Classifying Promoters by Interpreting the Hidden Information of DNA Sequences via Deep Learning and Combination of Continuous FastText N-Grams

Abstract

A promoter is a short region of DNA (100–1,000 bp) where transcription of a gene by RNA polymerase begins. It is typically located directly upstream or at the 5′ end of the transcription initiation site. DNA promoter has been proven to be the primary cause of many human diseases, especially diabetes, cancer, or Huntington's disease. Therefore, classifying promoters has become an interesting problem and it has attracted the attention of a lot of researchers in the bioinformatics field. There were a variety of studies conducted to resolve this problem, however, their performance results still require further improvement. In this study, we will present an innovative approach by interpreting DNA sequences as a combination of continuous FastText N-grams, which are then fed into a deep neural network in order to classify them. Our approach is able to attain a cross-validation accuracy of 85.41 and 73.1% in the two layers, respectively. Our results outperformed the state-of-the-art methods on the same dataset, especially in the second layer (strength classification). Throughout this study, promoter regions could be identified with high accuracy and it provides analysis for further biological research as well as precision medicine. In addition, this study opens new paths for the natural language processing application in omics data in general and DNA sequences in particular.

The methylation status of the chemerin promoter region located from − 252 to + 258 bp regulates constitutive but not acute-phase cytokine-inducible chemerin expression levels

“…We next investigated DNA methylation of the RARRES2 promoter region as a possible mechanism underlying differential 29 constitutive and regulated chemerin expression in various cell types. We studied DNA fragments ranged ranging in location from − 735 to + 258 bp of the RARRES2 gene because promoter sequences are typically defined as being 100 to 1,000 bp upstream of the transcription start site and 100 bp downstream of the transcription start site 30 . Moreover, this DNA region contains all the binding sites of previously characterized transcription factors (TFs) of RARRES2 18 – 20 .…”

MSU-Net: Multi-Scale U-Net for 2D Medical Image Segmentation

“…With the development of convolutional neural network (CNN) in the field of natural image processing and medical image analysis, automatic feature learning algorithm using deep learning has become a feasible method for biomedical image segmentation (Le et al, 2019 , 2020 ; Sua et al, 2020 ). Segmentation method based on deep learning is a learning method with pixel-classification, which is different from the traditional pixel or superpixel classification method (Abramoff et al, 2007 ; Kitrungrotsakul et al, 2015 ; Tian et al, 2015 ) using hand-made features.…”

Hepatocellular Carcinoma Automatic Diagnosis within CEUS and B-Mode Ultrasound Images Using Advanced Machine Learning Methods

“…Recently, the deep learning techniques, such as the Stacked Denoising Autoencoders (SAE) [ 20 ], the Deep Belief Networks (DBN), the Recurrent Neural Networks (RNN), respectively, the CNN-based classifiers, were successfully employed for automatic diagnosis within medical images [ 21 , 22 ]. They demonstrated their value in other fields, as well, such as bioinformatics [ 23 , 24 ], object detection and recognition [ 25 ], semantic segmentation of images [ 26 ]. CNN began to be utilized on a large scale when powerful computational resources, such as the parallel units or the Graphical Processing Units (GPU), appeared—their value being emphasized during the ImageNet competition in 2012.…”

“…The CNN-based methods also demonstrated their value in the field of bioinformatics. In [ 23 ], the authors described their methodology, aimed at classifying DNA promoters through the interpretation of the DNA sequences. They employed deep learning and appropriate text processing techniques for this purpose.…”