DTC-m6Am: A Framework for Recognizing N6,2′-O-dimethyladenosine Sites in Unbalanced Classification Patterns Based on DenseNet and Attention Mechanisms

Background: m6Am is a specific RNA modification that plays an important role in regulating mRNA stability, translational efficiency, and cellular stress response. m6Am’s precise identification is essential to gain insight into its functional mechanisms at transcriptional and post-...

Full description

Saved in:
Bibliographic Details
Main Authors: Hui Huang, Fenglin Zhou, Jianhua Jia, Huachun Zhang
Format: Article
Language:English
Published: IMR Press 2025-04-01
Series:Frontiers in Bioscience-Landmark
Subjects:
Online Access:https://www.imrpress.com/journal/FBL/30/4/10.31083/FBL36603
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850142807627399168
author Hui Huang
Fenglin Zhou
Jianhua Jia
Huachun Zhang
author_facet Hui Huang
Fenglin Zhou
Jianhua Jia
Huachun Zhang
author_sort Hui Huang
collection DOAJ
description Background: m6Am is a specific RNA modification that plays an important role in regulating mRNA stability, translational efficiency, and cellular stress response. m6Am’s precise identification is essential to gain insight into its functional mechanisms at transcriptional and post-transcriptional levels. Due to the limitations of experimental assays, the development of efficient computational tools to predict m6Am sites has become a major focus of research, offering potential breakthroughs in RNA epigenetics. In this study, we present a robust and reliable deep learning model, DTC-m6Am, for identifying m6Am sites across the transcriptome. Methods: Our proposed DTC-m6Am model first represents RNA sequences by One-Hot coding to capture base-based features and provide structured inputs for subsequent deep learning models. The model then combines densely connected convolutional networks (DenseNet) and temporal convolutional network (TCN). The DenseNet module leverages its dense connectivity property to effectively extract local features and enhance information flow, whereas the TCN module focuses on capturing global time series dependencies to enhance the modeling capability for long sequence features. To further optimize feature extraction, the Convolutional Block Attention Module (CBAM) is used to focus on key regions through spatial and channel attention mechanisms. Finally, a fully connected layer is used for the classification task to achieve accurate prediction of the m6Am site. For the data imbalance problem, we use the focal loss function to balance the learning effect of positive and negative samples and improve the performance of the model on imbalanced data. Results: The deep learning-based DTC-m6Am model performs well on all evaluation metrics, achieving 87.8%, 50.3%, 69.1%, 41.1%, and 76.5% for sensitivity (Sn), specificity (Sp), accuracy (ACC), Mathew’s correlation coefficient (MCC), and area under the curve (AUC), respectively, on the independent test set. Conclusions: We critically evaluated the performance of DTC-m6Am using 10-fold cross-validation and independent testing and compared it to existing methods. The MCC value of 41.1% was achieved when using the independent test, which is 19.7% higher than the current state-of-the-art prediction method, m6Aminer. The results indicate that the DTC-m6Am model has high accuracy and stability and is an effective tool for predicting m6Am sites.
format Article
id doaj-art-f4e95722d4b54a26aa9631bc4c8ec487
institution OA Journals
issn 2768-6701
language English
publishDate 2025-04-01
publisher IMR Press
record_format Article
series Frontiers in Bioscience-Landmark
spelling doaj-art-f4e95722d4b54a26aa9631bc4c8ec4872025-08-20T02:28:55ZengIMR PressFrontiers in Bioscience-Landmark2768-67012025-04-013043660310.31083/FBL36603S2768-6701(25)01700-9DTC-m6Am: A Framework for Recognizing N6,2′-O-dimethyladenosine Sites in Unbalanced Classification Patterns Based on DenseNet and Attention MechanismsHui Huang0Fenglin Zhou1Jianhua Jia2Huachun Zhang3School of Information Engineering, Jingdezhen Ceramic University, 333403 Jingdezhen, Jiangxi, ChinaSchool of Information Engineering, Jingdezhen Ceramic University, 333403 Jingdezhen, Jiangxi, ChinaSchool of Information Engineering, Jingdezhen Ceramic University, 333403 Jingdezhen, Jiangxi, ChinaSchool of Information Engineering, Jingdezhen Ceramic University, 333403 Jingdezhen, Jiangxi, ChinaBackground: m6Am is a specific RNA modification that plays an important role in regulating