Deep6mA: A deep learning framework for exploring similar patterns in DNA N6-methyladenine sites across different species

Abstract

N6-methyladenine (6mA) is an important DNA modification form associated with a wide range of biological processes. Identifying accurately 6mA sites on a genomic scale is crucial for under-standing of 6mA’s biological functions. However, the existing experimental techniques for detecting 6mA sites are cost-ineffective, which implies the great need of developing new computational methods for this problem. In this paper, we developed, without requiring any prior knowledge of 6mA and manually crafted sequence features, a deep learning framework named Deep6mA to identify DNA 6mA sites, and its performance is superior to other DNA 6mA prediction tools. Specifically, the 5-fold cross-validation on a benchmark dataset of rice gives the sensitivity and specificity of Deep6mA as 92.96% and 95.06%, respectively, and the overall prediction accuracy is 94%. Importantly, we find that the sequences with 6mA sites share similar patterns across different species. The model trained with rice data predicts well the 6mA sites of other three species: Arabidopsis thaliana, Fragaria vesca and Rosa chinensis with a prediction accuracy over 90%. In addition, we find that (1) 6mA tends to occur at GAGG motifs, which means the sequence near the 6mA site may be conservative; (2) 6mA is enriched in the TATA box of the promoter, which may be the main source of its regulating downstream gene expression.

DNA N6-Methyladenine Modification in Eukaryotic Genome

“…Compared with traditional laboratory experiments, bioinformatics tools have significant advantages in terms of price and time cost (Figure 1D). At present, there are many deep learning models used for predicting 6 mA, such as DNA6mA-MINT (Rehman and Chong, 2020), i6mA-stack (Khanal et al, 2021), SNNRice6mA (Yu and Dai, 2019), SMEP (Wang et al, 2021), Deep6mA (Li et al, 2021b), LA6mA, AL6mA (Zhang et al, 2021), GC6mA-Pred (Cai et al, 2022), Meta-i6mA (Hasan et al, 2021), and BERT6mA (Tsukiyama et al, 2022). Based on neural networks, Yu and Dai.…”

“…Other algorithms also have their characteristics. For example, Deep6mA presents an accuracy of more than 90% in predicting plants such as Arabidopsis (Li et al, 2021b). LA6mA and AL6mA capture location information from DNA sequences through a self-attention mechanism (Zhang et al, 2021).…”

6mAPred-MSFF: A Deep Learning Model for Predicting DNA N6-Methyladenine Sites across Species Based on a Multi-Scale Feature Fusion Mechanism

“…To demonstrate the effectiveness of the proposed method, we compared its performance with three other existing state-of-the-art methods, including MM-6mAPred [21], SNNRice6mA [33], and Deep6mA [34]. MM-6mAPred is traditional machine learning method training the model by hand-made features extracted from original DNA sequences.…”

“…Li et al developed a deep learning framework named Deep6mA to identify DNA 6mA sites. Deep6mA, composed of a CNN and a bidirectional LSTM (BLSTM) module, is shown to have a better performance than other methods above on 6mA prediction [34]. Although the above methods have made great progress, their performance is still not satisfactory.…”

iDNA-ABF: multi-scale deep biological language learning model for the interpretable prediction of DNA methylations

“…To simplify the model construction, SNNRice6mA [ 16 ] builds a simple and lightweight deep learning model using Convolutional Neural Network (CNN) to identify 6mA sites in the rice genome. Later on, Li et al proposed Deep6mA [ 17 ], a hybrid deep learning network of CNN and Long Short-Term Memory (LSTM), with more accurate 6mA prediction. BERT6mA [ 18 ] is a similar model but uses transformer to build predictive models, demonstrating the effectiveness of natural language processing techniques with applications in 6mA prediction.…”