AI-enabled Multi-omics for Stem Cell Regeneration

Stem cell biology encompasses the mechanisms that govern self-renewal, multilineage differentiation, tissue homeostasis, and regeneration. Single-cell RNA sequencing, ATAC-seq, spatial transcriptomics, proteomics, and other multi-omics technologies have revealed substantial heterogeneity in stem cell populations, dynamic lineage trajectories, and complex interactions with their microenvironments. However, integrating these high-dimensional and multimodal datasets remains challenging because of differences in scale, resolution, sparsity, batch effects, and biological context. Recent studies using machine learning, deep learning, graph-based methods, and network inference have improved the identification of cell states, regulatory programs, differentiation trajectories, and niche-dependent signals. Nevertheless, many models remain difficult to interpret, are insufficiently transferable across datasets, or lack experimental validation. A more integrated approach is needed to translate AI-generated predictions into mechanistic insights and reliable strategies for regenerative medicine.This Research Topic aims to advance the integration and interpretation of multi-omics data through artificial intelligence to improve understanding of stem cell biology and regeneration. It will examine how AI can predict stem cell potency and differentiation outcomes, identify regulators of self-renewal and lineage commitment, reconstruct regenerative trajectories, and characterize interactions between stem cells and their niches. The Research Topic also seeks to promote biologically interpretable, reproducible, and experimentally testable computational frameworks. Particular emphasis will be placed on connecting predictive models with biomarker discovery, quality control, therapeutic optimization, and mechanistic validation, thereby supporting the development of more effective and reliable stem cell-based interventions.To gather further insights into AI-driven analysis of stem cell multi-omics, this Research Topic will focus on computational and experimental studies addressing stem cell states, fate decisions, regeneration, and therapeutic translation. Studies based solely on public datasets without experimental validation will not be considered. We welcome articles addressing, but not limited to, the following themes:• AI-driven integration of single-cell, spatial, epigenomic, transcriptomic, and proteomic data for reconstructing regenerative trajectories.• Machine learning and deep learning models for predicting stem cell potency, differentiation, and functional outcomes.• Graph neural networks, network biology, and regulatory inference for identifying master regulators of self-renewal and lineage commitment.• AI-assisted biomarker discovery, cell-state classification, and quality control for stem cell products and therapies.• Analysis of stem cell heterogeneity, niche interactions, cell–cell communication, and regenerative potential.• Computational approaches for modelling lineage plasticity, reprogramming, and tissue regeneration.• Data standards, computational infrastructure, reproducible workflows, and benchmarking strategies for stem cell multi-omics.• Experimental validation of AI-derived predictions and their relevance to regenerative medicine.• Optimization of stem cell manufacturing, therapeutic dosing, and treatment response through predictive modelling. Topic editors: Yucang He, Songyun Zhao, Wei Song, Haoyuan Wang Source: https://www.frontiersin.org/research-topics/85761/ai-enabled-multi-omics-for-stem-cell-regeneration