1
|
Rathore AS, Choudhury S, Arora A, Tijare P, Raghava GPS. ToxinPred 3.0: An improved method for predicting the toxicity of peptides. Comput Biol Med 2024; 179:108926. [PMID: 39038391 DOI: 10.1016/j.compbiomed.2024.108926] [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: 08/24/2023] [Revised: 05/17/2024] [Accepted: 07/17/2024] [Indexed: 07/24/2024]
Abstract
Toxicity emerges as a prominent challenge in the design of therapeutic peptides, causing the failure of numerous peptides during clinical trials. In 2013, our group developed ToxinPred, a computational method that has been extensively adopted by the scientific community for predicting peptide toxicity. In this paper, we propose a refined variant of ToxinPred that showcases improved reliability and accuracy in predicting peptide toxicity. Initially, we utilized a similarity/alignment-based approach employing BLAST to predict toxic peptides, which yielded satisfactory accuracy; however, the method suffered from inadequate coverage. Subsequently, we employed a motif-based approach using MERCI software to uncover specific patterns or motifs that are exclusively observed in toxic peptides. The search for these motifs in peptides allowed us to predict toxic peptides with a high level of specificity with poor sensitivity. To overcome the coverage limitations, we developed alignment-free methods using machine/deep learning techniques to balance sensitivity and specificity of prediction. Deep learning model (ANN - LSTM with fixed sequence length) developed using one-hot encoding achieved a maximum AUROC of 0.93 with MCC of 0.71 on an independent dataset. Machine learning model (extra tree) developed using compositional features of peptides achieved a maximum AUROC of 0.95 with MCC of 0.78. We also developed large language models and achieved maximum AUC of 0.93 using ESM2-t33. Finally, we developed hybrid or ensemble methods combining two or more methods to enhance performance. Our specific hybrid method, which combines a motif-based approach with a machine learning-based model, achieved a maximum AUROC of 0.98 with MCC 0.81 on an independent dataset. In this study, all models were trained and tested on 80 % of data using five-fold cross-validation and evaluated on the remaining 20 % of data called independent dataset. The evaluation of all methods on an independent dataset revealed that the method proposed in this study exhibited better performance than existing methods. To cater to the needs of the scientific community, we have developed a standalone software, pip package and web-based server ToxinPred3 (https://github.com/raghavagps/toxinpred3 and https://webs.iiitd.edu.in/raghava/toxinpred3/).
Collapse
Affiliation(s)
- Anand Singh Rathore
- Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi, 110020, India.
| | - Shubham Choudhury
- Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi, 110020, India.
| | - Akanksha Arora
- Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi, 110020, India.
| | - Purva Tijare
- Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi, 110020, India.
| | - Gajendra P S Raghava
- Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi, 110020, India.
| |
Collapse
|
2
|
Rusic D, Kumric M, Seselja Perisin A, Leskur D, Bukic J, Modun D, Vilovic M, Vrdoljak J, Martinovic D, Grahovac M, Bozic J. Tackling the Antimicrobial Resistance "Pandemic" with Machine Learning Tools: A Summary of Available Evidence. Microorganisms 2024; 12:842. [PMID: 38792673 PMCID: PMC11123121 DOI: 10.3390/microorganisms12050842] [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: 03/16/2024] [Revised: 04/16/2024] [Accepted: 04/19/2024] [Indexed: 05/26/2024] Open
Abstract
Antimicrobial resistance is recognised as one of the top threats healthcare is bound to face in the future. There have been various attempts to preserve the efficacy of existing antimicrobials, develop new and efficient antimicrobials, manage infections with multi-drug resistant strains, and improve patient outcomes, resulting in a growing mass of routinely available data, including electronic health records and microbiological information that can be employed to develop individualised antimicrobial stewardship. Machine learning methods have been developed to predict antimicrobial resistance from whole-genome sequencing data, forecast medication susceptibility, recognise epidemic patterns for surveillance purposes, or propose new antibacterial treatments and accelerate scientific discovery. Unfortunately, there is an evident gap between the number of machine learning applications in science and the effective implementation of these systems. This narrative review highlights some of the outstanding opportunities that machine learning offers when applied in research related to antimicrobial resistance. In the future, machine learning tools may prove to be superbugs' kryptonite. This review aims to provide an overview of available publications to aid researchers that are looking to expand their work with new approaches and to acquaint them with the current application of machine learning techniques in this field.
