan Dharma College, Sector 32-C, Chandigarh 160030, India
| | - Aayushi Rathore
- Institute of Bioinformatics and Applied Biotechnology, Biotech Park, Bengaluru 560100, India
| | - Sheetal Sharma
- Department of Biophysics, Panjab University, Sector 25, Chandigarh 160014, India
| | - Avneet Saini
- Department of Biophysics, Panjab University, Sector 25, Chandigarh 160014, India
| |
Collapse
|
12
|
Ye J, Li A, Zheng H, Yang B, Lu Y. Machine Learning Advances in Predicting Peptide/Protein-Protein Interactions Based on Sequence Information for Lead Peptides Discovery. Adv Biol (Weinh) 2023; 7:e2200232. [PMID: 36775876 DOI: 10.1002/adbi.202200232] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2022] [Revised: 12/30/2022] [Indexed: 02/14/2023]
Abstract
Peptides have shown increasing advantages and significant clinical value in drug discovery and development. With the development of high-throughput technologies and artificial intelligence (AI), machine learning (ML) methods for discovering new lead peptides have been expanded and incorporated into rational drug design. Predictions of peptide-protein interactions (PepPIs) and protein-protein interactions (PPIs) are both opportunities and challenges in computational biology, which will help to better understand the mechanisms of disease and provide the impetus for the discovery of lead peptides. This paper comprehensively reviews computational models for PepPI and PPI predictions. It begins with an introduction of various databases of peptide ligands and target proteins. Then it discusses data formats and feature representations for proteins and peptides. Furthermore, classical ML methods and emerging deep learning (DL) methods that can be used to train prediction models of PepPI and PPI are classified into four categories, and their advantages and disadvantages are analyzed. To assess the relative performance of different models, different validation protocols and evaluation indexes are discussed. The goal of this review is to help researchers quickly get started to develop computational frameworks using these integrated resources and eventually promote the discovery of lead peptides.
Collapse
Affiliation(s)
- Jiahao Ye
- School of Medicine, Shanghai University, Shanghai, 200444, China
| | - An Li
- Department of Critical Care Medicine, Shanghai Tenth People's Hospital, School of Medicine, Tongji University, Shanghai, 200072, China
- Department of Biochemical Pharmacy, School of Pharmacy, Second Military Medical University, Shanghai, 200433, China
| | - Hao Zheng
- School of Medicine, Shanghai University, Shanghai, 200444, China
| | - Banghua Yang
- School of Medicine, Shanghai University, Shanghai, 200444, China
| | - Yiming Lu
- School of Medicine, Shanghai University, Shanghai, 200444, China
- Department of Critical Care Medicine, Shanghai Tenth People's Hospital, School of Medicine, Tongji University, Shanghai, 200072, China
- Department of Biochemical Pharmacy, School of Pharmacy, Second Military Medical University, Shanghai, 200433, China
| |
Collapse
|
13
|
Asensio-Calavia P, González-Acosta S, Otazo-Pérez A, López MR, Morales-delaNuez A, Pérez de la Lastra JM. Teleost Piscidins-In Silico Perspective of Natural Peptide Antibiotics from Marine Sources. Antibiotics (Basel) 2023; 12:antibiotics12050855. [PMID: 37237758 DOI: 10.3390/antibiotics12050855] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/29/2023] [Revised: 04/28/2023] [Accepted: 05/02/2023] [Indexed: 05/28/2023] Open
Abstract
Fish, like all other animals, are exposed to constant contact with microbes, both on their skin and on the surfaces of their respiratory and digestive systems. Fish have a system of non-specific immune responses that provides them with initial protection against infection and allows them to survive under normal conditions despite the presence of these potential invaders. However, fish are less protected against invading diseases than other marine vertebrates because their epidermal surface, composed primarily of living cells, lacks the keratinized skin that serves as an efficient natural barrier in other marine vertebrates. Antimicrobial peptides (AMPs) are one type of innate immune protection present in all life forms. AMPs have been shown to have a broader range of biological effects than conventional antibiotics, including antibacterial, antiviral, antiprotozoal, and antifungal effects. Although other AMPs, such as defensins and hepcidins, are found in all vertebrates and are relatively well conserved, piscidins are found exclusively in Teleost fish and are not found in any other animal. Therefore, there is less information on the expression and bioactivity of piscidins than on other AMPs. Piscidins are highly effective against Gram-positive and Gram-negative bacteria that cause disease in fish and humans and have the potential to be used as pharmacological anti-infectives in biomedicine and aquaculture. To better understand the potential benefits and limitations of using these peptides as therapeutic agents, we are conducting a comprehensive study of the Teleost piscidins included in the "reviewed" category of the UniProt database using bioinformatics tools. They all have amphipathic alpha-helical structures. The amphipathic architecture of piscidin peptides and positively charged residues influence their antibacterial activity. These alpha-helices are intriguing antimicrobial drugs due to their stability in high-salt and metal environments. New treatments for multidrug-resistant bacteria, cancer, and inflammation may be inspired by piscidin peptides.
