Machine Learning Model Optimization with GPU Acceleration in Computational Biology

EasyChair Preprint no. 13745

Abstract

The application of machine learning (ML) in computational biology has revolutionized the analysis and interpretation of complex biological datasets, enabling significant advancements in genomics, proteomics, and drug discovery. However, the computational intensity required for training and optimizing ML models in this domain poses substantial challenges, often leading to prolonged processing times and limited scalability when using traditional central processing unit (CPU) based computations. To overcome these limitations, the adoption of graphics processing units (GPUs) has emerged as a powerful solution.

This paper explores the impact of GPU acceleration on ML model optimization in computational biology, highlighting the substantial improvements in computational efficiency and model performance. By leveraging the parallel processing capabilities of GPUs, researchers can perform numerous simultaneous calculations and handle large matrices more effectively, thereby accelerating the training and optimization processes of ML models. We present several case studies and examples that demonstrate the effectiveness of GPU-accelerated ML models in solving complex biological problems, from genomic sequence analysis to protein structure prediction.

Keyphrases: Central Processing Unit (CPU), Graphics Processing Units (GPUs), Machine Learning (ML)

@Booklet{EasyChair:13745,
  author = {Abill Robert},
  title = {Machine Learning Model Optimization with GPU Acceleration in Computational Biology},
  howpublished = {EasyChair Preprint no. 13745},

  year = {EasyChair, 2024}}