Collapse
Affiliation(s)
- Doris Rusic
- Department of Pharmacy, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia; (D.R.); (A.S.P.); (D.L.); (J.B.); (D.M.)
| | - Marko Kumric
- Department of Pathophysiology, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia; (M.K.); (M.V.); (J.V.); (D.M.)
- Laboratory for Cardiometabolic Research, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia
| | - Ana Seselja Perisin
- Department of Pharmacy, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia; (D.R.); (A.S.P.); (D.L.); (J.B.); (D.M.)
| | - Dario Leskur
- Department of Pharmacy, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia; (D.R.); (A.S.P.); (D.L.); (J.B.); (D.M.)
| | - Josipa Bukic
- Department of Pharmacy, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia; (D.R.); (A.S.P.); (D.L.); (J.B.); (D.M.)
| | - Darko Modun
- Department of Pharmacy, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia; (D.R.); (A.S.P.); (D.L.); (J.B.); (D.M.)
| | - Marino Vilovic
- Department of Pathophysiology, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia; (M.K.); (M.V.); (J.V.); (D.M.)
- Laboratory for Cardiometabolic Research, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia
| | - Josip Vrdoljak
- Department of Pathophysiology, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia; (M.K.); (M.V.); (J.V.); (D.M.)
- Laboratory for Cardiometabolic Research, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia
| | - Dinko Martinovic
- Department of Pathophysiology, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia; (M.K.); (M.V.); (J.V.); (D.M.)
- Department of Maxillofacial Surgery, University Hospital of Split, Spinciceva 1, 21000 Split, Croatia
| | - Marko Grahovac
- Department of Pharmacology, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia;
| | - Josko Bozic
- Department of Pathophysiology, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia; (M.K.); (M.V.); (J.V.); (D.M.)
- Laboratory for Cardiometabolic Research, University of Split School of Medicine, Soltanska 2A, 21000 Split, Croatia
| |
Collapse
|
3
|
Iwaniak A, Minkiewicz P, Darewicz M. Bioinformatics and bioactive peptides from foods: Do they work together? ADVANCES IN FOOD AND NUTRITION RESEARCH 2024; 108:35-111. [PMID: 38461003 DOI: 10.1016/bs.afnr.2023.09.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/11/2024]
Abstract
We live in the Big Data Era which affects many aspects of science, including research on bioactive peptides derived from foods, which during the last few decades have been a focus of interest for scientists. These two issues, i.e., the development of computer technologies and progress in the discovery of novel peptides with health-beneficial properties, are closely interrelated. This Chapter presents the example applications of bioinformatics for studying biopeptides, focusing on main aspects of peptide analysis as the starting point, including: (i) the role of peptide databases; (ii) aspects of bioactivity prediction; (iii) simulation of peptide release from proteins. Bioinformatics can also be used for predicting other features of peptides, including ADMET, QSAR, structure, and taste. To answer the question asked "bioinformatics and bioactive peptides from foods: do they work together?", currently it is almost impossible to find examples of peptide research with no bioinformatics involved. However, theoretical predictions are not equivalent to experimental work and always require critical scrutiny. The aspects of compatibility of in silico and in vitro results are also summarized herein.
Collapse
Affiliation(s)
- Anna Iwaniak
- Chair of Food Biochemistry, Faculty of Food Science, University of Warmia and Mazury in Olsztyn, Olsztyn-Kortowo, Poland.
| | - Piotr Minkiewicz
- Chair of Food Biochemistry, Faculty of Food Science, University of Warmia and Mazury in Olsztyn, Olsztyn-Kortowo, Poland
| | - Małgorzata Darewicz
- Chair of Food Biochemistry, Faculty of Food Science, University of Warmia and Mazury in Olsztyn, Olsztyn-Kortowo, Poland
| |
Collapse
|
4
|
Bajiya N, Choudhury S, Dhall A, Raghava GPS. AntiBP3: A Method for Predicting Antibacterial Peptides against Gram-Positive/Negative/Variable Bacteria. Antibiotics (Basel) 2024; 13:168. [PMID: 38391554 PMCID: PMC10885866 DOI: 10.3390/antibiotics13020168] [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: 12/26/2023] [Revised: 02/03/2024] [Accepted: 02/06/2024] [Indexed: 02/24/2024] Open
Abstract
Most of the existing methods developed for predicting antibacterial peptides (ABPs) are mostly designed to target either gram-positive or gram-negative bacteria. In this study, we describe a method that allows us to predict ABPs against gram-positive, gram-negative, and gram-variable bacteria. Firstly, we developed an alignment-based approach using BLAST to identify ABPs and achieved poor sensitivity. Secondly, we employed a motif-based approach to predict ABPs and obtained high precision with low sensitivity. To address the issue of poor sensitivity, we developed alignment-free methods for predicting ABPs using machine/deep learning techniques. In the case of alignment-free methods, we utilized a wide range of peptide features that include different types of composition, binary profiles of terminal residues, and fastText word embedding. In this study, a five-fold cross-validation technique has been used to build machine/deep learning models on training datasets. These models were evaluated on an independent dataset with no common peptide between training and independent datasets. Our machine learning-based model developed using the amino acid binary profile of terminal residues achieved maximum AUC 0.93, 0.98, and 0.94 for gram-positive, gram-negative, and gram-variable bacteria, respectively, on an independent dataset. Our method performs better than existing methods when compared with existing approaches on an independent dataset. A user-friendly web server, standalone package and pip package have been developed to facilitate peptide-based therapeutics.
