Fast and Efficient Computational Drug Repositioning Using GPU-Accelerated ML

EasyChair Preprint 14189

Abstract

Drug repositioning, the process of finding new therapeutic uses for existing drugs, presents a promising avenue for accelerating drug discovery and reducing development costs. Traditional computational methods for drug repositioning can be time-consuming and resource-intensive, necessitating innovative approaches to enhance their efficiency. This study explores the use of Graphics Processing Units (GPUs) to accelerate machine learning (ML) algorithms in computational drug repositioning. By leveraging the parallel processing power of GPUs, we propose a framework that significantly reduces the computational time required for predicting novel drug-disease associations. Our approach involves the integration of GPU-accelerated deep learning models with extensive chemical and biological data sets to enhance the accuracy and speed of drug repositioning predictions. We demonstrate the effectiveness of this framework through a series of experiments on various drug and disease data sets, highlighting substantial improvements in computational efficiency and prediction accuracy. This research underscores the potential of GPU-accelerated ML techniques to transform drug repositioning processes, paving the way for faster identification of new therapeutic applications and ultimately improving drug discovery workflows.

Keyphrases: Graphics Processing Units (GPUs), Machine Learning (ML), Support Vector Machines (SVM)

@booklet{EasyChair:14189,
  author    = {Abill Robert},
  title     = {Fast and Efficient Computational Drug Repositioning Using GPU-Accelerated ML},
  howpublished = {EasyChair Preprint 14189},
  year      = {EasyChair, 2024}}