Fast and Accurate Analysis of Non-Coding RNA Using GPU-Accelerated ML

EasyChair Preprint 14118

Abstract

Non-coding RNAs (ncRNAs) play crucial roles in gene regulation, cellular processes, and disease mechanisms, yet their analysis remains a significant challenge due to the complexity and volume of biological data. Traditional methods for ncRNA analysis are often computationally intensive and time-consuming, hindering large-scale studies and rapid discoveries. This paper presents a novel approach for the fast and accurate analysis of non-coding RNA using GPU-accelerated machine learning techniques. By leveraging the parallel processing power of GPUs, we achieve substantial performance gains, enabling the handling of large datasets with improved speed and precision. Our approach integrates advanced machine learning algorithms optimized for GPU architectures, which significantly reduces computational time without compromising the accuracy of ncRNA classification, prediction, and functional annotation. We demonstrate the effectiveness of our method through extensive benchmarking on various ncRNA datasets, showcasing its potential to accelerate research and applications in genomics, personalized medicine, and molecular biology. The results highlight the transformative impact of GPU-accelerated machine learning in enhancing the efficiency and accuracy of ncRNA analysis, paving the way for deeper insights and innovations in the field.

Keyphrases: Convolutional Neural Networks (CNNs), Non-coding RNAs (ncRNAs), Support Vector Machines (SVMs)

@booklet{EasyChair:14118,
  author    = {Abi Litty},
  title     = {Fast and Accurate Analysis of Non-Coding RNA Using GPU-Accelerated ML},
  howpublished = {EasyChair Preprint 14118},
  year      = {EasyChair, 2024}}