BERT contextual embeddings for taxonomic classification of bacterial DNA sequences

作者：

Highlights：

• Interactions and positions of biological components are significant.

• BERT Contextual Embeddings capture salient sequence interactions.

• Convolutional Neural Networks efficiently classify biological sequences.

• Data augmentation methods boost classification performance

摘要

•Interactions and positions of biological components are significant.•BERT Contextual Embeddings capture salient sequence interactions.•Convolutional Neural Networks efficiently classify biological sequences.•Data augmentation methods boost classification performance

论文关键词：DNA,Taxonomic classification,BERT,Contextual embedding,Deep Learning,Convolutional Neural Network

论文评审过程：Received 13 June 2021, Revised 7 May 2022, Accepted 22 June 2022, Available online 30 June 2022, Version of Record 16 July 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117972