This special Collection in Human Genomics focuses on the integration of artificial intelligence (AI), machine learning (ML), and deep learning methodologies with omics and multi-omics data, with a particular emphasis on human health and disease modeling. As AI technologies rapidly evolve, their potential to revolutionize omics research and precision medicine is - especially in understanding genetic variation in human populations and advancing disease modeling - is becoming increasingly clear. However, bridging the gap between omics experts and AI specialists remains crucial for fully harnessing this potential.

We invite manuscripts featuring original studies that utilize state-of-the-art AI and deep learning algorithms applied to clinical, population-based, or other human-focused omics and multi-omics datasets. Contributions should demonstrate clearly how these methodologies can identify biomarkers, elucidate complex disease mechanisms, and inform precision medicine strategies, presented in a way accessible to researchers without extensive computational backgrounds. Additionally, this Collection aims to inform AI and computer science communities about the types and availability of omics datasets, with a focus on human-centric applications, thereby promoting interdisciplinary collaborations. Submissions that provide practical guidance, review emerging AI methodologies, offer clear tutorials, or highlight successful interdisciplinary case studies are also highly encouraged.

Together, we seek to enhance AI literacy within the omics community and foster collaborative innovation, accelerating translational discoveries and advancing human genomic applications with tangible impact on public health. Topics of interest include but are not limited to:

• Original research applying deep learning algorithms to human-focused omics and multi-omics datasets

• Reviews highlighting the current state-of-the-art AI methodologies, including generative and foundational models, and their applications in human disease modeling

• Tutorials introducing deep and graph-based learning concepts tailored for omics researchers

• Descriptions and characterizations of publicly available omics datasets suitable for AI applications, with emphasis on clinical or population-based datasets

• Perspectives and case studies on interdisciplinary collaboration between omics scientists and AI specialists

We encourage clear, concise, and accessible writing for interdisciplinary readers to support greater integration across these rapidly advancing fields.

This Collection supports and amplifies research related to SDG 3, Good Health and Well-Being .

This HUGO Collection welcomes original research, reviews, perspectives, and methods papers that advance the science and application of human pangenomes. We are particularly interested in work that moves beyond single linear references to graph‑based and multi‑haplotype models; improves detection and interpretation of structural and non‑coding variation; and develops interoperable, reproducible workflows that reduce reference bias across ancestries. Relevant submissions may include population‑scale analyses, benchmarking and standards, assembly and annotation pipelines, multi‑omics integration, and clinically oriented applications such as diagnostics and decision support.

A central aim of this Collection is to integrate scientific rigour with equity, ethics, and governance. We welcome contributions addressing inclusive participation and benefit-sharing; data sovereignty and responsible access; community and Indigenous engagement; privacy-preserving computation; biosecurity; and responsible applications of artificial intelligence in genomics. The Collection aligns with the goals of The Human Genome Project II (HGP2): Delivering Precision Public Health for Humanity, a UNESCO-endorsed project within the United Nations International Decade of Sciences for Sustainable Development (UN IDSSD 2024–2033). It is also supported by the emerging Centre for AI Capacity Building in Genomics, Health Data, and Responsible Research Systems (AI4GHR), and its role within the Global Network of Centres for Exchange and Cooperation on AI Capacity Building (AICBC), supported by the United Nations Office for Digital and Emerging Technologies (UN ODET). The focus is on developing cutting-edge methodologies and ethical frameworks for globally inclusive science, open science, and rights-based precision public health.

We welcome manuscripts that:

• Advance methods for data access, reliability, and quality that promote assembly, annotation, and analysis of human pangenomes (graph models, alternative haplotypes, structural and non‑coding variation);
• Demonstrate interoperable, reproducible pipelines that reduce reference bias and improve variant detection across populations and ancestries;
• Integrate multi‑omics, spatial omics, and clinical evidence to strengthen diagnostics, risk prediction, and decision support;
• Embed ethics, governance, open‑science, and sovereignty principles within digital tools and study design for genomics; and
• Advance standards, implementation science, ethics guidance, and assessment frameworks for responsible pangenomics in research, clinical, and public-health settings, including LMIC considerations and sustainable infrastructures.

This Collection prioritizes global representation and aims to support advanced scientific and practical foundations for equitable, high impact pangenomics.

All submissions in this collection undergo the journal’s standard peer review process. Similarly, all manuscripts authored by a Guest Editor(s) are handled by the Editor-in-Chief. As an open access publication, this journal levies an article processing fee (details here). We recognize that many key stakeholders may not have access to such resources and are committed to supporting participation in this issue wherever resources are a barrier. For more information about what support may be available, please visit OA funding and support, or email OAfundingpolicy@springernature.com or the Editor-in-Chief.