Collapse
Affiliation(s)
- Patricia Asensio-Calavia
- Biotechnology of Macromolecules Research Group, Instituto de Productos Naturales y Agrobiología (IPNA-CSIC), Avda. Astrofísico Francisco Sánchez, 3, 38206 San Cristóbal de La Laguna, Spain
- School of Doctoral and Graduate Studies, Universidad de La Laguna, Avda. Astrofísico Francisco Sánchez, SN. Edificio Calabaza-Apdo. 456, 38200 San Cristóbal de La Laguna, Spain
| | - Sergio González-Acosta
- Biotechnology of Macromolecules Research Group, Instituto de Productos Naturales y Agrobiología (IPNA-CSIC), Avda. Astrofísico Francisco Sánchez, 3, 38206 San Cristóbal de La Laguna, Spain
- School of Doctoral and Graduate Studies, Universidad de La Laguna, Avda. Astrofísico Francisco Sánchez, SN. Edificio Calabaza-Apdo. 456, 38200 San Cristóbal de La Laguna, Spain
| | - Andrea Otazo-Pérez
- Biotechnology of Macromolecules Research Group, Instituto de Productos Naturales y Agrobiología (IPNA-CSIC), Avda. Astrofísico Francisco Sánchez, 3, 38206 San Cristóbal de La Laguna, Spain
- School of Doctoral and Graduate Studies, Universidad de La Laguna, Avda. Astrofísico Francisco Sánchez, SN. Edificio Calabaza-Apdo. 456, 38200 San Cristóbal de La Laguna, Spain
| | - Manuel R López
- Biotechnology of Macromolecules Research Group, Instituto de Productos Naturales y Agrobiología (IPNA-CSIC), Avda. Astrofísico Francisco Sánchez, 3, 38206 San Cristóbal de La Laguna, Spain
| | - Antonio Morales-delaNuez
- Biotechnology of Macromolecules Research Group, Instituto de Productos Naturales y Agrobiología (IPNA-CSIC), Avda. Astrofísico Francisco Sánchez, 3, 38206 San Cristóbal de La Laguna, Spain
| | - José Manuel Pérez de la Lastra
- Biotechnology of Macromolecules Research Group, Instituto de Productos Naturales y Agrobiología (IPNA-CSIC), Avda. Astrofísico Francisco Sánchez, 3, 38206 San Cristóbal de La Laguna, Spain
| |
Collapse
|
14
|
Yao L, Li W, Zhang Y, Deng J, Pang Y, Huang Y, Chung CR, Yu J, Chiang YC, Lee TY. Accelerating the Discovery of Anticancer Peptides through Deep Forest Architecture with Deep Graphical Representation. Int J Mol Sci 2023; 24:ijms24054328. [PMID: 36901759 PMCID: PMC10001941 DOI: 10.3390/ijms24054328] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2023] [Revised: 02/02/2023] [Accepted: 02/07/2023] [Indexed: 02/24/2023] Open
Abstract
Cancer is one of the leading diseases threatening human life and health worldwide. Peptide-based therapies have attracted much attention in recent years. Therefore, the precise prediction of anticancer peptides (ACPs) is crucial for discovering and designing novel cancer treatments. In this study, we proposed a novel machine learning framework (GRDF) that incorporates deep graphical representation and deep forest architecture for identifying ACPs. Specifically, GRDF extracts graphical features based on the physicochemical properties of peptides and integrates their evolutionary information along with binary profiles for constructing models. Moreover, we employ the deep forest algorithm, which adopts a layer-by-layer cascade architecture similar to deep neural networks, enabling excellent performance on small datasets but without complicated tuning of hyperparameters. The experiment shows GRDF exhibits state-of-the-art performance on two elaborate datasets (Set 1 and Set 2), achieving 77.12% accuracy and 77.54% F1-score on Set 1, as well as 94.10% accuracy and 94.15% F1-score on Set 2, exceeding existing ACP prediction methods. Our models exhibit greater robustness than the baseline algorithms commonly used for other sequence analysis tasks. In addition, GRDF is well-interpretable, enabling researchers to better understand the features of peptide sequences. The promising results demonstrate that GRDF is remarkably effective in identifying ACPs. Therefore, the framework presented in this study could assist researchers in facilitating the discovery of anticancer peptides and contribute to developing novel cancer treatments.
Collapse
Affiliation(s)
- Lantian Yao
- Kobilka Institute of Innovative Drug Discovery, School of Medicine, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
- School of Science and Engineering, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
| | - Wenshuo Li
- School of Science and Engineering, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
- Warshel Institute for Computational Biology, School of Medicine, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
| | - Yuntian Zhang
- Warshel Institute for Computational Biology, School of Medicine, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
- School of Medicine, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
| | - Junyang Deng
- School of Medicine, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
| | - Yuxuan Pang
- School of Science and Engineering, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
- Warshel Institute for Computational Biology, School of Medicine, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
| | - Yixian Huang
- Warshel Institute for Computational Biology, School of Medicine, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
- School of Medicine, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
| | - Chia-Ru Chung
- Kobilka Institute of Innovative Drug Discovery, School of Medicine, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
| | - Jinhan Yu
- Warshel Institute for Computational Biology, School of Medicine, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
- School of Medicine, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
| | - Ying-Chih Chiang
- Kobilka Institute of Innovative Drug Discovery, School of Medicine, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
- Correspondence: (Y.-C.C.); (T.-Y.L.)
