Design and implementation of a scalable high-performance computing (HPC) cluster for omics data analysis: achievements, challenges and recommendations in LMICs

Gigascience. 2024 Jan 2:13:giae060. doi: 10.1093/gigascience/giae060.

Abstract

Background: The advent of high-throughput technologies, including cutting-edge sequencing devices, has revolutionized biomedical data generation and processing. Nevertheless, big data applications require novel hardware and software for parallel computing and management to handle the ever-growing data size and analysis complexity. On-premise, high-performance computing (HPC) is increasingly used in biomedical research for big data stewardship.

Findings: In this work, we present Tunisia's first high-performance computational infrastructure for omics research.

Method: We highlight measurements and recommendations that may help institutions in other low- and middle-income countries that are eager to implement local HPC in facilities for bioinformatics research and omics data analyses.

Keywords: HPC; Tunisia; bioinformatics; computational power; computing cluster; infrastructure.

MeSH terms

  • Big Data
  • Computational Biology* / methods
  • Data Analysis
  • Developing Countries
  • Genomics / methods
  • Humans
  • Software*