GPU-Accelerated Analysis of Genome Editing Outcomes Using Machine Learning

EasyChair Preprint 14198

Abstract

The advent of genome editing technologies, such as CRISPR-Cas9, has revolutionized the field of genetic engineering, offering unprecedented opportunities for targeted modifications in genomic sequences. However, the complexity and scale of data generated from genome editing experiments pose significant challenges in accurately analyzing and interpreting the outcomes. This study explores the integration of GPU-accelerated machine learning techniques to enhance the analysis of genome editing results. By leveraging the parallel processing capabilities of GPUs, we demonstrate improved efficiency and performance in processing large-scale genomic datasets and training complex machine learning models. Our approach includes the development of GPU-optimized algorithms for predicting off-target effects, assessing edit efficiency, and identifying unintended genetic variations. The results highlight a marked increase in computational speed and model accuracy, facilitating more precise and timely insights into genome editing outcomes. This advancement not only streamlines the analysis process but also contributes to more reliable evaluations of genome editing technologies, paving the way for more effective and safer applications in genetic research and therapy.

Keyphrases: Graphics Processing Units (GPUs), Machine Learning (ML), Next Generation Sequencing (NGS)

@booklet{EasyChair:14198,
  author    = {Abi Litty},
  title     = {GPU-Accelerated Analysis of Genome Editing Outcomes Using Machine Learning},
  howpublished = {EasyChair Preprint 14198},
  year      = {EasyChair, 2024}}