Real-Time Bioinformatics Workflows Using GPU-Accelerated Machine Learning

EasyChair Preprint 14184

Abstract

The rapid advancement in genomic research and bioinformatics has necessitated the development of more efficient computational tools to manage and analyze vast amounts of biological data. This paper explores the implementation of GPU-accelerated machine learning techniques to enhance real-time bioinformatics workflows. By leveraging the parallel processing capabilities of Graphics Processing Units (GPUs), our approach aims to significantly reduce the time required for complex bioinformatics analyses, such as genomic sequence alignment, variant detection, and protein structure prediction. We present a detailed methodology for integrating GPU acceleration into existing bioinformatics pipelines, including the optimization of algorithms for GPU execution and the design of scalable data processing workflows. Performance benchmarks demonstrate substantial improvements in computational speed and efficiency compared to traditional CPU-based methods. Furthermore, we discuss the impact of these advancements on real-time data analysis, highlighting their potential to accelerate discoveries in genomics and personalized medicine. This study provides a comprehensive framework for researchers seeking to harness the power of GPU technology to streamline bioinformatics workflows and address the growing demands of modern biological research.

Keyphrases: Central Processing Units (CPUs), Graphics Processing Units (GPUs), machine learning

@booklet{EasyChair:14184,
  author    = {Abill Robert},
  title     = {Real-Time Bioinformatics Workflows Using GPU-Accelerated Machine Learning},
  howpublished = {EasyChair Preprint 14184},
  year      = {EasyChair, 2024}}