Genomics at the Nexus of AI, Computer Vision, and Machine Learning

16An Efficient Deep Convolutional Neural Networks Model for Genomic Sequence Classification

Amit Pimpalkar^1*, Nisarg Gandhewar ¹, Nilesh Shelke², Sachin Patil³ and Sharda Chhabria⁴

¹Department of Computer Science and Engineering (AIML), Shri Ramdeobaba College of Engineering and Management, Nagpur, India

²Department of Computer Science and Engineering, Symbiosis Institute of Technology, Nagpur Campus, Symbiosis International (Deemed University), Pune, India

³Department of Artificial Intelligence, St. Vincent Pallotti College of Engineering and Technology, Nagpur Maharashtra, India

⁴Department of Artificial Intelligence, G H Raisoni Institute of Engineering and Technology, Nagpur Maharashtra, India

Abstract

Identifying and classifying deoxyribonucleic acid (DNA) sequences is a crucial task in genomics analysis. Deep learning models have shown great potential in this area, with various architectures being proposed to improve accuracy and efficiency. This chapter introduces an innovative framework, the efficient deep convolutional neural networks (CNN) model, for identifying and classifying DNA sequences in genomics research. Leveraging the hierarchical learning capabilities of CNNs, this model autonomously extracts intricate features from raw DNA sequences, capturing local and global patterns critical for genomic understanding.

A novel k-mer embedding technique transforms raw DNA sequences into a numerical representation suitable for CNN processing, preserving sequence order ...