| | - Tzong-Yi Lee
- Warshel Institute for Computational Biology, School of Medicine, The Chinese University of Hong Kong (Shenzhen), 2001 Longxiang Road, Shenzhen 518172, China
- Correspondence: (Y.-C.C.); (T.-Y.L.)
| |
Collapse
|
15
|
Zhang H, Saravanan KM, Wei Y, Jiao Y, Yang Y, Pan Y, Wu X, Zhang JZH. Deep Learning-Based Bioactive Therapeutic Peptide Generation and Screening. J Chem Inf Model 2023; 63:835-845. [PMID: 36724090 DOI: 10.1021/acs.jcim.2c01485] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/02/2023]
Abstract
Many bioactive peptides demonstrated therapeutic effects over complicated diseases, such as antiviral, antibacterial, anticancer, etc. It is possible to generate a large number of potentially bioactive peptides using deep learning in a manner analogous to the generation of de novo chemical compounds using the acquired bioactive peptides as a training set. Such generative techniques would be significant for drug development since peptides are much easier and cheaper to synthesize than compounds. Despite the limited availability of deep learning-based peptide-generating models, we have built an LSTM model (called LSTM_Pep) to generate de novo peptides and fine-tuned the model to generate de novo peptides with specific prospective therapeutic benefits. Remarkably, the Antimicrobial Peptide Database has been effectively utilized to generate various kinds of potential active de novo peptides. We proposed a pipeline for screening those generated peptides for a given target and used the main protease of SARS-COV-2 as a proof-of-concept. Moreover, we have developed a deep learning-based protein-peptide prediction model (DeepPep) for rapid screening of the generated peptides for the given targets. Together with the generating model, we have demonstrated that iteratively fine-tuning training, generating, and screening peptides for higher-predicted binding affinity peptides can be achieved. Our work sheds light on developing deep learning-based methods and pipelines to effectively generate and obtain bioactive peptides with a specific therapeutic effect and showcases how artificial intelligence can help discover de novo bioactive peptides that can bind to a particular target.
Collapse
Affiliation(s)
- Haiping Zhang
- Shenzhen Institute of Synthetic Biology, Faculty of Synthetic Biology, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, Guangdong, China
| | - Konda Mani Saravanan
- Department of Biotechnology, Bharath Institute of Higher Education and Research, Chennai 600073, Tamil Nadu, India
| | - Yanjie Wei
- Center for High Performance Computing, Joint Engineering Research Center for Health Big Data Intelligent Analysis Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, Guangdong, China
| | - Yang Jiao
- Faculty of Computer Science and Control Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
| | - Yang Yang
- Shenzhen Key Laboratory of Pathogen and Immunity, National Clinical Research Center for infectious disease, State Key Discipline of Infectious Disease, Shenzhen Third People's Hospital, Second Hospital Affiliated to Southern University of Science and Technology, Shenzhen 518112, China
| | - Yi Pan
- Center for High Performance Computing, Joint Engineering Research Center for Health Big Data Intelligent Analysis Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, Guangdong, China.,Faculty of Computer Science and Control Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
| | - Xuli Wu
- School of Medicine, Shenzhen University, Shenzhen 518060, Guangdong, China
| | - John Z H Zhang
- Shenzhen Institute of Synthetic Biology, Faculty of Synthetic Biology, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, Guangdong, China.,East China Normal University, Shanghai 200062, China.,NYU-ECNU Center for Computational Chemistry at NYU Shanghai, Shanghai 200062, China
| |
Collapse
|
16
|
Zhu F. Amaranth proteins and peptides: Biological properties and food uses. Food Res Int 2023; 164:112405. [PMID: 36738021 DOI: 10.1016/j.foodres.2022.112405] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/27/2022] [Revised: 12/16/2022] [Accepted: 12/24/2022] [Indexed: 12/31/2022]
Abstract
Amaranthus grains have attracted great attention due to its attractive health benefits. The grains have processing properties (e.g., starch related properties) similar to those of common cereals. Amaranth grains are gluten free and protein is a significant component of these grains. Proteins of the grains have been used in various food applications such as formulations of edible films and emulsions for controlled release of bioactive compounds. The proteins have been hydrolyzed using different enzymes to produce peptides and hydrolysates, which showed a range of biological functions including anti-hypertensive and antioxidant activities among others. They have been formulated into staple foods including breads and pastas for improved nutritional quality. This review summarizes the recent advances of the last 5 years in understanding the biological functions and food applications of proteins, protein hydrolysates and peptides from the grains of different Amaranthus species. Limitations in the studies summarized are critically discussed with an aim to improve the efficiency in amaranth grain protein and peptide research.
