{"scope":{"layer":"general","tissue_scope":"unknown","species":"unknown","system":"unknown","evidence_level":"peer_reviewed","importance":"","importance_reason":""},"id":"VC0174","type":"paper","title":"Emerging frontiers for AI in single-cell genomics","authors_or_org":"Mitra S, Li J, Leslie CS.","date":"2026-10-15","year":"2026","venue":"Molecular Cell","url":"https://doi.org/10.1016/j.molcel.2026.09.014","doi":"10.1016/j.molcel.2026.09.014","pmid":"42880218","brain_tumor_focus":"no","tags":["review","foundation-model","scrna-seq","perturb-seq","aivc"],"tag_slugs":["review","foundation-model","scrna-seq","perturb-seq","aivc"],"tag_labels":["Review","Foundation model","scRNA-seq","Perturb-seq","AI virtual cell"],"tag_labels_zh":["综述","基础模型","单细胞 RNA 测序","Perturb-seq 扰动测序","AI 虚拟细胞"],"unmapped_tags":[],"one_line_summary_en":"Review (Mitra, Li and Leslie; Memorial Sloan Kettering; Molecular Cell 86:4131–4148, 2026) of AI embedding and foundation models for scRNA-seq and scATAC-seq, machine-learning work on single-cell multiome in regulatory genomics, and strategies to learn \"virtual cell\" models from Perturb-seq, ending with current limitations of single-cell AI models. The authors note that most early single-cell embedding and foundation models did not gain wide traction among experimental biologists. Declared interest: C.S.L. is on the journal's advisory board.","one_line_summary_zh":"综述（Mitra、Li 与 Leslie；纪念斯隆-凯特琳癌症中心；Molecular Cell 86:4131–4148，2026）：回顾 scRNA-seq 与 scATAC-seq 的 AI 嵌入与基础模型、单细胞多组学在调控基因组学中的机器学习研究，以及从 Perturb-seq 学习“虚拟细胞”模型的策略，并总结当前单细胞 AI 模型的局限。作者指出，多数早期单细胞嵌入与基础模型并未在实验生物学家中广泛使用。利益声明：C.S.L. 为该刊顾问委员会成员。","verified":"yes","verification_source":"PubMed E-utilities PMID 42880218 (title, 3 authors, MSKCC, Mol Cell 86(20):4131-4148, 2026 Oct 15, abstract, conflict statement) + Crossref (journal-article) fetched 2026-10-20; full text not read","page_url":"https://gliostate.com/library/VC0174/","api_url":"https://gliostate.com/api/items/VC0174.json","sameAs":["https://doi.org/10.1016/j.molcel.2026.09.014","https://pubmed.ncbi.nlm.nih.gov/42880218/"],"is_preprint":false,"facets":{"type":"https://gliostate.com/library/type/paper/","year":"https://gliostate.com/library/year/2026/","tags":["https://gliostate.com/library/tag/review/","https://gliostate.com/library/tag/foundation-model/","https://gliostate.com/library/tag/scrna-seq/","https://gliostate.com/library/tag/perturb-seq/","https://gliostate.com/library/tag/aivc/"]},"cited_by":[],"related":[{"id":"VC0173","title":"Virtual cells: progress and challenges from mechanistic modeling to data-driven integration","shared_tags":["review","aivc","foundation-model"],"page_url":"https://gliostate.com/library/VC0173/","api_url":"https://gliostate.com/api/items/VC0173.json"},{"id":"VC0175","title":"Benchmarking biological knowledge-graph priors against single-cell foundation models for Perturb-seq prediction","shared_tags":["perturb-seq","foundation-model"],"page_url":"https://gliostate.com/library/VC0175/","api_url":"https://gliostate.com/api/items/VC0175.json"},{"id":"VC0171","title":"AI in Neuro-Oncology: An Overarching Review","shared_tags":["review"],"page_url":"https://gliostate.com/library/VC0171/","api_url":"https://gliostate.com/api/items/VC0171.json"},{"id":"VC0006","title":"Beyond the drug-centric view: Advancing AI virtual cell platforms for environmental perturbation modelling.","shared_tags":["review"],"page_url":"https://gliostate.com/library/VC0006/","api_url":"https://gliostate.com/api/items/VC0006.json"},{"id":"VC0084","title":"Current landscape of single-cell genomics in meningioma.","shared_tags":["review"],"page_url":"https://gliostate.com/library/VC0084/","api_url":"https://gliostate.com/api/items/VC0084.json"},{"id":"VC0004","title":"AI-driven virtual cell models in preclinical research: technical pathways, validation mechanisms, and clinical translation potential.","shared_tags":["review"],"page_url":"https://gliostate.com/library/VC0004/","api_url":"https://gliostate.com/api/items/VC0004.json"}]}