High-Performance Computational Biology for Infectious Disease Research Using GPU

EasyChair Preprint 14201

Abstract

The advent of high-performance computing (HPC) and the integration of Graphics Processing Units (GPUs) have revolutionized computational biology, particularly in the realm of infectious disease research. This paper explores the transformative impact of GPU-accelerated computational techniques on the analysis, modeling, and prediction of infectious diseases. By leveraging the parallel processing capabilities of GPUs, complex biological computations, such as genomic sequencing, protein structure prediction, and epidemiological modeling, can be performed at unprecedented speeds and scales. This acceleration facilitates real-time data analysis, enhancing our ability to respond promptly to emerging infectious threats. We highlight several case studies where GPU-enhanced models have significantly improved the accuracy and efficiency of disease outbreak predictions, pathogen identification, and drug discovery. Furthermore, the integration of machine learning algorithms with GPU technology enables the extraction of intricate patterns from vast biological datasets, providing deeper insights into pathogen behavior and host-pathogen interactions. The paper also discusses the challenges and future prospects of GPU-based HPC in infectious disease research, emphasizing the need for continued innovation and collaboration across computational and biological sciences. Through this interdisciplinary approach, we aim to demonstrate that GPU-accelerated computational biology holds the potential to drastically improve our understanding and management of infectious diseases, ultimately contributing to global health security.

Keyphrases: Graphics Processing Units (GPUs), High Performance Computing (HPC), computational biology

@booklet{EasyChair:14201,
  author    = {Abill Robert},
  title     = {High-Performance Computational Biology for Infectious Disease Research Using GPU},
  howpublished = {EasyChair Preprint 14201},
  year      = {EasyChair, 2024}}