Collapse
Affiliation(s)
- Fan Zhu
- School of Chemical Sciences, The University of Auckland, Private Bag 92019, Auckland 1142, New Zealand.
| |
Collapse
|
17
|
Ghaly G, Tallima H, Dabbish E, Badr ElDin N, Abd El-Rahman MK, Ibrahim MAA, Shoeib T. Anti-Cancer Peptides: Status and Future Prospects. Molecules 2023; 28:molecules28031148. [PMID: 36770815 PMCID: PMC9920184 DOI: 10.3390/molecules28031148] [Citation(s) in RCA: 11] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2022] [Revised: 12/26/2022] [Accepted: 01/19/2023] [Indexed: 01/26/2023] Open
Abstract
The dramatic rise in cancer incidence, alongside treatment deficiencies, has elevated cancer to the second-leading cause of death globally. The increasing morbidity and mortality of this disease can be traced back to a number of causes, including treatment-related side effects, drug resistance, inadequate curative treatment and tumor relapse. Recently, anti-cancer bioactive peptides (ACPs) have emerged as a potential therapeutic choice within the pharmaceutical arsenal due to their high penetration, specificity and fewer side effects. In this contribution, we present a general overview of the literature concerning the conformational structures, modes of action and membrane interaction mechanisms of ACPs, as well as provide recent examples of their successful employment as targeting ligands in cancer treatment. The use of ACPs as a diagnostic tool is summarized, and their advantages in these applications are highlighted. This review expounds on the main approaches for peptide synthesis along with their reconstruction and modification needed to enhance their therapeutic effect. Computational approaches that could predict therapeutic efficacy and suggest ACP candidates for experimental studies are discussed. Future research prospects in this rapidly expanding area are also offered.
Collapse
Affiliation(s)
- Gehane Ghaly
- Department of Chemistry, The American University in Cairo, New Cairo 11835, Egypt
| | - Hatem Tallima
- Department of Chemistry, The American University in Cairo, New Cairo 11835, Egypt
| | - Eslam Dabbish
- Department of Chemistry, The American University in Cairo, New Cairo 11835, Egypt
| | - Norhan Badr ElDin
- Analytical Chemistry Department, Faculty of Pharmacy, Cairo University, Kasr-El Aini Street, Cairo 11562, Egypt
| | - Mohamed K. Abd El-Rahman
- Analytical Chemistry Department, Faculty of Pharmacy, Cairo University, Kasr-El Aini Street, Cairo 11562, Egypt
- Department of Chemistry and Chemical Biology, Harvard University, 12 Oxford Street, Cambridge, MA 02138, USA
| | - Mahmoud A. A. Ibrahim
- Computational Chemistry Laboratory, Chemistry Department, Faculty of Science, Minia University, Minia 61519, Egypt
- School of Health Sciences, University of Kwa-Zulu-Natal, Westville, Durban 4000, South Africa
| | - Tamer Shoeib
- Department of Chemistry, The American University in Cairo, New Cairo 11835, Egypt
- Correspondence:
| |
Collapse
|
18
|
Garai S, Thomas J, Dey P, Das D. LGBM-ACp: an ensemble model for anticancer peptide prediction and in silico screening with potential drug targets. Mol Divers 2023:10.1007/s11030-023-10602-0. [PMID: 36637711 DOI: 10.1007/s11030-023-10602-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2022] [Accepted: 01/06/2023] [Indexed: 01/14/2023]
Abstract
Conventional cancer therapies are highly expensive and have serious complications. An alternative approach now emphasizes on the development of small, biologically active peptides without acute toxicity. Experimental screening to find curative anticancer peptides (ACP) often gives rise to multiple obstacles and is time dependent. Consequently, developing an effective computational technique to identify promising ACP candidates prior to preclinical research is in high demand. This study proposed a machine-learning framework that used the light gradient-boosting machine as a classifier and two compositional and two binary profile features as input. The ensemble model displayed an accuracy, MCC, and AUROC of 97.52%, 0.91, and 0.98, respectively, which outclassed most of the existing sequence-based computational tools. A distinct dataset of non-mutagenic, non-toxic, and non-inhibitory Cytochrome P-450 peptides was used to validate the hybrid model. The most relevant ACP in the alternative dataset was compared with two standard ACPs, beta defensin 2, and cecropin-A. Molecular docking of the predicted peptide revealed that it has a strong binding affinity with twenty-five anticancer drug targets, most notably phosphoenolpyruvate carboxykinase (- 7.2 kcal/mol). Additionally, molecular dynamics simulation and principal component analysis supported the stability of the peptide-receptor complex. Overall, the present findings will take a step forward in rational drug design through rapid identification and screening of therapeutic peptides.
