CNN6mA: Interpretable neural network model based on position-specific CNN and cross-interactive network for 6mA site prediction

Tsukiyama, Sho; Hasan, Md. Mehedi; Kurata, Hiroyuki

doi:10.1016/j.csbj.2022.12.043

Cited by 6 publications

(2 citation statements)

References 38 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TC-6mA-Pred employed the deep transformer neural network to accurately predict the 6mA sites. CNN6mA proposed one position-specific 1-D CNN module and one cross-interactive network module for the 6mA site prediction. The above methods verified that CNN, BiLSTM, and SAM can be used to help improve the prediction performance of 6mA sites.…”

Section: Introductionmentioning

confidence: 99%

Improving DNA 6mA Site Prediction via Integrating Bidirectional Long Short-Term Memory, Convolutional Neural Network, and Self-Attention Mechanism

Hu,

Tang,

Zhou

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Identifying DNA N6-methyladenine (6mA) sites is significantly important to understanding the function of DNA. Many deep learning-based methods have been developed to improve the performance of 6mA site prediction. In this study, to further improve the performance of 6mA site prediction, we propose a new meta method, called Co6mA, to integrate bidirectional long short-term memory (BiLSTM), convolutional neural networks (CNNs), and self-attention mechanisms (SAM) via assembling two different deep learning-based models. The first model developed in this study is called CBi6mA, which is composed of CNN, BiLSTM, and fully connected modules. The second model is borrowed from LA6mA, which is an existing 6mA prediction method based on BiLSTM and SAM modules. Experimental results on two independent testing sets of different model organisms, i.e., Arabidopsis thaliana and Drosophila melanogaster, demonstrate that Co6mA can achieve an average accuracy of 91.8%, covering 89% of all 6mA samples while achieving an average Matthews correlation coefficient value (0.839), which is higher than the second-best method DeepM6A.

show abstract

Section: Introductionmentioning

confidence: 99%

Improving DNA 6mA Site Prediction via Integrating Bidirectional Long Short-Term Memory, Convolutional Neural Network, and Self-Attention Mechanism

Hu,

Tang,

Zhou

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…Recently, many computational prediction models of m6A modification have been proposed, such as BERT6mA and CNN6mA. Compared with traditional technologies, they have the advantages of reduced time, low cost, and a high prediction accuracy; thus, they are expected to be widely adopted in the future (Tsukiyama et al, 2022(Tsukiyama et al, , 2023.…”

Section: Introductionmentioning

confidence: 99%

Comprehensive analysis of m6A modifications in oral squamous cell carcinoma by MeRIP sequencing

Liu,

Long,

Zhong

et al. 2023

Genes Genet. Syst.

View full text Add to dashboard Cite

N6-methyladenosine (m6A) modifications are the most abundant internal modifications of mRNA and have a significant role in various cancers; however, the m6A methylome profile of oral squamous cell carcinoma (OSCC) in the mRNA-wide remains unknown. In this study, we examined the relationship between m6A and OSCC. Four pairs of OSCC and adjacent normal tissues were compared by Methylated RNA immunoprecipitation sequencing (MeRIP-seq). Gene Ontology, Kyoto Encyclopedia of Genes and Genomes (KEGG), and Ingenuity Pathway Analysis (IPA) analyses were used to further analyze the MeRIP-seq data. A total of 2,348 different m6A peaks were identified in the OSCC group, including 85 m6A upregulated peaks and 2,263 m6A downregulated peaks. Differentially methylated m6A binding sites were enriched in the coding sequence in proximity to the stop codon of both groups. KEGG analysis revealed genes with upregulated m6A-modified sites in the OSCC group, which were prominently associated with the forkhead box O (FOXO) signaling pathway. Genes containing downregulated m6A-modified sites were significantly correlated with the PI3K/Akt signaling pathway, spliceosome, protein processing in the endoplasmic reticulum, and endocytosis. IPA analysis indicated that several genes with differential methylation peaks form networks with m6A regulators. Overall, this study established the mRNA-wide m6A map for human OSCC and indicated the potential links between OSCC and N6-methyladenosine modification.

show abstract

Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning

ŞAHiN,

Arslan,

Özdemir

2024

Neural Comput & Applic

View full text Add to dashboard Cite

CNN6mA: Interpretable neural network model based on position-specific CNN and cross-interactive network for 6mA site prediction

Cited by 6 publications

References 38 publications

Improving DNA 6mA Site Prediction via Integrating Bidirectional Long Short-Term Memory, Convolutional Neural Network, and Self-Attention Mechanism

Improving DNA 6mA Site Prediction via Integrating Bidirectional Long Short-Term Memory, Convolutional Neural Network, and Self-Attention Mechanism

Comprehensive analysis of m6A modifications in oral squamous cell carcinoma by MeRIP sequencing

Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning

Contact Info

Product

Resources

About