Artificial Intelligence for Computational Biology and Health Informatics Challenges

In recent years, Artificial Intelligence (AI) is emerging as a transformative force in Computational Biology and Health Informatics. Traditional computational approaches in bioinformatics often struggle with the complexity, heterogeneity, and dimensionalities of biomedical data, limiting their effectiveness in challenging biological and health science problems. AI techniques offer powerful solutions to model nonlinear relationships, uncover hidden patterns, and enable predictive and personalized approaches in biomedical research and healthcare. These methods — including among others machine learning, deep learning, and generative models — have demonstrated promising results in areas such as omics and health data integration, drug discovery, disease classification, biomarker identification, and clinical decision support.

This article collection aims to highlight impactful AI-driven approaches addressing current challenges in Computational Biology and Health Informatics. We welcome contributions showcasing innovative methodologies and applications, interdisciplinary frameworks, and emerging paradigms that advance the frontier of AI in life and health sciences.

This article collection invites high-quality, multidisciplinary research works at the intersection of artificial intelligence, computational biology, and medical informatics. Our aim is to gather innovative AI-driven methodologies that address key open problems in bioinformatics, biostatistics, and medical informatics, particularly where classical statistical or bioinformatics approaches fall short.

We welcome studies demonstrating how AI can advance current knowledge, shape new paradigms in the life and health sciences, support clinical decision-making, drive precision medicine, and improve patient outcomes. Submissions may include methodologies and/or applications involving diverse biomedical and healthcare data sources, such as electronic health records, heterogeneous omics data, other molecular data, medical imaging and digital health technologies.

This collection serves as a gateway to explore current trends and future opportunities for AI in life science and healthcare — encouraging contributions that bridge disciplines and deliver novel, actionable insights in fundamental and translational research. We encourage authors to submit original research articles regarding computational intelligence methods for bioinformatics and biostatistics. Areas of interest include but are not limited to:

• AI-driven methods for preprocessing, harmonization, and integration of multi-omics, imaging, clinical, and sensor-derived health data.
• Machine learning and deep learning approaches for biomarker discovery, disease classification, and patient stratification
• Large language models (LLMs) and natural language processing (NLP) for mining unstructured clinical data (e.g., EHRs, pathology reports)
• Generative models for simulating biological data, augmenting disease cohorts, or generating plausible molecular profiles
• Network-based approaches for modeling gene, protein, or patient similarity networks, pathway analysis, and systems-level inference
• Explainable AI (XAI) and interpretable models to support clinical decision-making and foster trust in health care AI
• Federated and transfer learning frameworks to address data privacy, heterogeneity, and scarcity
• AI applications in drug discovery and therapeutic target prediction, especially in complex diseases
• Benchmarking studies and reproducible pipelines for AI in biomedicine