Collapse
Affiliation(s)
- Swarnava Garai
- Department of Bioengineering, NIT Agartala, Tripura, 799046, India
| | - Juanit Thomas
- Department of Bioengineering, NIT Agartala, Tripura, 799046, India
| | - Palash Dey
- Civil Engineering Department, The ICFAI University, Tripura, 799210, India
| | - Deeplina Das
- Department of Bioengineering, NIT Agartala, Tripura, 799046, India.
| |
Collapse
|
19
|
Kordi M, Borzouyi Z, Chitsaz S, Asmaei MH, Salami R, Tabarzad M. Antimicrobial peptides with anticancer activity: Today status, trends and their computational design. Arch Biochem Biophys 2023; 733:109484. [PMID: 36473507 DOI: 10.1016/j.abb.2022.109484] [Citation(s) in RCA: 11] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/25/2022] [Revised: 11/29/2022] [Accepted: 11/30/2022] [Indexed: 12/12/2022]
Abstract
Some antimicrobial peptides have been shown to be able to inhibit the proliferation of cancer cell lines. Various strategies for treating cancers with active peptides have been pursued. According to the reports, anticancer peptides are important therapeutic peptides, which can act through two distinct pathways: they either just create pores in the cell membrane, or they have a vital intracellular target. In this review, publications up to Sep. 2021 had extracted form Scopus and PubMed using "antimicrobial peptide" and "anticancer peptide" as keywords. In second step, "computational design" related publications extracted. Among publications, those have similar scopes were classified and selected based on mechanisms of action and application. In this review, the most recent advances in the field of antimicrobial peptides with anti-cancer activities have been summarized. Freely available webservers such as AntiCP, ACPP, iACP, iACP-GAEnsC, ACPred are discussed here. In conclusion, despite some limitations of ACPs such as production cost and challenges, short half-life and toxicity on normal cells, the beneficial properties of AMPs make some of them good therapeutic agents for cancer therapy. Towards designing novel ACPs, the computational methods have substantial position and have been used progressively, today.
Collapse
Affiliation(s)
- Masoumeh Kordi
- Department of Plant Science and Biotechnology, School of Life Sciences and Biotechnology, Shahid Beheshti University, Tehran, Iran.
| | - Zeynab Borzouyi
- Department of Agriculture, School of Agriculture and Plant Breeding, Islamic Azad University, Sabzevar, Iran
| | - Saideh Chitsaz
- Department of Microbiology, Islamic Azad University, Karaj, Iran
| | | | - Robab Salami
- Department of Plant Science and Biotechnology, School of Life Sciences and Biotechnology, Shahid Beheshti University, Tehran, Iran
| | - Maryam Tabarzad
- Protein Technology Research Center, Shahid Beheshti University of Medical Science, Iran.
| |
Collapse
|
20
|
Thi Phan L, Woo Park H, Pitti T, Madhavan T, Jeon YJ, Manavalan B. MLACP 2.0: An updated machine learning tool for anticancer peptide prediction. Comput Struct Biotechnol J 2022; 20:4473-4480. [PMID: 36051870 PMCID: PMC9421197 DOI: 10.1016/j.csbj.2022.07.043] [Citation(s) in RCA: 21] [Impact Index Per Article: 10.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2022] [Revised: 07/25/2022] [Accepted: 07/25/2022] [Indexed: 12/24/2022] Open
Abstract
We present a novel meta-approach, MLACP 2.0, and implement it as a user-friendly webserver for the accurate identification of ACPs. MLACP 2.0 employed 11 different encoding schemes and eight different classifiers, including convolutional neural networks, to create a stable meta-model. Benchmarking study has demonstrated that MLACP 2.0 achieves superior performance in ACP prediction compared to publicly available state-of-the-art predictors.
Anticancer peptides are emerging anticancer drug that offers fewer side effects and is more effective than chemotherapy and targeted therapy. Predicting anticancer peptides from sequence information is one of the most challenging tasks in immunoinformatics. In the past ten years, machine learning-based approaches have been proposed for identifying ACP activity from peptide sequences. These methods include our previous method MLACP (developed in 2017) which made a significant impact on anticancer research. MLACP tool has been widely used by the research community, however, its robustness must be improved significantly for its continued practical application. In this study, the first large non-redundant training and independent datasets were constructed for ACP research. Using the training dataset, the study explored a wide range of feature encodings and developed their respective models using seven different conventional classifiers. Subsequently, a subset of encoding-based models was selected for each classifier based on their performance, whose predicted scores were concatenated and trained through a convolutional neural network (CNN), whose corresponding predictor is named MLACP 2.0. The evaluation of MLACP 2.0 with a very diverse independent dataset showed excellent performance and significantly outperformed the recent ACP prediction tools. Additionally, MLACP 2.0 exhibits superior performance during cross-validation and independent assessment when compared to CNN-based embedding models and conventional single models. Consequently, we anticipate that our proposed MLACP 2.0 will facilitate the design of hypothesis-driven experiments by making it easier to discover novel ACPs. The MLACP 2.0 is freely available at https://balalab-skku.org/mlacp2.
