High Performance Computing for AI-driven Omics and Health Data Processing

The possibility to generate, collect and maintain large-scale biological and biomedical datasets presents unprecedented opportunities in computational biology. As a major consequence, the resulting explosion in data volume has led to the pervasive integration of Artificial Intelligence (AI) methods across various domains, going from precision medicine to systems biology and beyond. These AI models are capable of learning directly from raw data, significantly enhancing data-driven hypothesis generation and accelerating the process of scientific discovery.

These promising frontiers have also introduced significant computational challenges. The data-hungry nature of deep learning models and the high cost of training them require powerful computing infrastructure. High-Performance Computing (HPC) systems have therefore become essential, offering GPU acceleration and distributed computing capabilities across multiple machines.

This article collection aims to highlight novel contributions that foster collaboration among experts in deep learning, HPC, and data science to address the increasingly demanding challenges of modern computational biology, bioinformatics and medical informatics.

Areas of interest of HPC applications include but are not limited to:
● Deep Learning in Omics and Health Data Modeling and Analysis
● Foundation Models for Enhanced Omics Data Analysis
● Multimodal Approaches for Integrative Multi-Omics Analysis
● Generative Models for Virtual Biological Systems Simulation
● Computer Vision Applications in Bioinformatics and Medical Informatics
● Graph Neural Networks for Network Biology and Healthcare Applications
● Large Language Models Applications in Biology and Medicine
● Explainable AI for Transparent and Trustworthy Decision-Making in Biomedical Research
● High-Performance Computing for Scalable Analysis of Large-Scale Biological and Biome