Fast Phylogenomic Inference Using GPU-Accelerated ML Techniques

EasyChair Preprint 13911

Abstract

Phylogenomic inference, a cornerstone of evolutionary biology, involves analyzing the evolutionary relationships among species using genomic data. Traditional methods for phylogenetic analysis often suffer from high computational demands and prolonged processing times, hindering timely insights. The advent of GPU-accelerated machine learning (ML) techniques offers a transformative solution to these challenges. This paper explores the application of GPU-accelerated ML methods to significantly expedite phylogenomic inference. By leveraging the parallel processing capabilities of GPUs, we demonstrate substantial reductions in computational time while maintaining or improving the accuracy of phylogenetic reconstructions. Our approach integrates advanced ML algorithms optimized for GPU architectures, enabling the analysis of large-scale genomic datasets with unprecedented speed. Through a series of benchmark tests and real-world case studies, we illustrate the efficacy and scalability of our GPU-accelerated methods. This work underscores the potential of GPU-accelerated ML techniques to revolutionize phylogenomic research, paving the way for more efficient and comprehensive evolutionary studies.

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:13911,
  author    = {Abey Litty},
  title     = {Fast Phylogenomic Inference Using GPU-Accelerated ML Techniques},
  howpublished = {EasyChair Preprint 13911},
  year      = {EasyChair, 2024}}