Collapse
|
21
|
Agüero-Chapin G, Galpert-Cañizares D, Domínguez-Pérez D, Marrero-Ponce Y, Pérez-Machado G, Teijeira M, Antunes A. Emerging Computational Approaches for Antimicrobial Peptide Discovery. Antibiotics (Basel) 2022; 11:antibiotics11070936. [PMID: 35884190 PMCID: PMC9311958 DOI: 10.3390/antibiotics11070936] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2022] [Revised: 07/01/2022] [Accepted: 07/08/2022] [Indexed: 02/05/2023] Open
Abstract
In the last two decades many reports have addressed the application of artificial intelligence (AI) in the search and design of antimicrobial peptides (AMPs). AI has been represented by machine learning (ML) algorithms that use sequence-based features for the discovery of new peptidic scaffolds with promising biological activity. From AI perspective, evolutionary algorithms have been also applied to the rational generation of peptide libraries aimed at the optimization/design of AMPs. However, the literature has scarcely dedicated to other emerging non-conventional in silico approaches for the search/design of such bioactive peptides. Thus, the first motivation here is to bring up some non-standard peptide features that have been used to build classical ML predictive models. Secondly, it is valuable to highlight emerging ML algorithms and alternative computational tools to predict/design AMPs as well as to explore their chemical space. Another point worthy of mention is the recent application of evolutionary algorithms that actually simulate sequence evolution to both the generation of diversity-oriented peptide libraries and the optimization of hit peptides. Last but not least, included here some new considerations in proteogenomic analyses currently incorporated into the computational workflow for unravelling AMPs in natural sources.
Collapse
Affiliation(s)
- Guillermin Agüero-Chapin
- CIIMAR—Centro Interdisciplinar de Investigação Marinha e Ambiental, Universidade do Porto, Terminal de Cruzeiros do Porto de Leixões, Av. General Norton de Matos, s/n, 4450-208 Porto, Portugal;
- Departamento de Biologia, Faculdade de Ciências, Universidade do Porto, Rua do Campo Alegre, 4169-007 Porto, Portugal
- Correspondence: (G.A.-C.); (A.A.); Tel.: +351-22-340-1813 (G.A.-C. & A.A.)
| | - Deborah Galpert-Cañizares
- Departamento de Ciencia de la Computación, Universidad Central Marta Abreu de Las Villas (UCLV), Santa Clara 54830, Cuba;
| | - Dany Domínguez-Pérez
- CIIMAR—Centro Interdisciplinar de Investigação Marinha e Ambiental, Universidade do Porto, Terminal de Cruzeiros do Porto de Leixões, Av. General Norton de Matos, s/n, 4450-208 Porto, Portugal;
- Proquinorte, Unipessoal, Lda, Avenida 5 de Outubro, 124, 7º Piso, Avenidas Novas, 1050-061 Lisboa, Portugal
| | - Yovani Marrero-Ponce
- Universidad San Francisco de Quito (USFQ), Grupo de Medicina Molecular y Translacional (MeM&T), Colegio de Ciencias de la Salud (COCSA), Escuela de Medicina, Edificio de Especialidades Médicas and Instituto de Simulación Computacional (ISC-USFQ), Diego de Robles y vía Interoceánica, Quito 170157, Ecuador;
| | - Gisselle Pérez-Machado
- EpiDisease S.L—Spin-Off of Centro de Investigación Biomédica en Red de Enfermedades Raras (CIBERER), 46980 Valencia, Spain;
| | - Marta Teijeira
- Departamento de Química Orgánica, Facultade de Química, Universidade de Vigo, 36310 Vigo, Spain;
- Instituto de Investigación Sanitaria Galicia Sur, Hospital Álvaro Cunqueiro, 36213 Vigo, Spain
| | - Agostinho Antunes
- CIIMAR—Centro Interdisciplinar de Investigação Marinha e Ambiental, Universidade do Porto, Terminal de Cruzeiros do Porto de Leixões, Av. General Norton de Matos, s/n, 4450-208 Porto, Portugal;
- Departamento de Biologia, Faculdade de Ciências, Universidade do Porto, Rua do Campo Alegre, 4169-007 Porto, Portugal
- Correspondence: (G.A.-C.); (A.A.); Tel.: +351-22-340-1813 (G.A.-C. & A.A.)
| |
Collapse
|
22
|
Yu J, Wang D, Zheng M. Uncertainty quantification: Can we trust artificial intelligence in drug discovery? iScience 2022; 25:104814. [PMID: 35996575 PMCID: PMC9391523 DOI: 10.1016/j.isci.2022.104814] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022] Open
Abstract
The problem of human trust is one of the most fundamental problems in applied artificial intelligence in drug discovery. In silico models have been widely used to accelerate the process of drug discovery in recent years. However, most of these models can only give reliable predictions within a limited chemical space that the training set covers (applicability domain). Predictions of samples falling outside the applicability domain are unreliable and sometimes dangerous for the drug-design decision-making process. Uncertainty quantification accordingly has drawn great attention to enable autonomous drug designing. By quantifying the confidence level of model predictions, the reliability of the predictions can be quantitatively represented to assist researchers in their molecular reasoning and experimental design. Here we summarize the state-of-the-art approaches to uncertainty quantification and underline how they can be used for drug design and discovery projects. Furthermore, we also outline four representative application scenarios of uncertainty quantification in drug discovery.
