AI and computational methods for reconstructing cell-state-specific gene regulatory networks from single-cell transcriptome and chromatin accessibility data in cancer: methods, applications, and perspectives

Mini-review (Wang and Chen; Frontiers in Genetics 17:1982712, 2026) of AI and computational methods for reconstructing cell-state-specific gene regulatory networks in cancer from single-cell transcriptome and chromatin accessibility data. It distinguishes same-cell paired, matched-unpaired, imputed and single-modality designs, organizes methods by inference objective (motif/co-accessibility inference, deep integration and graph learning, dynamic and cell-state-specific modeling, virtual perturbation, with tools such as CellOracle, Pando, GenKI and scTenifoldKnk discussed in the full text), and discusses applications to EMT, treatment resistance, lineage plasticity and tumor subtyping along an evidence hierarchy from association to experimentally supported causal regulation. The glioma example (patient-derived glioma stem-like cells, citing Park et al. 2024) appears in the main text, not the abstract, and is described there as preclinical. The authors state clinical utility still requires prospective validation.

Authors / organisation

Wang J, Chen F.

Venue

Frontiers in Genetics

Date

2026-10-20

Type

paper

Year

2026

DOI

10.3389/fgene.2026.1982712

Verification

Crossref (journal-article, Frontiers in Genetics vol 17, article 1982712, published 2026-10-20, CC BY 4.0, 2 authors, abstract) + Frontiers full-text page (tool names; glioma stem-like cell example citing Park et al. 2024 Sci Adv 10.1126/sciadv.adj7706) fetched 2026-10-21; no PMID yet

ReviewGene regulatory networkscRNA-seqMulti-omicsIn-silico perturbationCancer

Open in the searchable library → · JSON