{"scope":{"layer":"general","tissue_scope":"unknown","species":"unknown","system":"unknown","evidence_level":"preprint","importance":"","importance_reason":""},"id":"VC0151","type":"preprint","title":"MRFlow: Mechanism-Structured Residual Flow Matching for Virtual Cell Perturbation Prediction","authors_or_org":"Yang H, Su R.","date":"2026-10","year":"2026","venue":"arXiv (preprint, not peer-reviewed)","url":"https://arxiv.org/abs/2610.13966","doi":"","pmid":"","brain_tumor_focus":"no","tags":["perturbation-prediction","flow-matching","optimal-transport","preprint"],"tag_slugs":["generative"],"tag_labels":["Generative AI & diffusion"],"tag_labels_zh":["生成式 AI 与扩散模型"],"unmapped_tags":["perturbation-prediction","optimal-transport","preprint"],"one_line_summary_en":"Preprint (not peer-reviewed): Yang and Su (Tianjin University) propose MRFlow, which treats perturbation prediction as latent conditional transport with flow matching; the authors report the highest composite score across eight gene and drug perturbation benchmarks (self-reported, single run).","one_line_summary_zh":"预印本（未经同行评审）：Yang 与 Su（天津大学）提出 MRFlow，将扰动预测视为潜空间条件传输并用流匹配实现；作者报告其在八个基因与药物扰动基准上综合得分最高（作者自报，单次运行）。","verified":"yes","verification_source":"arXiv abs page 2610.13966 (title, authors Haojie Yang & Ran Su, abstract, full text read 2026-10-19); exact submission date not retrieved (ID = Oct 2026); no peer-reviewed version found","page_url":"https://gliostate.com/library/VC0151/","api_url":"https://gliostate.com/api/items/VC0151.json","sameAs":["https://arxiv.org/abs/2610.13966"],"is_preprint":true,"facets":{"type":"https://gliostate.com/library/type/preprint/","year":"https://gliostate.com/library/year/2026/","tags":["https://gliostate.com/library/tag/generative/"]},"cited_by":[],"related":[{"id":"VC0138","title":"PerturbLDM: conditional latent diffusion for modelling single-cell perturbation responses","shared_tags":["generative"],"page_url":"https://gliostate.com/library/VC0138/","api_url":"https://gliostate.com/api/items/VC0138.json"},{"id":"VC0077","title":"Generative AI for spatial tumor growth on MRI: a proof-of-principle study in pediatric diffuse midline glioma.","shared_tags":["generative"],"page_url":"https://gliostate.com/library/VC0077/","api_url":"https://gliostate.com/api/items/VC0077.json"},{"id":"VC0033","title":"X-Cell: Scaling Causal Perturbation Prediction Across Diverse Cellular Contexts via Diffusion Language Models","shared_tags":["generative"],"page_url":"https://gliostate.com/library/VC0033/","api_url":"https://gliostate.com/api/items/VC0033.json"},{"id":"VC0137","title":"Towards building a World Model to simulate perturbation-induced cellular dynamics by AlphaCell","shared_tags":["generative"],"page_url":"https://gliostate.com/library/VC0137/","api_url":"https://gliostate.com/api/items/VC0137.json"},{"id":"VC0035","title":"CellFluxV2 : An Image Generative Foundation Model for Virtual Cell Modeling","shared_tags":["generative"],"page_url":"https://gliostate.com/library/VC0035/","api_url":"https://gliostate.com/api/items/VC0035.json"},{"id":"VC0028","title":"STPath: a generative foundation model for integrating spatial transcriptomics and whole-slide images.","shared_tags":["generative"],"page_url":"https://gliostate.com/library/VC0028/","api_url":"https://gliostate.com/api/items/VC0028.json"}]}