Collapse
|
23
|
Otović E, Njirjak M, Kalafatovic D, Mauša G. Sequential Properties Representation Scheme for Recurrent Neural Network-Based Prediction of Therapeutic Peptides. J Chem Inf Model 2022; 62:2961-2972. [PMID: 35704881 DOI: 10.1021/acs.jcim.2c00526] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
The discovery of therapeutic peptides is often accelerated by means of virtual screening supported by machine learning-based predictive models. The predictive performance of such models is sensitive to the choice of data and its representation scheme. While the peptide physicochemical and compositional representations fail to distinguish sequence permutations, the amino acid arrangement within the sequence lacks the important information contained in physicochemical, conformational, topological, and geometrical properties. In this paper, we propose a solution to the identified information gap by implementing a hybrid scheme that complements the best traits from both approaches with the aim of predicting antimicrobial and antiviral activities based on experimental data from DRAMP 2.0, AVPdb, and Uniprot data repositories. Using the Friedman test of statistical significance, we compared our hybrid, sequential properties approach to peptide properties, one-hot vector encoding, and word embedding schemes in the 10-fold cross-validation setting, with respect to the F1 score, Matthews correlation coefficient, geometric mean, recall, and precision evaluation metrics. Moreover, the sequence modeling neural network was employed to gain insight into the synergic effect of both properties- and amino acid order-based predictions. The results suggest that sequential properties significantly (P < 0.01) surpasses the aforementioned state-of-the-art representation schemes. This makes it a strong candidate for increasing the predictive power of screening methods based on machine learning, applicable to any category of peptides.
Collapse
Affiliation(s)
- Erik Otović
- University of Rijeka, Faculty of Engineering, 51000 Rijeka, Croatia
| | - Marko Njirjak
- University of Rijeka, Faculty of Engineering, 51000 Rijeka, Croatia
| | - Daniela Kalafatovic
- University of Rijeka, Department of Biotechnology, 51000 Rijeka, Croatia.,University of Rijeka, Center for Artificial Intelligence and Cybersecurity, 51000 Rijeka, Croatia
| | - Goran Mauša
- University of Rijeka, Faculty of Engineering, 51000 Rijeka, Croatia.,University of Rijeka, Center for Artificial Intelligence and Cybersecurity, 51000 Rijeka, Croatia
| |
Collapse
|
24
|
Yan J, Zhang B, Zhou M, Kwok HF, Siu SWI. Multi-Branch-CNN: Classification of ion channel interacting peptides using multi-branch convolutional neural network. Comput Biol Med 2022; 147:105717. [PMID: 35752114 DOI: 10.1016/j.compbiomed.2022.105717] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2022] [Revised: 05/18/2022] [Accepted: 06/05/2022] [Indexed: 11/03/2022]
Abstract
Ligand peptides that have high affinity for ion channels are critical for regulating ion flux across the plasma membrane. These peptides are now being considered as potential drug candidates for many diseases, such as cardiovascular disease and cancers. In this work, we developed Multi-Branch-CNN, a CNN method with multiple input branches for identifying three types of ion channel peptide binders (sodium, potassium, and calcium) from intra- and inter-feature types. As for its real-world applications, prediction models that are able to recognize novel sequences having high or low similarities to training sequences are required. To this end, we tested our models on two test sets: a general test set including sequences spanning different similarity levels to those of the training set, and a novel-test set consisting of only sequences that bear little resemblance to sequences from the training set. Our experiments showed that the Multi-Branch-CNN method performs better than thirteen traditional ML algorithms (TML13), yielding an improvement in accuracy of 3.2%, 1.2%, and 2.3% on the test sets as well as 8.8%, 14.3%, and 14.6% on the novel-test sets for sodium, potassium, and calcium ion channels, respectively. We confirmed the effectiveness of Multi-Branch-CNN by comparing it to the standard CNN method with one input branch (Single-Branch-CNN) and an ensemble method (TML13-Stack). The data sets, script files to reproduce the experiments, and the final predictive models are freely available at https://github.com/jieluyan/Multi-Branch-CNN.
Collapse
Affiliation(s)
- Jielu Yan
- PAMI Research Group, Department of Computer and Information Science, University of Macau, Taipa, Macao Special Administrative Region of China
| | - Bob Zhang
- PAMI Research Group, Department of Computer and Information Science, University of Macau, Taipa, Macao Special Administrative Region of China.
| | - Mingliang Zhou
- School of Computer Science, Chongqing University, Shapingba, Chongqing, China
| | - Hang Fai Kwok
- Department of Biomedical Sciences, Faculty of Health Sciences, University of Macau, Taipa, Macao Special Administrative Region of China.
| | - Shirley W I Siu
- Department of Computer and Information Science, University of Macau, Taipa, Macao Special Administrative Region of China; Institute of Science and Environment, University of Saint Joseph, Estr. Marginal da Ilha Verde, Macao Special Administrative Region of China.