mRNA stability, translational efficiency, and cellular stress response. m6Am’s precise identification is essential to gain insight into its functional mechanisms at transcriptional and post-transcriptional levels. Due to the limitations of experimental assays, the development of efficient computational tools to predict m6Am sites has become a major focus of research, offering potential breakthroughs in RNA epigenetics. In this study, we present a robust and reliable deep learning model, DTC-m6Am, for identifying m6Am sites across the transcriptome. Methods: Our proposed DTC-m6Am model first represents RNA sequences by One-Hot coding to capture base-based features and provide structured inputs for subsequent deep learning models. The model then combines densely connected convolutional networks (DenseNet) and temporal convolutional network (TCN). The DenseNet module leverages its dense connectivity property to effectively extract local features and enhance information flow, whereas the TCN module focuses on capturing global time series dependencies to enhance the modeling capability for long sequence features. To further optimize feature extraction, the Convolutional Block Attention Module (CBAM) is used to focus on key regions through spatial and channel attention mechanisms. Finally, a fully connected layer is used for the classification task to achieve accurate prediction of the m6Am site. For the data imbalance problem, we use the focal loss function to balance the learning effect of positive and negative samples and improve the performance of the model on imbalanced data. Results: The deep learning-based DTC-m6Am model performs well on all evaluation metrics, achieving 87.8%, 50.3%, 69.1%, 41.1%, and 76.5% for sensitivity (Sn), specificity (Sp), accuracy (ACC), Mathew’s correlation coefficient (MCC), and area under the curve (AUC), respectively, on the independent test set. Conclusions: We critically evaluated the performance of DTC-m6Am using 10-fold cross-validation and independent testing and compared it to existing methods. The MCC value of 41.1% was achieved when using the independent test, which is 19.7% higher than the current state-of-the-art prediction method, m6Aminer. The results indicate that the DTC-m6Am model has high accuracy and stability and is an effective tool for predicting m6Am sites.https://www.imrpress.com/journal/FBL/30/4/10.31083/FBL36603m6am site identificationdeep learningdensenettcncbamclass imbalance
spellingShingle Hui Huang
Fenglin Zhou
Jianhua Jia
Huachun Zhang
DTC-m6Am: A Framework for Recognizing N6,2′-O-dimethyladenosine Sites in Unbalanced Classification Patterns Based on DenseNet and Attention Mechanisms
Frontiers in Bioscience-Landmark
m6am site identification
deep learning
densenet
tcn
cbam
class imbalance
title DTC-m6Am: A Framework for Recognizing N6,2′-O-dimethyladenosine Sites in Unbalanced Classification Patterns Based on DenseNet and Attention Mechanisms
title_full DTC-m6Am: A Framework for Recognizing N6,2′-O-dimethyladenosine Sites in Unbalanced Classification Patterns Based on DenseNet and Attention Mechanisms
title_fullStr DTC-m6Am: A Framework for Recognizing N6,2′-O-dimethyladenosine Sites in Unbalanced Classification Patterns Based on DenseNet and Attention Mechanisms
title_full_unstemmed DTC-m6Am: A Framework for Recognizing N6,2′-O-dimethyladenosine Sites in Unbalanced Classification Patterns Based on DenseNet and Attention Mechanisms
title_short DTC-m6Am: A Framework for Recognizing N6,2′-O-dimethyladenosine Sites in Unbalanced Classification Patterns Based on DenseNet and Attention Mechanisms
title_sort dtc m6am a framework for recognizing n6 2 o dimethyladenosine sites in unbalanced classification patterns based on densenet and attention mechanisms
topic m6am site identification
deep learning
densenet
tcn
cbam
class imbalance
url https://www.imrpress.com/journal/FBL/30/4/10.31083/FBL36603
work_keys_str_mv AT huihuang dtcm6amaframeworkforrecognizingn62odimethyladenosinesitesinunbalancedclassificationpatternsbasedondensenetandattentionmechanisms
AT fenglinzhou dtcm6amaframeworkforrecognizingn62odimethyladenosinesitesinunbalancedclassificationpatternsbasedondensenetandattentionmechanisms
AT jianhuajia dtcm6amaframeworkforrecognizingn62odimethyladenosinesitesinunbalancedclassificationpatternsbasedondensenetandattentionmechanisms
AT huachunzhang dtcm6amaframeworkforrecognizingn62odimethyladenosinesitesinunbalancedclassificationpatternsbasedondensenetandattentionmechanisms