Real-Time Sequence Analysis Using GPU-Accelerated Machine Learning

EasyChair Preprint 14000

Abstract

Real-time sequence analysis has become a cornerstone in modern bioinformatics, crucial for rapid disease detection, evolutionary studies, and personalized medicine. Traditional methods, often limited by computational power, fail to meet the escalating demands for speed and accuracy. This paper presents a comprehensive study on the implementation of GPU-accelerated machine learning techniques for real-time sequence analysis. By leveraging the parallel processing capabilities of GPUs, our approach significantly enhances the throughput and precision of sequence alignment, variant calling, and phylogenetic analysis. We demonstrate the effectiveness of GPU-accelerated models through a series of benchmarks against conventional CPU-based methods, showcasing improvements in processing speed by up to 20-fold without compromising accuracy. Additionally, the integration of deep learning frameworks enables adaptive learning from vast datasets, further refining the analysis process. Our results indicate that GPU acceleration not only meets but surpasses current computational challenges, paving the way for more responsive and scalable bioinformatics applications. This study underscores the potential of GPU-accelerated machine learning as a transformative tool in the field of real-time sequence analysis, offering a robust solution to handle the growing complexity and volume of biological data

Keyphrases: Bioinformatic algorithms, Computational genomics, Deep learning in bioinformatics, GPU-accelerated machine learning, GPU-based bioinformatics, High Performance Computing

@booklet{EasyChair:14000,
  author    = {Abi Cit},
  title     = {Real-Time Sequence Analysis Using GPU-Accelerated Machine Learning},
  howpublished = {EasyChair Preprint 14000},
  year      = {EasyChair, 2024}}