{"scope":{"layer":"general","tissue_scope":"unknown","species":"human","system":"unknown","evidence_level":"preprint","importance":"","importance_reason":""},"id":"VC0178","type":"preprint","title":"BioMod: Biological Module Tokenization for Single-Cell Foundation Modeling","authors_or_org":"Meng L, Zhu J, Han B, Zang Y, Li W, Zong K, Zhong J, Yang Y, Liu J, Jia J, Sun R, Yu G, Han J, Chen Y, Zhang L, Xu J.","date":"2026-10-13","year":"2026","venue":"bioRxiv (preprint, not peer-reviewed)","url":"https://doi.org/10.64898/2026.10.12.758490","doi":"10.64898/2026.10.12.758490","pmid":"","brain_tumor_focus":"no","tags":["foundation-model","scrna-seq","perturbation","drug-response"],"tag_slugs":["foundation-model","scrna-seq","perturbation","drug-response"],"tag_labels":["Foundation model","scRNA-seq","Perturbation","Drug response"],"tag_labels_zh":["基础模型","单细胞 RNA 测序","扰动","药物反应"],"unmapped_tags":[],"one_line_summary_en":"Preprint (not peer-reviewed): Meng et al. (Shenzhen Loop Area Institute) present BioMod, a 50-million-parameter single-cell foundation model that represents cells with an overlapping vocabulary of 660 biological modules (from curated pathways and data-driven gene programs) instead of individual genes, pretrained on about 73 million human cells. The authors report state-of-the-art performance on cell-type annotation, zero-shot batch integration, perturbation-response prediction and drug-response forecasting, with inference on a single GPU. Self-reported; no independent evaluation yet.","one_line_summary_zh":"预印本（未经同行评审）：Meng 等（深圳河套学院）提出 BioMod，一个 5000 万参数的单细胞基础模型，以 660 个相互重叠的生物模块（来自策展通路与数据驱动的基因程序）代替单个基因来表示细胞，在约 7300 万个人类细胞上预训练。作者报告其在细胞类型注释、零样本批次整合、扰动响应预测与药物响应预测上达到当前最佳，且可在单块 GPU 上推理。为作者自报结果，尚无独立评测。","verified":"yes","verification_source":"bioRxiv API details (title, 16 authors, posted 2026-10-13, v1, new results, bioinformatics, CC BY, corresponding institution Shenzhen Loop Area Institute, abstract) fetched 2026-10-20; full text not read","page_url":"https://gliostate.com/library/VC0178/","api_url":"https://gliostate.com/api/items/VC0178.json","sameAs":["https://doi.org/10.64898/2026.10.12.758490"],"is_preprint":true,"facets":{"type":"https://gliostate.com/library/type/preprint/","year":"https://gliostate.com/library/year/2026/","tags":["https://gliostate.com/library/tag/foundation-model/","https://gliostate.com/library/tag/scrna-seq/","https://gliostate.com/library/tag/perturbation/","https://gliostate.com/library/tag/drug-response/"]},"cited_by":[],"related":[{"id":"VC0008","title":"scGPT: toward building a foundation model for single-cell multi-omics using generative AI.","shared_tags":["foundation-model","scrna-seq","perturbation"],"page_url":"https://gliostate.com/library/VC0008/","api_url":"https://gliostate.com/api/items/VC0008.json"},{"id":"VC0152","title":"Computational deconvolution of drug sensitivity via single-cell-to-bulk transcriptome mapping","shared_tags":["drug-response","scrna-seq"],"page_url":"https://gliostate.com/library/VC0152/","api_url":"https://gliostate.com/api/items/VC0152.json"},{"id":"VC0176","title":"A multimodal precision oncology platform integrating genomics, single-cell transcriptomics, and functional drug screening expands therapeutic options in pediatric brain tumors","shared_tags":["scrna-seq","drug-response"],"page_url":"https://gliostate.com/library/VC0176/","api_url":"https://gliostate.com/api/items/VC0176.json"},{"id":"VC0132","title":"Drug and single-cell gene expression integration identifies sensitive and resistant glioblastoma cell populations","shared_tags":["scrna-seq","drug-response"],"page_url":"https://gliostate.com/library/VC0132/","api_url":"https://gliostate.com/api/items/VC0132.json"},{"id":"VC0138","title":"PerturbLDM: conditional latent diffusion for modelling single-cell perturbation responses","shared_tags":["drug-response","perturbation"],"page_url":"https://gliostate.com/library/VC0138/","api_url":"https://gliostate.com/api/items/VC0138.json"},{"id":"VC0147","title":"DELPHAI predicts heterogeneous perturbation responses with learned single-cell fitness","shared_tags":["perturbation","drug-response"],"page_url":"https://gliostate.com/library/VC0147/","api_url":"https://gliostate.com/api/items/VC0147.json"}]}