Accelerating Gene Network Inference with Machine Learning and GPU

EasyChair Preprint 13994

Abstract

Gene network inference plays a pivotal role in understanding complex biological systems by elucidating relationships among genes under different conditions. Traditional methods, while valuable, often face challenges in scalability and computational efficiency, particularly with large-scale genomic datasets. This paper proposes leveraging machine learning techniques accelerated by Graphics Processing Units (GPUs) to address these challenges. By harnessing GPU capabilities, significant advancements in parallel processing power can expedite the inference of gene regulatory networks. This approach not only enhances computational speed but also facilitates the integration of diverse omics data sources, thereby enabling more accurate and comprehensive biological insights. Through case studies and performance benchmarks, this research demonstrates the feasibility and benefits of GPU-accelerated machine learning for gene network inference, paving the way for enhanced understanding of biological processes and diseases.

Keyphrases: Gene regulatory networks (GRNs), gene network inference, machine learning

@booklet{EasyChair:13994,
  author    = {Abi Cit},
  title     = {Accelerating Gene Network Inference with Machine Learning and GPU},
  howpublished = {EasyChair Preprint 13994},
  year      = {EasyChair, 2024}}