Accelerated ML Models for Predicting Protein-Protein Interactions Using GPUs

EasyChair Preprint 13909

Abstract

Predicting protein-protein interactions (PPIs) is pivotal in understanding cellular functions and disease mechanisms. This study explores the efficacy of accelerated machine learning (ML) models leveraging Graphics Processing Units (GPUs) for enhancing the prediction accuracy and efficiency of PPIs. By harnessing GPU-accelerated deep learning algorithms, specifically tailored for large-scale genomic data, this research aims to expedite the identification of potential PPIs from vast datasets. The integration of GPU computing optimizes computational throughput, enabling real-time analysis and facilitating novel insights into complex biological networks. This approach not only enhances predictive performance but also advances our capabilities in deciphering intricate molecular interactions critical for biomedical research and therapeutic development.

Keyphrases: Accelerated sequence analysis, Bioinformatic algorithms, Computational Proteomics, Computational genomics, Deep learning in bioinformatics, GPU-accelerated machine learning, GPU-based bioinformatics, Genomic data processing, High Performance Computing

@booklet{EasyChair:13909,
  author    = {Abey Litty},
  title     = {Accelerated ML Models for Predicting Protein-Protein Interactions Using GPUs},
  howpublished = {EasyChair Preprint 13909},
  year      = {EasyChair, 2024}}