Fast and Accurate Protein Folding Prediction Using GPU-Accelerated ML Techniques

EasyChair Preprint 13904

Abstract

Protein folding, a critical process in molecular biology, determines the three-dimensional structure of proteins from their amino acid sequences. Accurate prediction of protein folding is essential for understanding cellular functions, designing drugs, and treating diseases. Traditional computational methods, although effective, often require significant time and computational resources. This paper explores the application of GPU-accelerated machine learning (ML) techniques to enhance the speed and accuracy of protein folding prediction. By leveraging the parallel processing capabilities of GPUs, we develop a deep learning model that significantly reduces the time required for protein structure prediction while maintaining high accuracy. Our approach integrates advanced ML algorithms with state-of-the-art GPU hardware, optimizing both the training and inference phases. We evaluate the model using benchmark datasets and compare its performance with existing methods. The results demonstrate that GPU acceleration not only expedites the prediction process but also improves the precision of the predicted protein structures. This research highlights the potential of GPU-accelerated ML techniques in revolutionizing protein folding prediction, offering a powerful tool for bioinformatics and computational biology applications.

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

@booklet{EasyChair:13904,
  author    = {Abey Litty},
  title     = {Fast and Accurate Protein Folding Prediction Using GPU-Accelerated ML Techniques},
  howpublished = {EasyChair Preprint 13904},
  year      = {EasyChair, 2024}}