Collapse
Affiliation(s)
- Nisha Bajiya
- Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi 110020, India
| | - Shubham Choudhury
- Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi 110020, India
| | - Anjali Dhall
- Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi 110020, India
| | - Gajendra P S Raghava
- Department of Computational Biology, Indraprastha Institute of Information Technology, Okhla Phase 3, New Delhi 110020, India
| |
Collapse
|
5
|
Charoenkwan P, Schaduangrat N, Mahmud SMH, Thinnukool O, Shoombuatong W. Recent development of machine learning-based methods for the prediction of defensin family and subfamily. EXCLI JOURNAL 2022; 21:757-771. [PMID: 35949489 PMCID: PMC9360473 DOI: 10.17179/excli2022-4913] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/05/2022] [Accepted: 05/03/2022] [Indexed: 11/05/2022]
Abstract
Nearly all living species comprise of host defense peptides called defensins, that are crucial for innate immunity. These peptides work by activating the immune system which kills the microbes directly or indirectly, thus providing protection to the host. Thus far, numerous preclinical and clinical trials for peptide-based drugs are currently being evaluated. Although, experimental methods can help to precisely identify the defensin peptide family and subfamily, these approaches are often time-consuming and cost-ineffective. On the other hand, machine learning (ML) methods are able to effectively employ protein sequence information without the knowledge of a protein's three-dimensional structure, thus highlighting their predictive ability for the large-scale identification. To date, several ML methods have been developed for the in silico identification of the defensin peptide family and subfamily. Therefore, summarizing the advantages and disadvantages of the existing methods is urgently needed in order to provide useful suggestions for the development and improvement of new computational models for the identification of the defensin peptide family and subfamily. With this goal in mind, we first provide a comprehensive survey on a collection of six state-of-the-art computational approaches for predicting the defensin peptide family and subfamily. Herein, we cover different important aspects, including the dataset quality, feature encoding methods, feature selection schemes, ML algorithms, cross-validation methods and web server availability/usability. Moreover, we provide our thoughts on the limitations of existing methods and future perspectives for improving the prediction performance and model interpretability. The insights and suggestions gained from this review are anticipated to serve as a valuable guidance for researchers for the development of more robust and useful predictors.
Collapse
Affiliation(s)
- Phasit Charoenkwan
- Modern Management and Information Technology, College of Arts, Media and Technology, Chiang Mai University, Chiang Mai, Thailand, 50200
| | - Nalini Schaduangrat
- Center of Data Mining and Biomedical Informatics, Faculty of Medical Technology, Mahidol University, Bangkok, Thailand, 10700
| | - S. M. Hasan Mahmud
- Center of Data Mining and Biomedical Informatics, Faculty of Medical Technology, Mahidol University, Bangkok, Thailand, 10700,Department of Computer Science, American International University-Bangladesh (AIUB), Kuratoli, Dhaka 1229, Bangladesh
| | - Orawit Thinnukool
- Modern Management and Information Technology, College of Arts, Media and Technology, Chiang Mai University, Chiang Mai, Thailand, 50200
| | - Watshara Shoombuatong
- Center of Data Mining and Biomedical Informatics, Faculty of Medical Technology, Mahidol University, Bangkok, Thailand, 10700,*To whom correspondence should be addressed: Watshara Shoombuatong, Center of Data Mining and Biomedical Informatics, Faculty of Medical Technology, Mahidol University, Bangkok, Thailand, 10700; Phone: +66 2 441 4371, Fax: +66 2 441 4380, E-mail:
| |
Collapse
|