Authors:
D. Lavanya, O. Jeba Singh, Akey Sungheetha, S. Rubin Bose, T. Shynu, Chou Yi Hsu

Addresses:
Department of Electronics and Communication Engineering, SRM Institute of Science and Technology, Tiruchirappalli, Tamil Nadu, India. Centre for Academic Research, Alliance University, Bengaluru, Karnataka, India. Department of Computer Science and Engineering, Alliance University, Bengaluru, Karnataka, India. School of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Research and Development, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India. Department of Pharmacy, Chia Nan University of Pharmacy and Science, Tainan, Taiwan.

Abstract:

The proposed method addresses a major challenge in Genomic Sequence Analysis (GSA), particularly in identifying regulatory motifs, deciphering complex DNA patterns, and predicting disease-linked genetic variants. To address these constraints, a hybrid neural network architecture integrating Convolutional Neural Networks (CNN) and a Transformer model is formulated. The CNN component effectively captures local genomic patterns and sequence features. The Transformer model, on the other hand, makes it easier to learn long-range dependencies in DNA sequences. This integrated architecture improves the accuracy and efficiency of genomic pattern recognition and functional element prediction. The experimental results show that the system works very well, with a precision of 94.7% and an accuracy of 91.3%. Also, the proposed model is about 23% better at detecting motifs and 18% better at classifying variants than traditional methods. These improvements demonstrate how well combining deep learning architectures can analyze complex genomic data. The method speeds up AI-driven genomic research and helps improve medical diagnostics, disease prediction, and scalable bioinformatics solutions. The proposed framework improves the ability to analyze large genomic datasets, which makes genomic interpretation in modern biomedical research more accurate and efficient.

Keywords: Artificial Intelligence; Genomic Sequence Analysis; Deep Learning Models; Convolutional Neural Networks; Transformer Models; DNA Sequences; CNN–Transformer.

Received on: 07/04/2025, Revised on: 12/06/2025, Accepted on: 05/08/2025, Published on: 03/03/2026

DOI: 10.69888/FTSNL.2026.000640

FMDB Transactions on Sustainable Neuroscience Letters, 2026 Vol. 1 No. 1, Pages: 1–12

• Views : 35
• Downloads : 10

Download PDF