GPU-Enhanced Predictive Models for Plant Genomics

EasyChair Preprint no. 14170

Abstract

The rapid advancement of plant genomics has significantly contributed to the understanding of genetic traits and improvement of crop species. However, the complexity and scale of genomic data pose substantial challenges to predictive modeling efforts. This paper presents a comprehensive exploration of GPU-enhanced predictive models for plant genomics, focusing on leveraging the parallel processing capabilities of Graphics Processing Units (GPUs) to accelerate computational tasks and enhance model performance. We discuss the implementation of GPU-accelerated deep learning algorithms and their application to various genomic prediction tasks, such as trait association studies, gene expression analysis, and genomic selection. By integrating GPU technology with advanced machine learning techniques, our approach aims to improve the accuracy and efficiency of predictive models, thereby facilitating more effective plant breeding and genetic research. The results highlight significant performance gains and computational advantages, demonstrating the potential of GPU-enhanced models to address the growing demands of plant genomics. This work contributes to the ongoing efforts in optimizing genomic research workflows and supports the development of innovative solutions for agricultural advancements.

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

@Booklet{EasyChair:14170,
  author = {Abill Robert},
  title = {GPU-Enhanced Predictive Models for Plant Genomics},
  howpublished = {EasyChair Preprint no. 14170},

  year = {EasyChair, 2024}}