UmamiPreDL: Deep learning model for umami taste prediction of peptides using BERT and CNN

• Published in: Computational biology and chemistry 2024-08, Vol.111, p.108116, Article 108116
• Main Authors: Indiran, Arun Pandiyan, Fatima, Humaira, Chattopadhyay, Sampriti, Ramadoss, Sureshkumar, Radhakrishnan, Yashwanth
• Format: Article
• Language: English
• Subjects: Deep Learning; Humans; peptide; Peptides - chemistry; ProtBERT; Taste; taste prediction; Umami
• ISSN: 1476-9271; 1476-928X; 1476-928X
• DOI: 10.1016/j.compbiolchem.2024.108116

Taste is crucial in driving food choice and preference. Umami is one of the basic tastes defined by characteristic deliciousness and mouthfulness that it imparts to foods. Identification of ingredients to enhance umami taste is of significant value to food industry. Various models have been shown to predict umami taste using feature encodings derived from traditional molecular descriptors such as amphiphilic pseudo-amino acid composition, dipeptide composition, and composition-transition-distribution. Highest reported accuracy of 90.5 % was recently achieved through novel model architecture. Here, we propose use of biological sequence transformers such as ProtBert and ESM2, trained on the Uniref databases, as the feature encoders block. With combination of 2 encoders and 2 classifiers, 4 model architectures were developed. Among the 4 models, ProtBert-CNN model outperformed other models with accuracy of 95 % on 5-fold cross validation data and 94 % on independent data. [Display omitted] •Taste prediction models are of significant use to food industry.•High accuracy taste prediction helps in time and cost efficient screening.•Recent models predict umami taste using traditional molecular descriptors.•Proposed model uses physiologically relevant peptide sequences for umami prediction.•Proposed model shows highest reported accuracy of 94 % with 5 fold cross validation.