FAD-BERT: Improved prediction of FAD binding sites using pre-training of deep bidirectional transformers

Quang Thai Ho, Trinh Trung Duong Nguyen, Nguyen Quoc Khanh Le, Yu Yen Ou

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)

Abstract

The electron transport chain is a series of protein complexes embedded in the process of cellular respiration, which is an important process to transfer electrons and other macromolecules throughout the cell. Identifying Flavin Adenine Dinucleotide (FAD) binding sites in the electron transport chain is vital since it helps biological researchers precisely understand how electrons are produced and are transported in cells. This study distills and analyzes the contextualized word embedding from pre-trained BERT models to explore similarities in natural language and protein sequences. Thereby, we propose a new approach based on Pre-training of Bidirectional Encoder Representations from Transformers (BERT), Position-specific Scoring Matrix profiles (PSSM), Amino Acid Index database (AAIndex) to predict FAD-binding sites from the transport proteins which are found in nature recently. Our proposed approach archives 85.14% accuracy and improves accuracy by 11%, with Matthew's correlation coefficient of 0.39 compared to the previous method on the same independent set. We also deploy a web server that identifies FAD-binding sites in electron transporters available for academics at http://140.138.155.216/fadbert/.

Original languageEnglish
Article number104258
JournalComputers in Biology and Medicine
Volume131
DOIs
Publication statusPublished - Apr 2021

Keywords

  • BERT
  • Deep learning
  • Electron transport chain
  • FAD binding Site
  • Natural language processing
  • Position specific scoring matrix

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Fingerprint

Dive into the research topics of 'FAD-BERT: Improved prediction of FAD binding sites using pre-training of deep bidirectional transformers'. Together they form a unique fingerprint.

Cite this