| |
Collapse
|
25
|
Lou C, Yang H, Wang J, Huang M, Li W, Liu G, Lee PW, Tang Y. IDL-PPBopt: A Strategy for Prediction and Optimization of Human Plasma Protein Binding of Compounds via an Interpretable Deep Learning Method. J Chem Inf Model 2022; 62:2788-2799. [PMID: 35607907 DOI: 10.1021/acs.jcim.2c00297] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/29/2023]
Abstract
The prediction and optimization of pharmacokinetic properties are essential in lead optimization. Traditional strategies mainly depend on the empirical chemical rules from medicinal chemists. However, with the rising amount of data, it is getting more difficult to manually extract useful medicinal chemistry knowledge. To this end, we introduced IDL-PPBopt, a computational strategy for predicting and optimizing the plasma protein binding (PPB) property based on an interpretable deep learning method. At first, a curated PPB data set was used to construct an interpretable deep learning model, which showed excellent predictive performance with a root mean squared error of 0.112 for the entire test set. Then, we designed a detection protocol based on the model and Wilcoxon test to identify the PPB-related substructures (named privileged substructures, PSubs) for each molecule. In total, 22 general privileged substructures (GPSubs) were identified, which shared some common features such as nitrogen-containing groups, diamines with two carbon units, and azetidine. Furthermore, a series of second-level chemical rules for each GPSub were derived through a statistical test and then summarized into substructure pairs. We demonstrated that these substructure pairs were equally applicable outside the training set and accordingly customized the structural modification schemes for each GPSub, which provided alternatives for the optimization of the PPB property. Therefore, IDL-PPBopt provides a promising scheme for the prediction and optimization of the PPB property and would be helpful for lead optimization of other pharmacokinetic properties.
Collapse
Affiliation(s)
- Chaofeng Lou
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, School of Pharmacy, East China University of Science and Technology, Shanghai 200237, China
| | - Hongbin Yang
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, School of Pharmacy, East China University of Science and Technology, Shanghai 200237, China
| | - Jiye Wang
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, School of Pharmacy, East China University of Science and Technology, Shanghai 200237, China
| | - Mengting Huang
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, School of Pharmacy, East China University of Science and Technology, Shanghai 200237, China
| | - Weihua Li
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, School of Pharmacy, East China University of Science and Technology, Shanghai 200237, China
| | - Guixia Liu
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, School of Pharmacy, East China University of Science and Technology, Shanghai 200237, China
| | - Philip W Lee
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, School of Pharmacy, East China University of Science and Technology, Shanghai 200237, China
| | - Yun Tang
- Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism, School of Pharmacy, East China University of Science and Technology, Shanghai 200237, China
| |
Collapse
|
26
|
Gupta S, Azadvari N, Hosseinzadeh P. Design of Protein Segments and Peptides for Binding to Protein Targets. BIODESIGN RESEARCH 2022; 2022:9783197. [PMID: 37850124 PMCID: PMC10521657 DOI: 10.34133/2022/9783197] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2021] [Accepted: 03/16/2022] [Indexed: 10/19/2023] Open
Abstract
Recent years have witnessed a rise in methods for accurate prediction of structure and design of novel functional proteins. Design of functional protein fragments and peptides occupy a small, albeit unique, space within the general field of protein design. While the smaller size of these peptides allows for more exhaustive computational methods, flexibility in their structure and sparsity of data compared to proteins, as well as presence of noncanonical building blocks, add additional challenges to their design. This review summarizes the current advances in the design of protein fragments and peptides for binding to targets and discusses the challenges in the field, with an eye toward future directions.
Collapse
Affiliation(s)
- Suchetana Gupta
- Knight Campus Center for Accelerating Scientific Impact, University of Oregon, Eugene OR 97403, USA
| | - Noora Azadvari
- Knight Campus Center for Accelerating Scientific Impact, University of Oregon, Eugene OR 97403, USA
| | - Parisa Hosseinzadeh
- Knight Campus Center for Accelerating Scientific Impact, University of Oregon, Eugene OR 97403, USA
| |
Collapse
|
27
|
Breast and Lung Anticancer Peptides Classification Using N-Grams and Ensemble Learning Techniques. BIG DATA AND COGNITIVE COMPUTING 2022. [DOI: 10.3390/bdcc6020040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
Anticancer peptides (ACPs) are short protein sequences; they perform functions like some hormones and enzymes inside the body. The role of any protein or peptide is related to its structure and the sequence of amino acids that make up it. There are 20 types of amino acids in humans, and each of them has a particular characteristic according to its chemical structure. Current machine and deep learning models have been used to classify ACPs problems. However, these models have neglected Amino Acid Repeats (AARs) that play an essential role in the function and structure of peptides. Therefore, in this paper, ACPs offer a promising route for novel anticancer peptides by extracting AARs based on N-Grams and k-mers using two peptides’ datasets. These datasets pointed to breast and lung cancer cells assembled and curated manually from the Cancer Peptide and Protein Database (CancerPPD). Every dataset consists of a sequence of peptides and their synthesis and anticancer activity on breast and lung cancer cell lines. Five different feature selection methods were used in this paper to improve classification performance and reduce the experimental costs. After that, ACPs were classified using four classifiers, namely AdaBoost, Random Forest Tree (RFT), Multi-class Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP). These classifiers were evaluated by applying five well-known evaluation metrics. Experimental results showed that the breast and lung ACPs classification process provided an accurate performance that reached 89.25% and 92.56%, respectively. In terms of AUC, it reached 95.35% and 96.92% for both breast and lung ACPs, respectively. The proposed classifiers performed competently somewhat equally in AUC, accuracy, precision, F-measures, and recall, except for Multi-class SVM-based feature selection, which showed superior performance. As a result, this paper significantly improved the predictive performance that can effectively distinguish ACPs as virtual inactive, experimental inactive, moderately active, and very active.
Collapse
|