{"scope":{"layer":"general","tissue_scope":"unknown","species":"unknown","system":"unknown","evidence_level":"preprint","importance":"","importance_reason":""},"id":"VC0155","type":"preprint","title":"SubcellPert: Benchmarking Subcellular Perturbation Prediction","authors_or_org":"Wang J, Cao H, Dang X, Zhou T, Zhao Y, Hsieh C-Y, Gu C, Heng PA.","date":"2026-10-17","year":"2026","venue":"bioRxiv (preprint, not peer-reviewed)","url":"https://doi.org/10.64898/2026.10.11.758305","doi":"10.64898/2026.10.11.758305","pmid":"","brain_tumor_focus":"no","tags":["benchmark","perturbation","spatial","aivc"],"tag_slugs":["benchmark","perturbation","spatial","aivc"],"tag_labels":["Benchmark & validation","Perturbation","Spatial omics","AI virtual cell"],"tag_labels_zh":["基准评测与验证","扰动","空间组学","AI 虚拟细胞"],"unmapped_tags":[],"one_line_summary_en":"Preprint (not peer-reviewed): Wang et al. (Chinese University of Hong Kong) introduce SubcellPert, a benchmark for perturbation-response prediction at single-RNA-molecule resolution: 14 imaging datasets, 13.88 million cells and 3.65 billion RNA molecules; an Oracle task (predict molecule positions given exact target counts) and a Joint task (counts and positions), with fixed perturbation and cellular-context holdouts; eight baselines including classical transport and frozen foundation-model adapters. The authors report that Gaussian transport gives the lowest Oracle spatial error on 8 of 11 cellular-context OOD datasets, and audits show that better centroid accuracy can accompany worse radial distributions. The abstract names no brain-tumor data.","one_line_summary_zh":"预印本（未经同行评审）：Wang 等（香港中文大学）提出 SubcellPert，在单 RNA 分子分辨率上评测扰动响应预测：14 个成像数据集、1,388 万个细胞、36.5 亿个 RNA 分子；设 Oracle（给定准确目标计数预测分子位置）与 Joint（同时预测计数与位置）两类任务，并固定扰动与细胞语境留出；8 个基线包括经典传输方法与冻结基础模型适配器。作者报告：在 11 个细胞语境分布外数据集中，高斯传输在 8 个上取得最低 Oracle 空间误差；审计显示质心更准时径向分布可能更差。摘要未提及脑肿瘤数据。","verified":"yes","verification_source":"bioRxiv API details (title, 8 authors, posted 2026-10-17, v1, new results, CC BY, corresponding institution CUHK, abstract) + Crossref posted-content record (same title/authors/date) fetched 2026-10-20; full text not read","page_url":"https://gliostate.com/library/VC0155/","api_url":"https://gliostate.com/api/items/VC0155.json","sameAs":["https://doi.org/10.64898/2026.10.11.758305"],"is_preprint":true,"facets":{"type":"https://gliostate.com/library/type/preprint/","year":"https://gliostate.com/library/year/2026/","tags":["https://gliostate.com/library/tag/benchmark/","https://gliostate.com/library/tag/perturbation/","https://gliostate.com/library/tag/spatial/","https://gliostate.com/library/tag/aivc/"]},"cited_by":[],"related":[{"id":"VC0036","title":"An operational perturbation proteomics-based virtual cell model.","shared_tags":["perturbation","aivc"],"page_url":"https://gliostate.com/library/VC0036/","api_url":"https://gliostate.com/api/items/VC0036.json"},{"id":"VC0138","title":"PerturbLDM: conditional latent diffusion for modelling single-cell perturbation responses","shared_tags":["aivc","perturbation"],"page_url":"https://gliostate.com/library/VC0138/","api_url":"https://gliostate.com/api/items/VC0138.json"},{"id":"VC0130","title":"UniPert-G2CP bridges genetic and chemical screens from molecular representation to phenotype modeling","shared_tags":["aivc","perturbation"],"page_url":"https://gliostate.com/library/VC0130/","api_url":"https://gliostate.com/api/items/VC0130.json"},{"id":"VC0135","title":"Harnessing AI to Build Virtual Cells (VCHarness)","shared_tags":["aivc","perturbation"],"page_url":"https://gliostate.com/library/VC0135/","api_url":"https://gliostate.com/api/items/VC0135.json"},{"id":"VC0136","title":"AetherCell: A generative engine for virtual cell perturbation and in vivo drug discovery","shared_tags":["aivc","perturbation"],"page_url":"https://gliostate.com/library/VC0136/","api_url":"https://gliostate.com/api/items/VC0136.json"},{"id":"VC0137","title":"Towards building a World Model to simulate perturbation-induced cellular dynamics by AlphaCell","shared_tags":["aivc","perturbation"],"page_url":"https://gliostate.com/library/VC0137/","api_url":"https://gliostate.com/api/items/VC0137.json"}]}