GT-Finder: Classify the family of glucose transporters with pre-trained BERT language models. (April 2021)

• Record Type: Journal Article
• Authors: Ali Shah, Syed Muazzam; Taju, Semmy Wellem; Ho, Quang-Thai; Nguyen, Trinh-Trung-Duong; Ou, Yu-Yen
• Is Part Of: Computers in biology and medicine. Volume 131(2021)
• Publication Date: 2021-04
• Subjects: BERT -- Contextualized word embedding -- Bidirectional encoder representations from transformers -- Glucose transporter -- Feature importance; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.104259
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Recently, language representation models have drawn a lot of attention in the field of natural language processing (NLP) due to their remarkable results. Among them, BERT (Bidirectional Encoder Representations from Transformers) has proven to be a simple, yet powerful language model that has achieved novel state-of-the-art performance. BERT adopted the concept of contextualized word embeddings to capture the semantics and context in which words appear. We utilized pre-trained BERT models to extract features from protein sequences for discriminating three families of glucose transporters: the major facilitator superfamily of glucose transporters (GLUTs), the sodium-glucose linked transporters (SGLTs), and the sugars will eventually be exported transporters (SWEETs). We treated protein sequences as sentences and transformed them into fixed-length meaningful vectors where a 768- or 1024-dimensional vector represents each amino acid. We observed that BERT-Base and BERT-Large models improved the performance by more than 4% in terms of average sensitivity and Matthews correlation coefficient (MCC), indicating the efficiency of this approach. We also developed a bidirectional transformer-based protein model (TransportersBERT) for comparison with existing pre-trained BERT models. Graphical abstract: Glucose transporters play an important role in cell signaling and serve as precursor for biomolecule synthesis. Therefore, interpreting the molecular functions of glucose transporters is an essential task for biologists. This study approached a revolutionary model that achieved state-of-the-art performance in Natural Language Processing (NLP), known as Bidirectional Encoder Representations from Transformers (BERT) to discriminate three families of glucose transporters (GLUT, SGLT, and SWEET). The promising results indicate the effectiveness of the proposed approach. Image 1 Highlights: Glucose is the primary source of energy for carrying out various activities in humans. Glucose transporters catalyze permeation of sugars into the cell along or against the concentration gradient. BERT is a state-of-the-art Natural Language Processing technique that generates contextual word embeddings. BERT enables the transfer of knowledge from a human language text corpus to protein sequence data. Results proved that BERT generates significant performance for classifying three families of glucose transporters.