A Comparative Analysis of Novel Deep Learning and Ensemble Learning Models to Predict the Allergenicity of Food Proteins

Abstract

Traditional food allergen identification mainly relies on in vivo and in vitro experiments, which often needs a long period and high cost. The artificial intelligence (AI)-driven rapid food allergen identification method has solved the above mentioned some drawbacks and is becoming an efficient auxiliary tool. Aiming to overcome the limitations of lower accuracy of traditional machine learning models in predicting the allergenicity of food proteins, this work proposed to introduce deep learning model—transformer with self-attention mechanism, ensemble learning models (representative as Light Gradient Boosting Machine (LightGBM) eXtreme Gradient Boosting (XGBoost)) to solve the problem. In order to highlight the superiority of the proposed novel method, the study also selected various commonly used machine learning models as the baseline classifiers. The results of 5-fold cross-validation showed that the area under the receiver operating characteristic curve (AUC) of the deep model was the highest (0.9578), which was better than the ensemble learning and baseline algorithms. But the deep model need to be pre-trained, and the training time is the longest. By comparing the characteristics of the transformer model and boosting models, it can be analyzed that, each model has its own advantage, which provides novel clues and inspiration for the rapid prediction of food allergens in the future.

Sequence-Based Prediction of Plant Allergenic Proteins: Machine Learning Classification Approach

“…Therefore, more attention has recently been given to bioinformatics and machine learning strategies as potential tools for detecting and classifying food allergens. Among the great variety of methods, intelligence neural networks, supervised learning, support vector machines with linear kernel functions, and different classifiers such as k -nearest neighbor are used as reliable options for identifying, modeling, and predicting allergenic properties. − Wang et al developed a new deep learning model (transformer with a self-attention mechanism combining the learning models Light Gradient Boosting Machine [LightGBM] and eXtreme Gradient Boosting [XGBoost]) for the prediction of food allergens. Machine learning is proving to be a tremendously helpful solution in this field.…”

Allergenicity evaluation of five types of commercial food-derived oligopeptide products

“…24 As the allergen database is being improved constantly, it is remarkable to underline that these silico tools do make allergen identification easier, especially for those newly found ones. 25,26 Recognizing the confusion about the safety of FDOPs, this paper evaluated the allergenicity of oligopeptides from soy, wheat, oyster, salmon skin and haddock skin based on the decision tree adapted by the FAO and WHO. These oligopeptides were selected for 2 reasons: firstly, they are all representative of allergenic foods, and secondly, their production technology is mature and they have been widely used in food and health products.…”

Automated Well-Log Pattern Alignment and Depth-Matching Techniques: An Empirical Review and Recommendations

“…Firstly, training these algorithms requires a large amount of data (which cannot always be guaranteed in geological problems [10]) and high-performance computing hardware which can contribute substantially to climate change [36]. To illustrate, despite being described as the best in natural language processing (NLP) tasks [11,39], the carbon dioxide emissions of training and applying a transformer (a type of deep neural networks) are even more substantial than the lifetime emissions of an automobile [36]. With calls from different quarters to decarbonise the energy system, within which the oil and gas industry has a significant role to play, the industry has to reconsider operations that can further contribute to global warming [42,24,34].…”