Accelerating Transcriptomics Research with GPU-Enhanced Machine Learning

EasyChair Preprint 14190

Abstract

The rapid advancement of transcriptomics research necessitates sophisticated analytical tools capable of handling vast and complex datasets. Traditional computational methods often fall short in terms of efficiency and scalability, leading to extended processing times and limited insights. This paper explores the integration of Graphics Processing Units (GPUs) with machine learning techniques to accelerate transcriptomics research. By leveraging GPU-accelerated machine learning algorithms, we enhance the speed and accuracy of gene expression data analysis, enabling more comprehensive and timely discoveries. Our approach includes the implementation of GPU-optimized deep learning models for differential gene expression analysis, gene co-expression network construction, and pathway enrichment analysis. The results demonstrate a significant reduction in computation time and an improvement in model performance compared to conventional CPU-based methods. This advancement paves the way for more efficient handling of large-scale transcriptomic data, fostering deeper biological insights and accelerating.

Keyphrases: Central Processing Units (CPUs), Graphics Processing Units (GPUs), transcriptomics

@booklet{EasyChair:14190,
  author    = {Abill Robert},
  title     = {Accelerating Transcriptomics Research with GPU-Enhanced Machine Learning},
  howpublished = {EasyChair Preprint 14190},
  year      = {EasyChair, 2024}}