Machine Learning–Driven Biomarker Discovery in Gene and Cell Therapy

Advances in next-generation sequencing and high-throughput profiling technologies have substantially expanded our capacity to characterize both therapeutic products and host biological responses. Genomic, transcriptomic, and epigenomic analyses are increasingly applied to explore determinants of cellular fitness, persistence, resistance mechanisms, and treatment-associated toxicities.At the same time, machine learning approaches are being incorporated into biomedical research to interrogate complex datasets and identify multidimensional patterns that may not be captured by conventional statistical methods. Despite this progress, variability in cohort size, data structure, and validation strategies continues to limit translation into routine clinical practice. A structured platform addressing these challenges in the specific context of gene and cell therapy is therefore timely.Gene and cell therapies have achieved remarkable clinical advances across several indications. Nevertheless, response rates remain variable and treatment-related toxicities can be difficult to anticipate. The identification of reliable biomarkers capable of informing patient selection, monitoring therapeutic dynamics, and predicting outcomes continues to be a central challenge in the field.The growing availability of high-dimensional molecular data, together with the development of machine learning methodologies, provides an opportunity to refine predictive strategies beyond traditional analytical frameworks. However, robust integration of computational modeling with biologically meaningful endpoints is still evolving.This Research Topic aims to bring together studies focused on biomarker discovery supported by machine learning approaches in gene and cell therapy. By highlighting work that connects molecular profiling, computational modeling, and clinical outcomes, the collection seeks to promote reproducible and clinically relevant predictive frameworks that may contribute to more precise and individualized therapeutic strategies.This Research Topic welcomes original research articles, systematic reviews, and methodological contributions addressing biomarker discovery and predictive modeling in gene and cell therapy. Studies integrating molecular profiling with machine learning–based analytical approaches will be of particular interest.Potential themes include:• genomic, transcriptomic, and epigenomic determinants of therapeutic response and resistance • computational integration of multi-omics datasets• predictive modeling of treatment-related toxicities and long-term outcomes• development and validation of bioinformatic pipelines • strategies aimed at improving reproducibility and external validation• Ethical considerations of adopting new approaches for biomarker discoverySubmissions may encompass different advanced therapeutic modalities, including engineered immune cell therapies, gene-editing strategies, and stem cell–based approaches. Contributions bridging molecular insight and clinical implementation are especially encouraged. Topic editors: Diego Carbonell, Javier Anguita Source: https://www.frontiersin.org/research-topics/78970/machine-learning-driven-biomarker-discovery-in-gene-and-cell-therapy