TCN-5mC: a predictor of 5-methylcytosine sites based on multi-feature fusion and TCN-inspired block networks

TL;DR

TCN-5mC is a new deep learning tool that accurately predicts 5-methylcytosine sites in DNA, improving on existing methods for epigenetic research.

Contribution

A novel deep learning model combining TCN and BiGRU with multi-feature encoding for improved 5mC prediction in imbalanced genomic data.

Findings

TCN-5mC achieved AUC values of 0.967 and 0.989 on lung cancer cell line datasets.

The model outperforms existing methods in specificity, accuracy, MCC, and AUC metrics.

The architecture effectively captures long-range dependencies and local sequence patterns.

Abstract

Accurate identification of 5-methylcytosine (5 mC) sites in promoter regions is crucial for understanding epigenetic regulation, but experimental methods remain costly and time-consuming, highlighting the need for reliable computational prediction tools. While existing deep learning approaches, such as BiLSTM-based, Transformer-based, and pretrained language models, have advanced the field, opportunities remain for further improvements in capturing long-range dependencies and handling imbalanced genomic data. Here, we present TCN-5mC, a deep learning model that integrates Temporal Convolutional Networks (TCN) inspired block with Bidirectional Gated Recurrent Units (BiGRU) and employs hybrid One-Hot and Nucleotide Chemical Property feature encoding. This architecture is designed to more effectively model both extended sequence contexts and local patterns. The model achieves high predictive performance on imbalanced datasets from lung cancer cell lines, with AUC values of 0.967 and 0.989 on two independent test sets, outperforming existing methods in specificity, accuracy, MCC, and AUC. The model thus provides a robust, high-throughput computational tool for 5 mC site prediction, with promising potential for epigenetic research and biomarker discovery.

Figures