Artificial Intelligence in Cancer Genetics: Deciphering Gene Regulatory Networks and Transcriptional Dynamics

Cancer tumorigenesis is fundamentally driven by the profound dysregulation of gene regulatory networks (GRNs) and complex epigenetic alterations. With the advent of high-resolution technologies, such as single-cell and spatial transcriptomics, researchers can now capture the immense genetic and epigenetic heterogeneity of tumors at an unprecedented scale. However, deciphering how these molecular layers interact to rewire cancer cells remains a significant computational challenge. Artificial intelligence (AI) and advanced machine learning offer indispensable frameworks to decode these high-dimensional datasets. To enhance precision and clarity in cancer genetics, it is crucial to narrow our focus from broad clinical phenotypes to these fundamental mechanisms. There is an urgent need to explore how AI can leverage single-cell and spatial data to reconstruct cancer-specific regulatory wiring and epigenetic dynamics, thereby uncovering the hidden drivers of tumor progression.The primary goal of this Research Topic is to focus the application of artificial intelligence precisely on the reconstruction and interpretation of gene regulatory networks and epigenetic alterations in cancer. By shifting the lens toward specific transcriptional and regulatory dynamics at high resolutions, we aim to provide deeper mechanistic insights into tumor biology.We seek to bring together computational biologists, geneticists, and bioinformaticians to explore how advanced AI models can integrate single-cell genomics, spatial transcriptomics, and epigenetic multi-omics to map precise regulatory landscapes. Specifically, this collection will highlight innovative machine learning and deep learning models that predict transcription factor dependencies, decode chromatin state transitions, and uncover network-level vulnerabilities in the tumor microenvironment. Through this focused approach, we aim to transform highly complex, spatially-resolved omics data into clear genetic insights.This Research Topic welcomes original research, methodologies, and review articles at the intersection of AI, cancer genetics, and high-resolution omics. Specific areas of interest include, but are not limited to:• AI-driven reconstruction of tumor-specific gene regulatory networks using single-cell and spatial transcriptomics;• Machine learning applications for decoding epigenetic modifications, chromatin accessibility, and DNA methylation in cancer;• Graph-based AI and deep learning models that integrate spatial and single-cell multi-omics to explore tumor heterogeneity;• Predictive modeling of how non-coding mutations impact transcriptional regulation and epigenetic landscapes;• AI-based identification of novel genetic and epigenetic vulnerabilities within cancer regulatory networks.Please note: manuscripts consisting solely of bioinformatics or computational analyses of public data are not suitable for this journal unless accompanied by independent validation (clinical/ patient cohort, or in vitro/in vivo biological validation) or demonstrating high innovation. Topic editors: Yongjian Chen, Ge Zhang, Kaisaierjiang Kadier, Lei Yin Source: https://www.frontiersin.org/research-topics/80300/artificial-intelligence-in-cancer-genetics-deciphering-gene-regulatory-networks-and-transcriptional-dynamics