 | This article relies largely or entirely on a single source. (October 2024) |
| Submission declined on 12 October 2024 by SafariScribe (talk). This submission is not adequately supported by reliable sources. Reliable sources are required so that information can be verified. If you need help with referencing, please see Referencing for beginners and Citing sources. This draft's references do not show that the subject qualifies for a Wikipedia article. In summary, the draft needs multiple published sources that are:
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
|  |
ALLERDET[1] is a web-based application developed for the prediction of protein allergenicity using machine learning techniques. It was introduced by Francisco M. García-Moreno and Miguel A. Gutiérrez-Naranjo in 2022. ALLERDET combines sequence alignment methods with deep learning models to achieve high sensitivity, specificity, and accuracy in predicting food allergens.
Background
editAllergic diseases are increasingly prevalent worldwide, particularly food allergies. The development of genetically modified crops has introduced new proteins into the human diet, raising concerns about potential allergens. Traditional methods for detecting allergens, such as the decision-tree schema recommended by the World Health Organization (WHO) and Food and Agriculture Organization (FAO), rely on sequence similarity, but they are often imprecise in terms of sensitivity and specificity.
Features
editALLERDET uses pairwise sequence alignment with the FASTA algorithm for feature extraction. It then employs deep learning techniques, particularly Restricted Boltzmann Machines (RBM), combined with decision trees to classify proteins as allergenic or non-allergenic. The model was trained using a large dataset of known allergens and non-allergens, achieving a balanced performance of over 98% in sensitivity, specificity, and accuracy.
Comparisons with Other Tools
editSeveral other allergen prediction tools exist, including:
- AllerCatPro: Achieves 84% accuracy in allergen prediction based on amino acid sequences and 3D protein structures.
- AllergenFP: Reaches 88% accuracy but struggles with balancing sensitivity and specificity.
- AllerTOP: Achieves 94% sensitivity but does not exceed 90% accuracy overall.
- AlgPred: Another well-known tool with lower performance metrics compared to ALLERDET.
Public Availability
editThe tool is publicly available for researchers and can be accessed via ALLERDET: http://allerdet.frangam.com/. It is designed to assist in the identification of food allergens, contributing to food safety and allergen research.
References
edit- ^ Garcia-Moreno, Francisco M.; Gutiérrez-Naranjo, Miguel A. (2022-11-01). "ALLERDET: A novel web app for prediction of protein allergenicity". Journal of Biomedical Informatics. 135: 104217. doi:10.1016/j.jbi.2022.104217. ISSN 1532-0464. PMID 36244612.